WO2004064393A1 - 放送受信方法、放送受信システム、記録媒体、及びプログラム - Google Patents
放送受信方法、放送受信システム、記録媒体、及びプログラム Download PDFInfo
- Publication number
- WO2004064393A1 WO2004064393A1 PCT/JP2003/017015 JP0317015W WO2004064393A1 WO 2004064393 A1 WO2004064393 A1 WO 2004064393A1 JP 0317015 W JP0317015 W JP 0317015W WO 2004064393 A1 WO2004064393 A1 WO 2004064393A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- additional information
- word
- broadcast
- recognition
- Prior art date
Links
- 238000000034 method Methods 0.000 title description 26
- 238000012937 correction Methods 0.000 claims description 52
- 230000005540 biological transmission Effects 0.000 claims description 16
- 230000002596 correlated effect Effects 0.000 abstract 3
- 230000000875 corresponding effect Effects 0.000 abstract 1
- 238000003860 storage Methods 0.000 description 174
- 230000014509 gene expression Effects 0.000 description 81
- 238000010586 diagram Methods 0.000 description 45
- 230000005236 sound signal Effects 0.000 description 38
- 230000006978 adaptation Effects 0.000 description 23
- 239000000284 extract Substances 0.000 description 22
- 230000002452 interceptive effect Effects 0.000 description 21
- 230000006870 function Effects 0.000 description 14
- 239000004065 semiconductor Substances 0.000 description 10
- 230000015654 memory Effects 0.000 description 9
- 238000000605 extraction Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 241000736199 Paeonia Species 0.000 description 1
- 235000006484 Paeonia officinalis Nutrition 0.000 description 1
- 241001441724 Tetraodontidae Species 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 239000000872 buffer Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/44—Receiver circuitry for the reception of television signals according to analogue transmission standards
- H04N5/445—Receiver circuitry for the reception of television signals according to analogue transmission standards for displaying additional information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/41—Structure of client; Structure of client peripherals
- H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
- H04N21/42203—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] sound input device, e.g. microphone
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/432—Content retrieval operation from a local storage medium, e.g. hard-disk
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
- H04N21/4332—Content storage operation, e.g. storage operation in response to a pause request, caching operations by placing content in organized collections, e.g. local EPG data repository
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/434—Disassembling of a multiplex stream, e.g. demultiplexing audio and video streams, extraction of additional data from a video stream; Remultiplexing of multiplex streams; Extraction or processing of SI; Disassembling of packetised elementary stream
- H04N21/4348—Demultiplexing of additional data and video streams
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/439—Processing of audio elementary streams
- H04N21/4394—Processing of audio elementary streams involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
- H04N21/44224—Monitoring of user activity on external systems, e.g. Internet browsing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/454—Content or additional data filtering, e.g. blocking advertisements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/4722—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for requesting additional data associated with the content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/47815—Electronic shopping
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
- H04N21/8405—Generation or processing of descriptive data, e.g. content descriptors represented by keywords
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04H—BROADCAST COMMUNICATION
- H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
- H04H60/35—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users
- H04H60/37—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users for identifying segments of broadcast information, e.g. scenes or extracting programme ID
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04H—BROADCAST COMMUNICATION
- H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
- H04H60/35—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users
- H04H60/48—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users for recognising items expressed in broadcast information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47214—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for content reservation or setting reminders; for requesting event notification, e.g. of sport results or stock market
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/08—Systems for the simultaneous or sequential transmission of more than one television signal, e.g. additional information signals, the signals occupying wholly or partially the same frequency band, e.g. by time division
- H04N7/087—Systems for the simultaneous or sequential transmission of more than one television signal, e.g. additional information signals, the signals occupying wholly or partially the same frequency band, e.g. by time division with signal insertion during the vertical blanking interval only
- H04N7/088—Systems for the simultaneous or sequential transmission of more than one television signal, e.g. additional information signals, the signals occupying wholly or partially the same frequency band, e.g. by time division with signal insertion during the vertical blanking interval only the inserted signal being digital
Definitions
- the present invention relates to a broadcast receiving method for receiving a broadcast broadcast from a broadcast station, a broadcast receiving system, a first device, a second device, a recording medium, and a program.
- the viewer may want to obtain an object such as a program or commercial that appeared in the program or music played in the program or commercial. .
- the viewer first connects a PC (Personal Computer) to the Internet, searches the Internet for information on these objects, and obtains information on the target objects.
- PC Personal Computer
- FIG. 37 is a block diagram showing a conceptual configuration of a shopping support system using interactive broadcasting in the inventor's application according to the present application.
- Fig. 38 is a flowchart showing the operation of the shopping support system using interactive broadcasting (hereinafter abbreviated as shopping support system).
- FIG. 39 is a functional block diagram showing details of the portion shown in FIG. 37.
- the shopping support system includes a broadcasting station 10, a seller 20, and a home 30.
- a TV / STB 310 and a remote controller 320 are installed in the home 30, a TV / STB 310 and a remote controller 320 are installed. I have.
- the broadcasting station 10 is a broadcasting station that broadcasts a program together with program additional information.
- Distributor 20 is a distributor that handles items appearing in the program as products.
- Home 30 is the home that receives the broadcast. ,
- TV / STB 31.0 is a two-way broadcast receiver such as a television or an STB (Set Top Box).
- the remote controller 320 is means for operating the TV / STB 310, and includes a microphone 3221.
- the TV / STB 310 includes a recognized vocabulary storage unit 311 and a voice recognition unit 312. That is, as shown in FIG. 39, TVZS TB 310 is Broadcast receiving unit 3 1 3, Recognized vocabulary generation unit 3 1 4, Recognized vocabulary storage unit 3 1 1, Voice recognition unit 3 1 2, Time expression dictionary 3 1 6, Storage time control unit 3 1 5, Additional information storage It consists of a unit 317, a display unit 318, and a transmission unit 319.
- the broadcast receiving section 313 is a means for receiving a broadcast wave.
- the recognition vocabulary generator 314 is a means for generating a target vocabulary for speech recognition from the program additional information received by the broadcast receiver 313.
- the recognized vocabulary storage unit 311 1 is a means for storing the generated recognized vocabulary.
- the time expression dictionary 3 16 is a dictionary that holds expressions relating to time, such as “soon ago” and “now,” as recognition vocabulary.
- the speech recognition unit 312 is a means for performing speech recognition using the recognition vocabulary storage unit 311 and the temporal expression dictionary 316 as a recognition vocabulary dictionary.
- the memory time controller 3 15 learns the relationship between each time expression vocabulary and the actual time width or the number of scenes from the relationship between the recognized time expression vocabulary and the viewer's information selection input, and performs speech recognition.
- the display section 318 is a means for displaying additional information.
- the transmitting unit 319 is means for transmitting the result of viewer input, such as selection of additional information, to the broadcasting station.
- FIG. 38 shows the operation of the shopping support system and services. This will be described below with reference to FIG.
- the viewer pays attention to things appearing in the program while watching the program, and utters words to convey that he / she is paying attention to a specific thing.
- the microphone 321 inputs the utterance and outputs the utterance to the voice recognition unit 312.
- the speech recognition unit 312 performs speech recognition on the utterance signal input from the microphone 3221. Then, based on the result of the voice recognition, the voice recognition unit 312 determines an object or the like to which the viewer pays attention, and specifies the corresponding program additional information. And store it in the additional information storage unit 3 17 (step 3 31).
- the voice uttered by the viewer is input from the microphone 3 2 1, and the voice recognition unit 3 1 2 recognizes the input voice by referring to the time expression dictionary 3 16 and the recognized vocabulary storage unit 3 1 1, and is broadcast.
- the corresponding additional information is extracted from the added program additional information.
- the recognition vocabulary stored in the recognition vocabulary storage unit 3 1 1 was generated by the recognition vocabulary generation unit 3 14, which sequentially generated vocabulary representing objects with added information and music from the received program additional information. Things. That is, the program additional information also includes key word information for specifying an object or music associated with the program additional information at the broadcasting station, and the recognition vocabulary generator 314 recognizes the key word information from the keyword information. Generate vocabulary.
- the speech recognition unit 312 extracts the recognition vocabulary from the uttered voice of the viewer by voice-recognizing the uttered voice of the viewer such as “I wish the red jacket just before”. For example, in the case of the utterance speech “I just like the red jacket,” the recognition vocabulary “red” and “jacket” are extracted. Then, the program additional information having the largest number of pieces of keyboard information corresponding to the extracted recognized vocabulary is selected, and the selected program additional information is stored in the additional information storage unit 317. In other words, if a certain program additional information includes both keyword information corresponding to the recognition vocabulary “red” and keyword information corresponding to the recognition vocabulary “jacket”, the program additional information is stored in the additional information. Store in part 3 17.
- the voice recognition unit 312 can be specified by selecting the program additional information.
- the speech recognition unit 312 has been described as selecting the program additional information having the largest number of pieces of keyword information corresponding to the recognized vocabulary extracted from the uttered voice of the viewer, but is not limited thereto.
- the voice recognition unit 312 selects, for example, five pieces of program additional information in the descending order of the number of pieces of keyword information corresponding to the recognized vocabulary extracted from the uttered voice of the viewer, and adds the selected program additional information to the additional information.
- the information may be stored in the storage unit 3 17. As described above, the voice recognition unit 312 may narrow down the program additional information instead of specifying it.
- the storage time controller 3 15 has a large time width or scene number corresponding to the predetermined time range or scene number, or the time expression learned from the viewer's previous utterance and subsequent input. During this time, control is performed so that the generated recognition vocabulary is maintained.
- the learning of the storage time control unit 315 will be described later. For example, in the case of an uttered voice saying “I'm looking forward to the red jacket,” the voice recognition unit 312 extracts the temporal expression vocabulary indicating the past “Soon ago” under the control of the storage time control unit 315. Then, referring to the time expression dictionary 31.6, the above-mentioned identification or narrowing down is performed on the program additional information broadcast during the time range or the number of scenes corresponding to “Saki”.
- the display unit 318 displays additional information corresponding to the thing appearing in the specified drama by voice recognition (step 3333).
- the additional information includes information such as size, weight, material, different colors, different sizes, prices, manufacturers, sellers, and seller contact information, etc.
- additional information is selected by a remote controller 320 or a pointing device or input means such as voice recognition and the purchase information is input.
- the transmission unit 3 19 matches the purchase information with the identification number of the corresponding additional information, etc. To the broadcast station (step 3 3 4).
- the storage time control unit 3 15 learns the relationship between each time expression vocabulary and the actual time width or the number of scenes from the relationship between the recognized time expression vocabulary and the information selection input of the viewer.
- the storage time control unit 315 holds information for associating the actual time width or the number of scenes for each recognition vocabulary, which is an expression relating to time, stored in the time expression dictionary 316.
- the storage time control unit 3 15 associates the recognition vocabulary “Saki” with the time range from 20 seconds ago to 5 minutes ago based on the current time. The time width from the current time to 30 seconds before the current time is associated with the current time.
- the speech recognition unit 312 performs control to specify and narrow down the program additional information received during the time period up to the previous time from 20 seconds before the current time. Identify and narrow down the program additional information received during the time width up to 5 minutes before, and store the specified or narrowed down program additional information in the additional information storage unit 3.
- the storage time control unit 315 controls so that the recognition vocabulary generated during this time width is retained.
- the storage time control unit 3 15 receives the recognition vocabulary representing the time expression “soon ago”, the storage time control unit 3 15
- the program additional information displayed in 18 may be different from the time width intended by the viewer.
- the viewer speaks into the microphone 321, saying “redo”, “want to display information before”, “want to display information after”.
- the voice recognition unit 312 performs voice recognition of the utterance from the viewer, and notifies the storage time control unit 315 of the voice recognition result.
- the voice recognition unit 3 1 2 recognizes the utterance “I want you to display the information before it”, it extracts “previous”, “information”, and “display” as the recognition vocabulary, and stores the memory time. Notify the control unit 3 15.
- the memory time control unit 3 15 When the memory time control unit 3 15 receives the recognition vocabulary of “before”, “information”, and “display” from the speech recognition unit 3 12, it is associated with the recognition vocabulary representing the time expression of “previous”. Correct the time width information. In other words, it is modified so that the recognition vocabulary "Saki” is associated with the time width from 40 seconds ago to 5 minutes 40 seconds ago based on the current time. Then, the storage time control unit 3 15 adds the program to the speech recognition unit 3 12 again for the program additional information received from 40 seconds ago to 5 minutes 40 seconds ago based on the current time. The voice recognition unit 3 1 2 is controlled so as to specify or narrow down the information.
- the voice recognition unit 312 again specifies or narrows down the program additional information under the control of the storage time control unit 315, and stores the specified or narrowed down program additional information in the additional information storage unit 317.
- the display unit 318 displays the program additional information stored in the additional information storage unit 317. Then, if the displayed program additional information includes a target item, the viewer selects the program additional information and inputs purchase information.
- the storage time control unit 315 can reflect the viewer's intention and associate the time width with the recognized vocabulary representing the time expression. This means that the storage time control unit 315 learns.
- the viewers are interested in the objects, music, etc. appearing in the program. Make natural utterances Thus, it is possible to acquire and purchase information continuously after viewing the program.
- the degree of matching between the speech-recognized word and the keyword corresponding to the keyword information including the additional information is determined.
- additional information is specified.
- the present invention has been made in consideration of the above problems, and provides a broadcast receiving method, a broadcast receiving system, a first apparatus, and a broadcast receiving method that can easily obtain a broadcast program or an object appearing in a commercial without much trouble. It is intended to provide two devices, a recording medium, and a program.
- Broadcast receiving method, broadcast receiving system, first device, second device, recording that can be easily and easily obtained by adapting the object appearing in The purpose is to provide media and programs.
- the present invention provides a broadcast receiving method and a broadcast receiving method which can easily obtain a broadcasted program or an object appearing in a commercial so as to be suitable for a viewer's interest without any hassle. It is intended to provide a receiving system, a first device, a second device, a recording medium, and a program.
- a first aspect of the present invention is a keyword associated with an object appearing in broadcast content broadcasted from a broadcast station, the keyword being for identifying the object.
- a display step of displaying additional information associated with the specified keyword information is a display step of displaying additional information associated with the specified keyword information.
- the second invention provides the additional information, which is additional information associated with an object appearing in broadcast content broadcasted from a broadcasting station and includes keyword information for specifying the object. Broadcast information and language model to the broadcast content A receiving step of receiving a broadcast to be broadcast at the same time;
- a synonym dictionary in which a plurality of words are classified into respective word classes based on the similarity between words, the frequency and / or frequency of occurrence of the predetermined combination of the word classes in the expression form of the language model Or a correction step of correcting the frequency of occurrence of a predetermined word based on the predetermined word class in the expression form of the language model based on history information of a voice recognition result of voice recognition that has already been performed;
- a display step of displaying additional information associated with the specified keyword information is a display step of displaying additional information associated with the specified keyword information. .,
- the third aspect of the present invention is the above-mentioned additional information, wherein the additional information includes keyword information for specifying the object, the additional information being associated with the object appearing in the broadcast content broadcast from the broadcast station.
- the voice uttered by the viewer is A voice recognition step to recognize
- a display step of displaying additional information associated with the specified keyword information is a display step of displaying additional information associated with the specified keyword information.
- the fourth present invention provides the additional information, which is additional information associated with an object appearing in broadcast content broadcast from a broadcasting station and includes keyword information for identifying the object.
- a first device having broadcasting means for broadcasting simultaneously with the broadcast content;
- Receiving means for receiving the broadcast from the first device; and a keyword dictionary using a synonym dictionary in which a plurality of words are classified into respective word classes on the basis of synonyms between words.
- Recognition vocabulary set generation means for generating a recognition vocabulary set composed of words belonging to the word class including words corresponding to information in association with the additional information, and a voice for recognizing a voice uttered by a viewer Recognition means, and when the word recognized by the speech recognition result is included in the recognized vocabulary set, specifying means for specifying the keyword information corresponding to the recognized vocabulary set, and corresponding to the specified keyword information
- a second device having display means for displaying the attached additional information.
- the additional information includes keyword information for identifying the object, the additional information being associated with the object appearing in the broadcast content broadcast from the broadcast station.
- a first device having broadcasting means for broadcasting information and a language model simultaneously with the broadcast content;
- the predetermined unit in a model expression form; History of speech recognition results of speech recognition that has already performed the frequency of occurrence of a combination of word classes and the frequency of occurrence of a predetermined word based on the predetermined word class in z or the expression format of the language model.
- a second device having a display unit for displaying additional information associated with the specified keyword information.
- the sixth invention is directed to additional information associated with an object appearing in the broadcast content broadcast from a broadcasting station, and including additional keyword information for specifying the object.
- a first device having broadcasting means for broadcasting the additional information and information for specifying the language model simultaneously with the broadcast content; a receiving means for receiving the broadcast broadcasted from the first device; and Using the information for specifying the language model, a plurality of words are assigned to each word class on the basis of language model specifying means for specifying the language model stored in advance, and similarity between words.
- Correcting means for correcting the appearance degree of a predetermined word based on the predetermined word class based on history information of a speech recognition result of speech recognition that has been performed, and the corrected language model.
- Voice recognition means for recognizing a voice uttered by the viewer, and a specifying means for specifying the keyword information based on the voice recognition result, and an addition associated with the specified keyword information.
- a broadcast receiving system comprising: a second device having display means for displaying information.
- the broadcast corresponds to the keyword information by using a synonym dictionary in which a plurality of words are classified into respective word classes based on receiving means for receiving the broadcast, and synonyms between words.
- a recognition vocabulary set generating means for generating a recognition vocabulary set composed of words belonging to the word class including words in association with the additional information, and a voice recognition means for voice recognition of a voice uttered by a viewer; And when the word recognized by the speech recognition result is included in the recognized vocabulary set, the key corresponding to the recognized vocabulary set.
- a first device that is received by a second device having a display unit that displays the additional information obtained.
- the eighth invention is directed to the additional information which includes additional information associated with an object appearing in the broadcast content broadcasted from a broadcasting station and includes keyword information for specifying the object.
- the broadcast is a receiving means for receiving the broadcast, and a synonym dictionary in which a plurality of words are classified into respective word classes on the basis of synonyms between words.
- the frequency of occurrence of the predetermined combination of the word classes and / or the frequency of occurrence of the predetermined word based on the predetermined word class in the expression form of the language model.
- Correction means for correcting based on the history information of the result; and voice recognition means for recognizing voice uttered by the viewer using the corrected language model; and the key based on the voice recognition result.
- Specifying means for specifying the key information, and the specified key information A first device which is received by a second device having a display means for displaying additional information associated with the first device.
- the ninth aspect of the present invention is the additional information, wherein the additional information includes keyword information for identifying the object, the additional information being associated with the object appearing in the broadcast content broadcast from the broadcast station.
- the broadcast includes: a receiving unit that receives the broadcast; and a language model specifying unit that specifies the language model stored in advance by using information for specifying the received language model.
- a synonym dictionary in which a plurality of words are classified into respective word classes on the basis of synonymity, a combination of the predetermined word classes in the expression form of the specified language model appears.
- the frequency of occurrence of a predetermined word in the expression form of Z or the specified language model based on the predetermined word class is corrected based on the history information of the voice recognition result of the voice recognition that has already been performed.
- voice recognition means for recognizing a voice uttered by a viewer, and the key based on the voice recognition result.
- Specifying means for specifying the over de information, and is received by a second device having a display means for displaying additional information associated with the identified said Kiwado information, which is the first device.
- the tenth aspect of the present invention is the additional information, wherein the additional information includes keyword information for identifying the object, the additional information being associated with the object appearing in the broadcast content broadcast from the broadcast station.
- Receiving means for receiving the broadcast broadcasted from the first device having broadcast means for broadcasting simultaneously with the broadcast content;
- a recognition vocabulary set generating means for generating a recognition vocabulary set composed of words belonging to the notation word class in association with the additional information
- Voice recognition means for recognizing a voice uttered by a viewer; and, when a word recognized by the voice recognition result is included in the recognized vocabulary set, the keyword information corresponding to the recognized vocabulary set is specified.
- a predetermined appearance frequency is added to each word of the synonym dictionary
- the voice recognition unit specifies the word having a higher appearance frequency as a word recognized in the voice recognition result. This is the second device.
- a twelfth aspect of the present invention is the second device according to the eleventh aspect of the present invention, further comprising an appearance frequency correction unit that rewrites the appearance frequency according to the recognition result of the speech recognition result.
- a thirteenth aspect of the present invention includes an appearance frequency correction unit for rewriting the appearance frequency corresponding to each word of the recognition vocabulary set according to the history information of the speech recognition result,
- the appearance frequency corresponding to the word is added.
- the speech recognition means is the second device of the present invention, wherein the speech recognition is performed using the appearance frequency of the recognized vocabulary set.
- the fourteenth invention is directed to the additional information, which is additional information associated with an object appearing in broadcast content broadcasted from a broadcasting station and includes key word information for specifying the object.
- the language model in the broadcast Receiving means for receiving the broadcast broadcasted from the first device having broadcast means for broadcasting at the same time;
- a correction means for correcting the frequency of occurrence of a predetermined word based on the predetermined word class in the expression form of the language model based on history information of a voice recognition result of voice recognition that has already been performed,
- Voice recognition means for recognizing voice uttered by the viewer using the corrected language model
- the fifteenth aspect of the present invention provides the additional information, wherein the additional information includes keyword information for identifying the object, the additional information being associated with the object appearing in the broadcast content broadcast from the broadcast station. And receiving means for receiving the broadcast broadcasted from the first device having broadcast means for broadcasting information for specifying a language model simultaneously with the broadcast content;
- language model specifying means for specifying the language model stored in advance
- a predetermined combination of the word classes in the expression form of the specified language model is determined.
- the frequency of occurrence and / or the frequency of occurrence of a predetermined word based on the predetermined word class in the specified expression format of the language model is determined by the speech recognition result of the already performed speech recognition.
- Voice recognition means for recognizing voice uttered by the viewer using the captured language model
- a display device for displaying additional information associated with the identified keyword information.
- a sixteenth aspect of the present invention is the second device according to the fifteenth aspect of the present invention, wherein the information for specifying the language model is an ID assigned to the language model in advance.
- the information for specifying the language model is language model specifying keyword information
- the language model identification keyword information is also added to the language model stored in advance,
- the language model specifying means is a second device according to a fifteenth aspect of the present invention, wherein the language model is specified in accordance with the degree of matching of the language model specifying keywords.
- an eighteenth aspect of the present invention relates to a case where the correction means corrects the appearance frequency of a predetermined word based on the predetermined word class in the expression form of the language model,
- the history information includes a word recognized by the already performed speech recognition
- the correction means extracts a word included in the word class including a word corresponding to the keyword information
- a nineteenth aspect of the present invention relates to a case where the correcting means corrects the frequency of occurrence of the predetermined combination of the word classes in the expression form of the language model,
- the history information includes a word recognized by the already performed speech recognition
- the correction means extracts a word class including a word corresponding to the keyword information
- the frequency of occurrence of a predetermined combination of the word classes in the expression form of the language model is increased, and with respect to the word class not extracted, in the expression form of the language model, A second device according to any one of the 14th to 17th inventions, wherein the frequency of occurrence of the word class after the predetermined word class sequence is reduced.
- the correcting means corrects the frequency of occurrence of the predetermined combination of the word classes in the expression form of the language model
- the history information includes a word class including a word recognized by the already performed speech recognition,
- the correction means extracts a word class corresponding to the keyword information, and increases a frequency of occurrence of a predetermined combination of word classes in the expression form of the language model with respect to the extracted word class.
- the second device according to any one of the 14th to 17th inventions, which reduces a frequency of occurrence of a predetermined combination of word classes in the expression of the language model with respect to the word classes that have not been extracted. It is.
- the twenty-first aspect of the present invention includes a transmission unit that transmits, when a predetermined operation is performed on the displayed additional information, an instruction corresponding to the predetermined operation to a predetermined destination.
- a second device according to any one of the tenth to seventeenth aspects of the present invention. .
- the twenty-second aspect of the present invention provides the program additional information product sales information and / or service sales information.
- the instruction corresponding to the predetermined operation is the second device according to the twenty-first aspect of the present invention, which is information requesting or purchasing information of the product and Z or the service.
- a twenty-third aspect of the present invention is the second device according to the fifteenth aspect of the present invention, wherein the language model stored in advance is obtained using a network in advance.
- a twenty-fourth aspect of the present invention is the tenth aspect of the second apparatus of the present invention, which is additional information associated with an object appearing in broadcast content broadcast from a broadcast station, and Receiving means for receiving the broadcast broadcasted from the first device having broadcast means for broadcasting the additional information including the keyword information for specifying simultaneously with the broadcast content;
- a recognition vocabulary set generating means for generating a vocabulary set in association with the additional information
- Voice recognition means for recognizing voice uttered by the viewer
- the word recognized by the speech recognition result is included in the recognized vocabulary set Specifying the keyword information corresponding to the recognized vocabulary set,
- a program for causing a computer to function as display means for displaying the additional information associated with the specified keyword information is the second device of the fifteenth aspect of the present invention, which is additional information associated with an object appearing in broadcast content broadcast from a broadcasting station, and Receiving means for receiving the broadcast broadcast from a first device having a broadcast means for broadcasting the additional information and language model including keyword information for specifying at the same time as the broadcast content;
- Voice recognition means for recognizing voice uttered by the viewer using the corrected language model
- a twenty-sixth aspect of the present invention is the second device of the fifteenth aspect of the present invention, which is additional information associated with an object appearing in broadcast content broadcast from a broadcasting station, and A receiver for receiving the broadcast broadcasted from a first device having broadcasting means for simultaneously broadcasting the additional information including the keyword information for specifying and the language model for specifying the language model; Steps and
- a language model specifying means for specifying the language model stored in advance, and a plurality of words based on the similarity between words.
- the frequency of occurrence of the predetermined combination of the word classes and the expression of Z or the specified language model in the expression form of the specified language model Correcting means for correcting the appearance frequency of a predetermined word based on the predetermined word class in a format based on history information of a voice recognition result of voice recognition already performed;
- Voice recognition means for recognizing voice uttered by the viewer using the corrected language model
- a program for causing a computer to function as display means for displaying additional information associated with the specified keyword information is a recording medium carrying the program of the twenty-fourth aspect of the present invention, which is a recording medium that can be processed by a computer.
- a twenty-eighth aspect of the present invention is a recording medium carrying the program of the twenty-fifth aspect of the present invention, which is a recording medium that can be processed by a computer.
- a twentieth aspect of the present invention is a recording medium that carries the program of the twenty-sixth aspect of the present invention, and is a recording medium that can be processed by a computer.
- FIG. 1 is a block diagram showing a schematic configuration of a shopping support system according to Embodiment 1 of the present invention.
- FIG. 2 is a block diagram showing a configuration of a TV / STB according to the first embodiment of the present invention. Lock diagram
- FIG. 3 is a block diagram showing a detailed configuration of the recognition vocabulary generation unit according to the first embodiment of the present invention.
- FIG. 4 is a flowchart showing an outline of the operation of the shopping support system according to the first embodiment of the present invention.
- FIG. 5 is a diagram illustrating an example of a synonym dictionary according to the first embodiment of the present invention.
- FIG. 6 is a flowchart illustrating details of the operation of the shopping support system according to the first embodiment of the present invention.
- FIG. 7 is a diagram illustrating an example of a recognized vocabulary set according to the first embodiment of the present invention.
- FIG. 8 is a flowchart illustrating details of the operation of the shopping support system according to the first embodiment of the present invention.
- FIG. 9 is a block diagram showing the configuration of TV / STB according to Embodiment 2 of the present invention.
- FIG. 10 is a block diagram showing a detailed configuration of a recognition vocabulary generation unit 360 in Embodiment 2 of the present invention.
- FIG. 11 is a diagram illustrating an example of a synonym dictionary according to the second embodiment of the present invention.
- FIG. 12 is a flowchart illustrating details of the operation of the shopping support system according to the second embodiment of the present invention.
- FIG. 13 is a diagram illustrating an example of a recognized vocabulary set according to the second embodiment of the present invention.
- FIG. 14 is a diagram showing an example of a recognized vocabulary set in which frequency is standardized according to the second embodiment of the present invention.
- FIG. 15 is a flowchart showing details of the operation of the shopping support system according to the second embodiment of the present invention.
- FIG. 16 is a block diagram showing the configuration of TVZSTB in Embodiment 3 of the present invention.
- FIG. 17 is a flowchart showing an outline of the operation of the shopping support system according to the third embodiment of the present invention.
- FIG. 18 is a flowchart showing details of the operation of the shopping support system according to the third embodiment of the present invention.
- FIG. 19 is a diagram illustrating an example of Ngram grammar information according to Embodiment 3 of the present invention.
- FIG. 20 is a diagram for explaining the operation of the vocabulary weight correcting unit according to the third embodiment of the present invention.
- FIG. 21 is a block diagram showing a configuration of TVZS TB according to Embodiment 4 of the present invention.
- FIG. 22 is a flowchart showing an outline of the operation of the shopping support system according to the fourth embodiment of the present invention.
- FIG. 23 is a flowchart showing details of the operation of the shopping support system according to the fourth embodiment of the present invention.
- FIG. 24 is a diagram showing an example of P (C i. I C M) of Formula 4 in Embodiment 4 of the present invention.
- FIG. 25 is a diagram for explaining the operation of the class weight correction unit according to the fourth embodiment of the present invention.
- FIG. 26 is a block diagram showing a configuration of a program additional information automatic creation device according to the related art 1 of the present invention.
- FIG. 27 is a flowchart showing the operation of the program additional information automatic creation device according to the related art 1 of the present invention.
- FIG. 28 is a diagram showing a relationship between a camera, a fixed position transmitter, and an additional information code transmitter in Related Art 1 of the present invention.
- FIG. 29 is a block diagram showing a configuration of a TV / STB according to the fifth embodiment of the present invention.
- FIG. 30 is a flowchart showing the operation of the shopping support system using bidirectional broadcasting according to the fifth embodiment of the present invention.
- FIG. 31 is a block diagram showing a configuration of a TV / STB according to the sixth embodiment of the present invention.
- FIG. 32 is a flowchart showing the operation of the shopping support system using interactive broadcasting according to the sixth embodiment of the present invention.
- FIG. 33 is a diagram showing an example of a list of product information according to the sixth embodiment of the present invention.
- FIG. 34 is a block diagram showing a configuration of a TVZS TB according to the seventh embodiment of the present invention.
- FIG. 35 is a flowchart showing the operation of the shopping support system using the interactive broadcast 'according to the seventh embodiment of the present invention.
- FIG. 36 is a flowchart showing an operation different from that of FIG. 35 of the shopping support system using interactive broadcasting according to the seventh embodiment of the present invention.
- FIG. 37 is a diagram showing the invention according to the present application. Block diagram showing the conceptual configuration of a shopping support system using interactive broadcasting in the applicant's application
- Fig. 38 is a flowchart showing the operation of the shopping support system by interactive broadcasting in the inventor's application according to the present application.
- Fig. 39 is a block diagram showing the detailed configuration of the shopping support system by interactive broadcasting in the 'inventor's application according to the present application.
- FIG. 1 is a block diagram showing a conceptual configuration of a shopping support system using interactive broadcasting according to Embodiment 1 of the present invention.
- a functional block diagram showing the details of the shopping support system (hereinafter referred to as the shopping support system) using i-way broadcasting in Fig. 2 is shown.
- the shopping support system includes a broadcasting station 10, a seller 20, and a home 30.
- the home 30 includes a TV / STB 310, a remote controller There are 3 20 installed.
- the broadcasting station 10 is a broadcasting station that broadcasts a program together with program additional information. Five
- Distributors 20 are distributors that handle items that appear in programs as products.
- Home 30 is the home that receives the broadcast.
- the TV / STB 310 is a two-way broadcast receiver as a television or an STB (Set Top Box), which is a two-way broadcast receiver.
- the remote controller 320 is a means for operating the TV / STB 310 and includes a microphone 3221.
- the TV / STB 310 includes a recognized vocabulary storage unit 351, a voice recognition unit 352, and the like.
- the TV / STB 310 is composed of a radio transmitting / receiving unit 3 13, a recognized vocabulary generation unit 354, a recognized vocabulary storage unit 3 51, a speech recognition unit 3 52 2, and a time expression dictionary. It consists of 3 16, storage time control section 3 15, additional information storage section 3 17, display section 3 18, and transmission section 3 19.
- the broadcast receiving section 3 13 is a means for receiving broadcast radio waves.
- the recognition vocabulary generation unit 354 is means for generating a recognition vocabulary set, which is a target vocabulary for speech recognition, from the program additional information received by the broadcast receiving unit 3 13.
- the recognition vocabulary storage unit 351 is a means for storing the generated recognition vocabulary set.
- the time expression dictionary 3 16 is a dictionary that holds expressions relating to time, such as “soon ago” and “now,” as recognition vocabulary.
- the speech recognition unit 352 is a means for performing speech recognition using the recognition vocabulary storage unit 351 and the time expression dictionary 316 as a recognition vocabulary dictionary.
- the memory time controller 3 15 learns the relationship between each time expression vocabulary and the actual time width or the number of scenes from the relationship between the recognized time expression vocabulary and the viewer's information selection input, and performs speech recognition. This is a means for controlling the section 3 52 and the recognized vocabulary storage section 3 51.
- the additional information storage unit 317 is means for storing additional information corresponding to an object in a program specified by voice recognition.
- the display unit 318 is a means for displaying additional information.
- the transmitting unit 319 is means for transmitting the input result of the viewer such as selection of additional information to the broadcasting station.
- Fig. 3 shows the detailed configuration of the recognition vocabulary generator 354.
- the generating unit 354 includes a recognized vocabulary extracting unit 355, a recognized vocabulary extending unit 357, a synonym dictionary 356, and a recognized vocabulary adapting unit 358.
- the recognition vocabulary extraction unit 355 is means for extracting a word corresponding to the keyword information included in the program additional information as a keyword.
- the recognition vocabulary extension section 357 is a means for generating a recognition vocabulary set by expanding the extracted keywords.
- the synonym dictionary 356 is a dictionary in which a plurality of words are classified into respective word classes based on the similarity between words. In the first embodiment, it is assumed that one word is always included in only one specific word class, and one word is not included in a plurality of word classes. The case where one word is included in a plurality of word classes will be described in detail in a second embodiment.
- the recognition vocabulary adaptation unit 358 is means for correcting the frequency of occurrence of each word described in the synonym dictionary 356 according to the speech recognition result.
- FIG. 4 is a flowchart showing an outline of the operation of the shopping support system according to the present embodiment.
- 6 and 8 are flowcharts showing details of the operation of the shopping support system according to the present embodiment. Hereinafter, description will be made based on FIGS. 4, 6, and 8.
- the broadcast receiver 3 13 receives this broadcast. Then, the recognition vocabulary generation unit 354 extracts the keyword information included in the program additional information (Step 351). Further, the recognition vocabulary generation unit 354 extracts a synonym of the keyword corresponding to the keyword information (step 352). Further, the recognition vocabulary generation unit 354 stores the extracted synonyms in the recognition vocabulary storage unit 351 as a recognition vocabulary set (step 353). Next, when the viewer speaks, the speech is recognized, the result is fed back to the synonym dictionary 390, and the weight is added to the recognized word in the synonym dictionary (step 354).
- steps 3 51, 3 52, and 3 53 will be described in detail, then the operation of voice recognition will be described, and then the operation of step 3 54 will be described in detail. .
- steps 351, 352, and 3553 will be described in more detail with reference to FIGS.
- Figure 5 shows the synonym dictionary 390.
- the synonym dictionary 39 0 is a dictionary that describes the word 39 1, the reading 3 9 2 of the word, the word class 3 9 3 containing the word, and the frequency 3 9 4 of the word. is there.
- a word class is a class in which a plurality of words are classified based on the similarity between words.
- the appearance frequency 3994 in the word class obtained from the sufficiently large Japanese corpus is described.
- the jacket reading 3992 is a jacket
- the word class 3993 containing the jacket is clothing
- the word class of the jacket is clothing.
- the appearance frequency 394 of the appearance of the jacket among the included words is 0.20.
- the reading of the jacket 392 is ⁇ ⁇
- the word class 393 containing 3 ⁇ is clothing and the word class of the jacket
- the appearance frequency 394 of the words included in the clothing in which the outerwear appears is 0.10.
- step 365 it is assumed that additional information of the jacket has been sent as additional information.
- the additional information in addition to the keyword information indicating the jacket, includes the price, color, and size of the jacket. Includes any descriptions and descriptions of jacket vendors.
- the additional information includes information about a product to which the additional information is associated in addition to the keyword information. The details of the additional information will be described later.
- the recognized vocabulary extraction unit S355 extracts keyword information included in the additional information. That is, when the additional information of the jacket is sent, the information corresponding to the jacket is extracted as the keyword information.
- the recognition vocabulary extension unit 357 uses the synonym dictionary 356 to generate a recognition vocabulary set including words belonging to the same word class 393 as the keyword corresponding to the extracted keyword information. You. ⁇
- the recognition vocabulary extraction unit 355 extracts a jacket, which is a keyword corresponding to the keyword information, from the additional information.
- the recognition vocabulary extension unit 357 extracts the word whose word class is clothing because the word class 393 including the jacket that is the keyword is clothing.
- the words whose word class 393 is clothing are jackets, jackets, and clothes.
- the recognition vocabulary extension unit 357 sets the jacket, the jacket, and the clothes as words constituting the recognition vocabulary set.
- the appearance frequency 394 corresponding to each word is described in the recognized vocabulary set.
- Figure 7 shows the recognition vocabulary set 395 created in this way. The readings of the jacket, the moon, and the jacket are described as jacket, fuku, and ⁇ ⁇ gi, respectively. Then, it can be seen that the frequency 397 in the word class is described as 0.2, 0.3, 0.1, etc. corresponding to the reading 3996.
- step 357 the recognition vocabulary extension unit 357 generates The recognized vocabulary set is stored in the recognized vocabulary storage unit 351 in association with the additional information.
- the recognition vocabulary storage unit 351 is a semiconductor memory or a hard disk device. Therefore, the generated recognition vocabulary set is stored in the semiconductor memory or the hard disk device in a format that can be associated with the additional information.
- Fig. 2 first, the viewer pays attention to things appearing in the program while watching the program, and utters a word to convey that he / she is paying attention to a specific thing. Then, the microphone 3 2 1 inputs the utterance and outputs it to the voice recognition unit 3 52.
- the speech recognition section 352 performs speech recognition on the utterance signal input from the microphone 3221. Then, based on the result of the voice recognition, the voice recognition unit 352 determines an object or the like to which the viewer pays attention, specifies the corresponding program additional information, and stores it in the additional information storage unit 317.
- the voice uttered by the viewer is input from the microphone-mouth phone 3 2 1, and the voice recognition unit 3 52 recognizes the input voice by referring to the time expression dictionary 3 16 and the recognized vocabulary storage unit 3 51,
- the relevant additional information is extracted from the broadcasted program additional information.
- the recognized vocabulary set 395 shown in FIG. 7 includes the word outerwear. Specifies the recognition vocabulary set 3 95.
- a word having a higher frequency 397 in the word class of the recognized vocabulary set 395 is spoken. Identify as a word recognized in the recognition result.
- the frequencies 397 in the word class of the plurality of words are directly compared with each other, and the speech recognition unit 352 may specify the word having the higher frequency 397 in the word class.
- the voice recognition results When the garage is recognized as a voice recognition sign, the word class clothing that includes the jacket and the building that is the word class that includes the garage have the same weight, that is, are treated equally. Then, the frequency 397 in the word class of the jacket is directly compared with the frequency 397 of the word class in the garage, and the one with the higher frequency 397 in the word class is identified as the word recognized as speech.
- each word class including the plurality of words is used.
- the frequency of occurrence of each word class has been described as being equal, but the frequency of occurrence of each word class is determined in advance from the sufficiently large Japanese corpus, and the frequency of occurrence of each word class is determined in advance. Considering the above, the words in the speech recognition result can be specified more accurately.
- the weight of each word class is broadcast by data broadcasting from the broadcasting station 10, the weight of each word class is received by the broadcast receiving unit 3 13, and the weight of each word class received by the voice recognition unit 3 52 is received. Weight can also be considered.
- TV / STB 310 and network For example, when a product is purchased from the Internet website through a PC connected by a network, the purchase history information is acquired, the weight of each word class is generated from the acquired purchase information, and the speech recognition unit is used. It is also possible to use it for speech recognition in 352.
- the speech recognition unit 352 identifies the recognition vocabulary set 395 in FIG. 7, the speech recognition unit 352 stores the recognition vocabulary set 395 in the additional information storage unit 317.
- the additional information of the jacket which is the additional information corresponding to 5, is stored.
- the keyword corresponding to the keyword information included in the additional information broadcast from broadcast station 10 is a jacket
- a recognized vocabulary set is generated to perform speech recognition.
- additional information corresponding to the jacket can be specified.
- the additional information of the jacket can be specified. Therefore, it becomes possible to easily specify an object appearing in a broadcasted program or a commercial so that it is suitable for expression when the viewer speaks, without any hassle.
- the memory time control unit 3 15 is a predetermined time range or number of scenes, or the maximum time width or the number of scenes corresponding to the time expression learned from the viewer's previous utterance and subsequent input. The control is performed so that the generated recognition vocabulary set is retained. The learning of the storage time control unit 315 will be described later. For example, in the case of the voice utterance “I just like the red outerwear.” According to the control of the storage time controller 315, the voice recognizer 352 uses the time expression vocabulary indicating the past “Saki”. Extract and refer to the time expression dictionary 3 1 6 to find the time range or The above identification is performed on the program additional information broadcast during the number of scenes. After the drama is over, the display unit 318 displays additional information corresponding to an object or the like appearing in the dramas specified by voice recognition.
- the additional information includes information such as the size, weight, material, color, size, price, manufacturer, seller, and seller contact information as described above. After confirming and examining, when purchasing, select additional information by input means such as remote controller 320, pointing device, or voice recognition and input purchase information.
- the transmitting section 319 transmits the purchase information to the broadcasting station together with the identification number of the corresponding additional information.
- the storage time control unit 3 15 uses the relationship between the recognized time expression vocabulary and the information selection input of the viewer to determine the relationship between each time expression vocabulary and the actual number of scenes with a time width.
- the storage time control unit 315 holds information for associating the actual time width or the number of scenes for each recognition vocabulary, which is an expression relating to time, stored in the time expression dictionary 316.
- the storage time control unit 3 15 associates the recognition vocabulary “Saki” with the time range from 20 seconds ago to 5 minutes ago based on the current time. The time width from the current time to 30 seconds before the current time is associated with the current time.
- the storage time control unit 3 15 5 minutes from 20 seconds before the current time
- the speech recognition unit 312 controls the broadcast additional information received during the time interval up to the previous time from 20 seconds before to 5 minutes before the current time.
- the additional program information received during the specified time interval is specified, and the specified additional program information is stored in the additional information storage unit 317. That is, the memory time system
- the control unit 315 controls so that the recognition vocabulary set generated during this time width is maintained.
- the storage time control unit 3 15 receives the recognized vocabulary representing the time expression “Saki”, it corresponds to the time range from 20 seconds before to 5 minutes before the current time as described above.
- the program additional information displayed on the display unit '318 by the viewer may be different from the intended time width of the viewer.
- the viewer speaks to the microphone 3 2 1 saying, "Redo”, "I want you to display the information before that" and "I want you to display more information later”.
- the voice recognition unit 352 performs voice recognition of the utterance from the viewer, and notifies the storage time control unit 315 of the voice recognition result.
- the voice recognition unit 352 recognizes the utterance "I want you to display the information earlier”, it extracts "earlier", "information” and "display” as recognized vocabulary and stores Notify the control unit 3 15.
- the memory time control unit 3 15 When the memory time control unit 3 15 receives the recognition vocabulary of “before”, “information”, and “display” from the speech recognition unit 3 12, it is associated with the recognition vocabulary representing the time expression of “previous” Correct the time width information. In other words, it is modified so that the recognition vocabulary "Saki” is associated with the time width from 40 seconds ago to 5 minutes 40 seconds ago based on the current time. Then, the storage time control unit 3 15 re-programs the voice recognition unit 3 52 with the program additional information received from 40 seconds ago to 5 minutes 40 seconds ago based on the current time. The voice recognition unit 352 is controlled so as to specify the additional information.
- the voice recognition unit 352 specifies the program additional information again under the control of the storage time control unit 315, stores the specified program additional information in the additional information storage unit 317, and displays the display information. 18 displays the program additional information stored in the additional information storage unit 3 17. Then, the viewer may include the desired information in the displayed program additional information. If so, the program additional information is selected and purchase information is input.
- the storage time control unit 315 can reflect the viewer's intention and associate the time width with the recognized vocabulary representing the time expression. This means that the storage time control unit 315 learns.
- step 354 of FIG. 4 will be described in detail with reference to the flowchart of FIG.
- the recognition vocabulary adaptation unit 358 in FIG. 3 feeds back the word recognition result to the synonym dictionary 390 and adds weight to the recognized words in the synonym dictionary 390. I do.
- Step 352 it is assumed that the speech recognition unit 352 has recognized the word A in Step 358 (Step 358). It is assumed that the word A is recognized as the word A, specifically, as described above.
- the synonym dictionary adaptation section 358 searches the synonym dictionary 390 for words whose reading is A (step 359). That is, the synonym dictionary adaptation unit 358 extracts a word whose pronunciation is ⁇ ⁇ from the synonym dictionary 390. Therefore, the word jacket is extracted.
- the synonym dictionary adaptation unit 358 adds (1 / total number of assumed occurrence words) to the word A, ie, the frequency 397 in the word class of the jacket.
- the synonym dictionary adaptation unit 358 determines the frequency of words other than the word A among words included in the word class including the word A (the frequency of occurrence of the word X (1 / Subtract the total number of assumed words))).
- the word class that includes outerwear is clothing, and clothing includes the words jacket and clothes as words other than outerwear. Therefore, the appearance frequency 394 of the words “jacket” and “clothes” is reduced.
- the recognition vocabulary adaptation unit 358 performs the processing of steps 359, 360, and 361 of FIG.
- the recognition vocabulary extension unit 3 57 When new additional information is broadcasted from the broadcast station 10, when the recognition vocabulary extension unit 3 57 generates the recognition vocabulary set 3 95, the appearance frequency 3 94 of the synonym dictionary 390 is used as described above. The captured appearance frequency 394 is used. Therefore, words that are often uttered by the viewer can be more easily recognized by the voice recognition unit 352.
- the viewer is interested in, for example, taking a note of the program itself, taking notes, etc. on the objects and music that appeared in the program. Only by making natural utterances without interruption, it becomes possible to acquire and purchase information continuously while watching the program.
- the recognized vocabulary set can be specified not only by the keyword corresponding to the keyword information included in the additional information but also by uttering words having a similarity to the keyword. Obedience Thus, additional information can be specified.
- the purchase information is transmitted from the transmitting unit 319 to the broadcasting station together with the identification number of the corresponding additional information, but may be transmitted to the distributor included in the additional information. good.
- the voice recognition unit 312 specifies the additional information corresponding to the recognition result. However, only the time stamp in the program is determined, and the additional information storage unit 3 17 The additional vocabulary set corresponding to the additional information before that, the time stamp, and the additional information before that may be stored. That is, the voice recognition unit 312 determines only the time at which the viewer uttered the voice, and the additional information storage unit 317 stores the additional information corresponding to the time and the predetermined time until the time. The broadcasted additional information and the set of recognized vocabulary words corresponding to the additional information can also be stored. After viewing, the viewer presents the stored additional information, recognizes the voice uttered by the viewer, and presents detailed additional information and transmits purchase information. The case where the additional information is specified after viewing the program as described above will be described in detail in Embodiments 5 to 7 described later.
- the additional information storage unit 3 17 stores only the selected additional information. However, it is assumed that all the additional information of the program is stored and only the additional information selected by the voice recognition unit is displayed. Is also good.
- the additional information is stored and displayed after the end of the program.
- the additional information and the corresponding scene which has been received and transmitted again to the program or the broadcast station which has been recorded may be displayed.
- the additional information is stored and displayed after the end of the program.
- only the identification code of the additional information may be stored, and the additional information may be transmitted to a broadcast station and received and displayed again.
- broadcast station 10 of the present embodiment is an example of the first device of the present invention.
- the TV / STB 310 of the embodiment is an example of the second device of the present invention, and the broadcast receiving section 3 14 of the present embodiment is an example of the receiving means of the present invention.
- the form recognition vocabulary generation unit 354 is an example of a recognition vocabulary set generation unit of the present invention
- the speech recognition unit 352 of the present embodiment is an example of a speech recognition unit of the present invention.
- the voice recognition unit 352 is an example of the specifying means of the present invention.
- the display unit 318 of the present embodiment is an example of the display means of the present invention.
- the recognition vocabulary adapting unit 358 of the present embodiment is It is an example of the appearance frequency correction means of the present invention.
- FIG. 1 is a block diagram showing a conceptual configuration of a shopping support system using interactive broadcasting according to the second embodiment of the present invention.
- the recognized vocabulary storage unit 35 1 is changed to a recognized vocabulary storage unit 36 1
- the speech recognition unit 3 is changed. This corresponds to a case where 52 is changed to a speech recognition unit 36 2. Therefore, the description of FIG. 1 is omitted because it is the same as that of the first embodiment.
- Figure 9 shows a functional block diagram showing the details of a shopping support system using interactive broadcasting (hereinafter referred to as a shopping support system).
- the TV / STB 310 has a broadcast receiver 3 13, a recognized vocabulary generator 360, a recognized vocabulary storage 3 61, a voice recognizer 3 62, and a time table current dictionary 3. 16, storage time control unit 3 15, additional information storage unit 3 17, display unit 3 18, transmission unit 3 19, recognition history storage unit 3 63
- the recognition vocabulary generation unit 360 ⁇ is a means for generating a recognition vocabulary set, which is a target vocabulary for speech recognition, from the program additional information received by the broadcast receiving unit 313.
- the recognition vocabulary generation unit 360 Embodiment 2 is different from Embodiment 1 in that a recognized vocabulary set is generated when the set is included in a plurality of word classes.
- the recognized vocabulary storage unit 361 is a means for storing a recognized vocabulary set generated when one word is included in a plurality of word classes.
- the speech recognition unit 362 is means for performing speech recognition using the recognition vocabulary storage unit 361 and the time expression dictionary 316 as a recognition vocabulary dictionary.
- the recognition history storage unit 365 stores the words already recognized by the speech recognition unit 362 and the word class including the words, and is configured by, for example, a semiconductor memory or a hard disk device.
- the recognition vocabulary generation unit 360 includes a recognition vocabulary extraction unit 364, a recognition vocabulary extension unit 366, and synonyms. It consists of a dictionary 365 and a recognition vocabulary adaptation unit 365.
- the recognition vocabulary extraction unit 365 is means for extracting a word corresponding to the keyword information included in the program additional information as a keyword.
- the recognition vocabulary extension unit 366 is a means for generating a recognition vocabulary set by expanding the extracted keywords.
- the synonym dictionary 365 is a dictionary in which a plurality of words are classified into respective word classes based on the similarity between words. Thus, the synonym dictionary 365 of Embodiment 2 can handle the case where one word is included in a plurality of word classes.
- the recognition vocabulary adaptation unit 365 is a means for correcting the frequency of occurrence of each word described in the synonym dictionary 365 according to the speech recognition result.
- FIG. 12 is a flowchart showing an operation performed by the shopping support system of the present embodiment until a recognized vocabulary set is generated and stored in the recognized vocabulary storage unit 361 in association with additional information.
- FIG. 15 is a flowchart showing an operation when the voice uttered by the viewer is recognized.
- a recognition vocabulary set is generated based on Fig. 12 and recognized in association with additional information. The operation up to storing the recognized vocabulary set in the vocabulary storage unit 36 1 will be described. Then, the operation in the case of recognizing the voice uttered by the viewer will be described.
- FIG. 12 as in Embodiment 1, from broadcast station 10, additional information associated with an object appearing in the broadcast content and including keyword information for identifying the object is included. Additional information will be broadcast along with the content of the broadcast. The broadcast receiver 3 13 receives this broadcast.
- FIG. 11 shows a synonym dictionary 400 used in the second embodiment.
- the synonym dictionary 4,000 can handle the case where one word is included in a plurality of word classes.
- the synonym dictionary 400 is composed of the word 401, the reading 46 1 of the word, the word class 1 (40 2) containing the word, the word class 2 (40 3), the word class ⁇ (404)
- This is a dictionary in which the frequency of occurrence of the word 405 is described.
- a word class is a class in which multiple words are classified based on the similarity between words.
- one word 401 is included in ⁇ word classes.
- the appearance frequency 405 obtained from a sufficiently large Japanese corpus is described. Unlike the first embodiment, the appearance frequency 405 describes the appearance frequency in a sufficiently large Japanese corpus.
- the reading of the jacket 46 1 is a jacket
- the word class 1 (402) containing the jacket is clothing
- the word class 2 (403) Is an epidemic.
- the appearance frequency 405 at which the jacket appears is 0.020.
- step 370 it is assumed that the jacket additional information has been sent as additional information.
- the additional information is the same as that described in the first embodiment.
- the recognized vocabulary extraction unit 365 extracts keyword information included in the additional information. That is, when the additional information of the jacket is sent, information corresponding to the jacket is extracted as the keyword information.
- the recognition vocabulary extension unit 3666 uses the synonym dictionary 365 to make the same word class 1 (402), word class 2 (400), and the same as the keyword corresponding to the extracted keyword information.
- ⁇ ⁇ ⁇ Generates a recognized vocabulary set composed of words belonging to word class n (404).
- the recognition vocabulary extraction unit 365 extracts a jacket, which is a keyword, corresponding to the keyword information from the additional information.
- the recognition vocabulary extension unit 366 determines that the word class 1 (402) including the jacket, which is the keyword, is clothing and the word class 2 (400) is flowing. Words such as clothing and fashion are extracted. In the case of the synonym dictionary 400 of FIG. 11, it can be seen that the word whose word class is clothing is a jacket or the like. Then, the recognition vocabulary extension unit 366 sets a jacket or the like as a word constituting the recognition vocabulary set.
- FIG. 13 shows an example of the recognition vocabulary set 406 created in this way.
- the recognition vocabulary set 400 consists of jackets, clothes, outerwear, bags and the like.
- the appearance frequency of the synonym dictionary 400 is also described as the frequency 409 in the word 406 of the recognized vocabulary set.
- the recognition vocabulary extension unit 366 obtains the frequency 409 of each word in the recognition vocabulary set. That is, the frequency 409 is normalized by the recognition vocabulary set 406 so that the sum of the degrees of alcohol 409 of each word in the recognition vocabulary set becomes 1.
- Figure 14 shows the recognized vocabulary set with the frequency 409 standardized in this way. Indicates 4 10.
- the recognition vocabulary adaptation unit 373 extracts words included in the word class including the keyword corresponding to the keyword information of the additional information from the recognition history storage unit 363. That is, the recognition history storage unit 36 3 is composed of a semiconductor memory or a hard disk, and the recognition history storage unit 36 3 stores the words recognized by the already performed speech recognition and the words to which the words belong. The class is stored, and among these words, the words included in the word class including the keyword "jacket" are extracted.
- the word classes included in the jacket include a plurality of word classes such as clothing and fashion, as shown in the synonym dictionary 401 of FIG.
- the recognition vocabulary adaptation unit 373 determines the frequency in the set of words that match the word extracted in step ⁇ 73 out of the words in the recognition vocabulary set 410. For, add (number of occurrences in recognition history / number of assumed words). On the other hand, among the words in the recognized vocabulary set 411, the frequency 412 in the set of words not extracted in step 373 is (frequency in the set X total number of words in the recognized vocabulary set in the recognition history. Number of occurrences) / (Estimated word occurrences) is subtracted.
- the recognition vocabulary adaptation unit 373 associates the recognition vocabulary set 411 from which the set frequency 412 was captured in step 374 with the additional information, and It is stored in the storage unit 3 6 1.
- the recognized vocabulary set 410 is stored in the recognized vocabulary storage unit 361 in association with the additional information.
- the operation of the speech recognition unit 362 using the recognition vocabulary set to specify the additional information is the same as in the first embodiment, and a description thereof will be omitted.
- the operation for voice recognition will be described.
- the operation described below is a process for reflecting the speech recognition result when the already generated recognition vocabulary set is used repeatedly even after speech recognition.
- the speech recognition unit 362 has recognized the word A in step 380. Specifically, it is assumed that the word A is recognized as word A.
- step 381 the recognition vocabulary adaptation unit 367 extracts a word class including the word A with reference to the synonym dictionary 400.
- the recognition vocabulary adaptation unit 3667 stores the word A and the word class including the word A in the recognition history storage unit 365. However, if the number of words stored in the recognition history storage unit 36 exceeds the upper limit of the number of words stored, the oldest words are deleted in order.
- the recognition vocabulary adaptation unit 367 searches for a word whose pronunciation is A in the synonym dictionary 400.
- the word that reads the word Pagi is searched to extract the word outerwear.
- Step 3 8 0 to Step 3 8 5 Returns Ri Repetitive processes from Step 3 8 0 to Step 3 8 5 for each speech recognition.
- the viewers are interested in the work, such as watching the program itself, taking notes, etc., for objects and music that appeared in the program. It is possible to acquire and purchase information continuously with the viewing of a program simply by making natural utterances without interruption.
- the recognition vocabulary set can be specified not only by the keyword corresponding to the keyword information included in the additional information but also by uttering words having a similarity to the keyword. And additional information can be specified accordingly.
- the broadcasting station 10 of the present embodiment is an example of the first device of the present invention
- the TV / STB 310 of the present embodiment is an example of the second device of the present invention.
- the broadcast receiving unit 3 13 of the embodiment is an example of the receiving unit of the present invention
- the recognized vocabulary generating unit 360 of the embodiment is an example of the recognized vocabulary set generating unit of the present invention.
- the voice recognition unit 36 2 of the embodiment is an example of the voice recognition unit of the present invention
- the voice recognition unit 36 2 of the embodiment is an example of the specifying unit of the present invention.
- Reference numeral 18 denotes an example of the display means of the present invention
- the recognized vocabulary adapting unit 365 of the present embodiment is an example of the appearance frequency correcting means of the present invention.
- FIG. 1 shows a functional block diagram showing the details of a shopping support system using interactive broadcasting (hereinafter referred to as a shopping support system).
- TV / STB 310 has a broadcast receiver 3 13, a recognized vocabulary generator 3 71, a synonym dictionary 3 74, a vocabulary weight corrector 3 75, and a grammar storage 37.
- Speech recognition unit 3 7 Recognition history storage unit 3 6 3
- Additional information storage unit 3 17 Display unit 3 18, Transmission unit 3 19, Remote controller 3 20, Microphone 3 21 1
- Storage time It is composed of a control unit 3 15.
- the recognition vocabulary generator 371 is composed of domain-specific rules 372 and a grammar selector 373. In other words, it is assumed that the recognition vocabulary generation unit 371 has the function of a semiconductor memory or a hard disk, and stores the rule 372 for each domain in the semiconductor memory or the hard disk.
- the grammar storage unit 376 has the function of a semiconductor memory or a hard disk, and stores therein Ngram grammar information described later.
- the recognition vocabulary generator 371 stores Ngram grammar information for each domain such as drama, outdoor, autumn, etc. in advance in its own semiconductor memory or hard disk, as shown in the rule by domain 372. This is a means for selecting the Ngram grammar information of the domain corresponding to the scene code sent from the broadcast receiver 3 13.
- the grammar selector 3 7 3 This is a means for selecting the Ngram grammar information of the domain corresponding to the scene code output from the communication unit 3 13.
- the grammar storage unit 376 has a function of a semiconductor memory or a hard disk, and is a means for storing the Ngram grammar information selected by the grammar selection unit 373 in one of these semiconductor memories or the hard disk.
- the vocabulary weight correction unit 3 7 5 uses the synonym dictionary 3 7 4 in which a plurality of words are classified into each word class based on the similarity between words, and A means for correcting the frequency of occurrence of a predetermined word based on a predetermined word class based on history information of voice recognition results of voice recognition already performed stored in the recognition history storage unit 365. is there.
- the speech recognizing unit 377 uses the Ngram grammar information stored in the grammar storage unit 376 to determine the voice uttered by the viewer by continuous speech recognition.
- the broadcast station 10 broadcasts the broadcast content to be broadcast, and additional information that is associated with the object appearing in the broadcast content and includes keyword information for identifying the object.
- a scene code for specifying Ngram grammar information is also broadcast.
- the broadcast receiver 3 13 receives this broadcast.
- the grammar selection unit 3733 extracts the key word information included in the scene code and the additional information from the data output from the broadcast reception unit 313.
- the scene code is information for identifying the Ngrara grammar information stored in the recognition vocabulary generation unit 371, for each domain.
- step 391 the grammar selector 3 7 13 Select the Ngram grammar information of the domain corresponding to the scene code output from 3.
- the vocabulary weight correction unit 375 determines the frequency of occurrence of a predetermined word based on a predetermined word class in the expression form of the Ngram grammatical information. Is corrected using the recognition history information and the synonym dictionary 374 stored in.
- the recognition vocabulary weight correction unit 3775 stores the corrected Ngram grammar information in the grammar storage unit 3756.
- the Ngram grammar information stored in the grammar storage unit 3776 in this way is used by the speech recognition unit 377 for speech recognition.
- the recognition vocabulary weight correction unit 375 corrects the Ngram grammar information using the recognition history information and the synonym dictionary 374, so it appears in broadcasted programs and commercials. Speech recognition can be performed so as to be suitable for the expression when the viewer utters the object. Therefore, additional information associated with a broadcasted program or an object appearing in a commercial can be specified so as to be suitable for expression when the viewer speaks. Hereinafter, this will be described in detail.
- the broadcast content broadcasted from the broadcast station 10 is broadcast, and additional information associated with the object appearing in the broadcast content is provided. Additional information including keyword information for specifying and a scene code for specifying Ngram grammar information will also be broadcast.
- step 400 the broadcast receiving unit 313 receives this broadcast.
- step 401 the grammar selector 3 7 3 determines whether the broadcast receiver 3 1 3 Keyword information included in the scene code and the additional information is extracted from the data output from the terminal.
- the scene code is information for specifying the N gram grammar information that the recognition vocabulary generation unit 371 stores for each domain.
- a scene code is a code for identifying a domain such as drama, outdoor, and autumn.
- Recognition vocabulary generator 3? In 1, N gram grammar information S is stored for each domain as shown in rule 3 7 • 2 for each domain. Therefore, by specifying the scene code, it is possible to specify the N gram grammar information of the domain corresponding to the specified scene code.
- the additional information may include a description of the jacket price, color, size, etc., and a description of the jacket distributor. Same as mode 1.
- the grammar storage unit 376 stores the selected Ngram grammar information.
- Equation 1 the general expression of the Ngram grammar information is as shown in the following Equation 1.
- the word Wi appears behind the word sequence Wi-iWi- 2 ⁇ ⁇ ⁇ Wi- n + i in a sufficiently large Japanese language corpus N (WiWi-l- ⁇ -Wi-n + l) is a sufficiently large Japanese
- the word string WiWi-1 in the corpus represents the frequency of appearance of 'Wi-n + l.
- Equation 1 is approximated as Equation 2 below.
- P (Ci I Ci-l- ⁇ Ci-n + l) is the word class Ci-i ⁇ ⁇ Ci -n + i followed by the word class Ci in a sufficiently large Japanese co-pass. Represents the probability that appears.
- P (Wi I Ci) represents the probability that the word Wi appears among the words included in the word class Ci in a sufficiently large Japanese co-path.
- Equation 2 becomes like Equation 4, (Equation 4)
- the word class Ci-l can be read as a word class sequence Ci-l ⁇ ⁇ 'Ci-n + l.
- Equation 4 P (Wi I WM) represents the probability that the word Wi appears after the word Wi-i, and P (Ci I CM) represents the word class Ci in a sufficiently large Japanese corpus. — Represents the probability that a word in the word class Ci will appear after a word in 1; P (Wi I Ci) is the word of the words in the word class Ci in the aforementioned Japanese corpus. , The probability that the word Wi appears.
- the word classes Ci and Ci-i are defined in the synonym dictionary 374. It is assumed that the synonym dictionary 374 is similar to, for example, the synonym dictionary 390 of FIG. 5 described in the first embodiment.
- Equation 4 shows that the probability that the word Wi appears after the word Wi-i is the probability that the word included in the word class Ci appears after the word included in the word class Ci-i and the probability that the word class Ci It shows that the word Wi is represented by the product of the probability that the word Wi appears.
- FIG. 19 shows Ngram grammar information 454 which is an example of the Ngram grammar information stored in the grammar storage unit 376 in this way.
- Ngram grammar information 454 for example, the probability that the word ⁇ ⁇ gi appears after the word “ano” is due to the fact that the word included in the word class “clothing” is added after the word included in the word class “indicative”. It is expressed as the product of the probability of appearance and the probability of the word Kegegi appearing in the word class [clothing].
- the vocabulary weight correction unit 375 stores the recognition frequency in the expression form of the Ngram grammatical information based on the predetermined word class with respect to the recognition history. Correction is performed using the recognition history information and the synonym dictionary 374 stored in Part 3 63. That is, P (Wi IC in Equation 4 is stored in the recognition history It is corrected using the recognition history information and the synonym dictionary 374.
- FIG. 20 is a diagram for explaining the operation of step 402 and step 403. Hereinafter, the operations of Step 402 and Step 403 will be specifically described with reference to FIG.
- the keyword corresponding to the keyword information included in the additional information is a jacket.
- the synonym dictionary 3 7 4 defines that a jacket is included in the word class [clothing].
- the synonym dictionary 374 defines a jacket, a fuku, a peony, and a sash as words included in the word class [clothing] as shown in C i 424.
- the vocabulary weight correction unit 3775 sets the [clothing] when the keyword corresponding to the keyword information included in the additional information is a jacket. Extract the jacket, fuku, ⁇ ⁇ gi, and shirt that belong to the word class.
- step 4003 words such as pumps, cuticles, televisions, and jackets are stored as recognition history information 421 in the recognition history storage unit 363.
- the recognition history information 4 21 stored in the recognition history storage unit 3 63 indicates the history of words that have been recognized as a result of speech recognition that has already been performed.
- Equation 4 P (Wi IC i) in Equation 4 is as shown in the initial state 4 2 1 I do. That is, among words included in the word class [clothing], the probability that a jacket appears is 0.4, and among words included in the word class [clothing], the probability that a hook appears is 0.3. class
- the vocabulary weight correction unit 375 determines the recognition history information 4 of the words that belong to the word class [clothing], which is a word class including the word jacket, such as jacket, fuku, ⁇ ⁇ gi, and shirt. 2 Add P (WiC in the recognition history information 4 2 1) / (expected word occurrences) to P in the number 4 of each word included in 1.
- the assumed word appearance number is This has the same meaning as that described in Embodiment 1.
- the recognition history information 421 includes the jacket and the fuku among the jacket, fuku, peg, and shirt, and the jacket is performed twice. In this case, if the assumed number of occurrences of the word is 100, in this case, 2/100 is assigned to P (jacket I [clothing]). Add 1 Z 100 to P (Fuku I [clothing]).
- the vocabulary weight correction unit 375 includes, in the recognition history information 421, words of the words “jacket”, “fuku”, ⁇ ⁇ gi, and “shatsu” that belong to the word class “clothing” that includes the word jacket. From P (W i IC) in the number 4 of each not-recognized word ((P (Wi I [clothing]) before correction) / (word belonging to word class [clothing] and not included in recognition history information 4 2 1 P of each word (Wi I
- Recognition history information 421 does not include ⁇ ⁇ gi and shirt among jackets, fuku, ⁇ ⁇ gi, and shirts. In such a case, if the assumed number of occurrences of the word is assumed to be 100, from P ( ⁇ ⁇ GI I [clothing]) to (0.2 / (P ( ⁇ Gi I [Clothing] + P (Shirt I [Clothing])) ⁇ (3Z1 o 0) is subtracted. Also, subtract (0.1 / (P ( ⁇ ⁇ gi i [clothing]) + P (shirt I [clothing])) X (3/1 00) from P (shirt I [clothing]).
- the vocabulary weight correction unit 375 also recognizes the words belonging to the word class [clothing], which includes the word jacket, such as the jacket, the fuku, the pegi, and the shut, as well as the recognition history information 42 1 If it is not included in, use P (Wi IC) in Equation 4 for the word class [clothing] without correction.
- the vocabulary weight correction unit 375 sets the grammar storage unit 376 by associating the Ngram grammar information shown in P (Equation 4 obtained by capturing Wi IC) with the additional information. To memorize.
- the voice recognition unit 377 performs voice recognition of the voice uttered by the viewer using the Ngram grammar information stored in the grammar storage unit 376.
- the speech recognition unit 377 uses the corrected Ngram grammar information stored in the grammar storage unit 376 to perform continuous speech recognition. . As a result, the sentence "that jacket is good” is recognized.
- the Ngram grammar information is used to divide a sequence of readings that have been recognized in speech recognition into words. '
- the speech recognition unit 377 uses the N-gram grammar information to recognize the words “that”, “jacket”, and “good”. Then, the speech recognition unit 377 then specifies the jacket additional information because the jacket, which is a keyword corresponding to the keyword information included in the additional information, matches the jacket, which is a word whose speech has been recognized. And identified The additional information of the jacket is stored in the additional information storage unit 3 17. The subsequent operations relating to the processing of the additional information are the same as those in the first embodiment, and thus description thereof will be omitted.
- the speech recognition unit 365 recognizes a word as described above, the recognized word is stored in the recognition history storage unit 365.
- the vocabulary weight correction unit 375 stores the new word every time a new word is stored in the recognition history information storage unit 363. The operations of Steps 402 and 4403 are repeated using the word as recognition history information 4 21. In this way, the vocabulary weight correction unit 375 corrects P (WiIC) in Equation 4 even during speech recognition.
- the recognition weight correction unit 375 performs the processing shown in FIG. 18 on the recognition history information 4 21 until the scene code is transmitted. Steps 402 and 403 are performed.
- the recognition weight correction unit 375 After performing speech recognition using Ngram grammar information in Embodiment 3, when specifying additional information using a keyword corresponding to the keyword information included in the additional information, use Embodiment 1 or Embodiment 2 Additional information can also be specified using the recognition vocabulary set described in. By doing so, the effects of the first and second embodiments can be obtained in addition to the effects of the present embodiment.
- the Ngram grammar information shown as the domain-specific rules 372 stored in the recognition vocabulary generation unit 371 of the present embodiment was downloaded in advance using a network such as the Internet. Anything may be used.
- N-gram grammar information identification key information which is information for specifying N-gram grammar information
- N-gram grammar information stored in domain-specific rule 37 2 is also N
- the grammar grammar information identification keyword information is added, and the grammar selection unit identifies the Ngram grammar information in accordance with the degree of matching of the Ngram grammar information identification keywords, and parses the identified Ngram grammar information. You can choose.
- N-gram grammatical information is described using N-gram grammatical information.
- languages other than Ngram include, for example, a hidden Markov model (hiddenMarkovmow ⁇ de1) and a stochastic context-free grammar (probabbilibsticccontext—rreegramram).
- hiddenMarkov model hidden Markovmow ⁇ de1
- stochastic context-free grammar probabbilibsticccontext—rreegramram
- the recognized word is output. From the “state”, the output probability that the word recognized by speech recognition is output is increased.
- "non-terminal" for example, representing the class to which the recognized word belongs
- expands to the recognized word Force increases the probability of generating the recognized word as a "terminal" It may be.
- the recognition weight correcting unit 375 captures P (Wi IC) in Equation 4, continuous speech suitable for the expression uttered by the viewer is more easily recognized. This makes it possible to specify additional information associated with an object appearing in a commercial or a commercial so as to be suitable for expression when the viewer speaks.
- the broadcasting station 10 of the present embodiment is an example of the first device of the present invention
- the TV / STB 310 of the present embodiment is an example of the second device of the present invention.
- the broadcast receiving section 3 13 of the embodiment is an example of the receiving means of the present invention
- the recognized vocabulary generating section 3 71 of the present embodiment is an example of the language model specifying means of the present invention.
- the vocabulary weight correction unit 3 75 5 is an example of the correction unit of the present invention.
- the speech recognition unit 3 77 7 of the present embodiment is an example of the speech recognition unit of the present invention.
- Reference numeral 377 denotes an example of the specifying means of the present invention
- the display section 318 of the present embodiment is an example of the display means of the present invention
- the scene code of the present embodiment is an example of the ID of the present invention. It is.
- FIG. 1 is a block diagram showing a conceptual configuration of a shopping support system using interactive broadcasting according to the fourth embodiment of the present invention.
- the recognized vocabulary storage unit 35 1 is changed to a grammar storage unit 376, and a speech recognition unit 35 This is equivalent to the case where 2 is replaced with a voice recognition unit 377. Therefore, the description of FIG. 1 is omitted because it is the same as in the first embodiment.
- Figure 21 shows a functional block diagram showing the details of the shopping support system using interactive broadcasting (hereinafter referred to as the shopping support system).
- the TV / STB 310 has a broadcast receiver 3 13, grammar storage 3 76, voice recognition 3 7 7, product data storage 3 17, display 3 18, It is composed of a transmission section 319, a classifying section 382, a recognition history storage section 363, a synonym dictionary 374, and a class weight correcting section 381.
- the broadcast receiving unit 3 13, additional information storage unit 3 17, display unit 3 18, transmitting unit 3 19, remote controller 320, and microphone 3 21 are the same as in the first embodiment, Detailed description is omitted.
- the grammar storage unit 376, the speech recognition unit 3777, and the recognition history storage unit 363 are the same as those in the third embodiment, and a detailed description will be omitted.
- the class weight correction unit 38 1 uses a plurality of units based on the similarity between words. This is a means of using the synonym dictionary 3 7 4 in which words are classified into each word class, to detect the frequency of occurrence of a given word class after a given word class in the Ngram grammar information expression format. .
- the speech recognition unit 3777 uses the synonym dictionary 3774 to identify a class including the word from the word recognized as a result of the speech recognition, and determines a class including the recognized word and a class including the word. Is stored in the recognition history storage unit 365.
- the broadcast station 10 broadcasts the broadcast content to be broadcast, and additional information that is associated with the object appearing in the broadcast content and includes keyword information for identifying the object. Also, Ngram grammar information will be broadcast.
- the broadcast receiver 3 13 receives this broadcast.
- step 410 the broadcast receiving unit 313 stores the broadcast Ngram grammar information in the grammar storage unit 3776.
- the class weight correction unit 38 1 determines the frequency of occurrence of a given word class after a given word class in the Ngram grammar information expression form by using a recognition history storage unit 36. Correction is performed using the recognition history information stored in 3.
- step 4 12 the class weight correcting unit 38 1 stores the captured Ngram grammar information in the grammar storage unit 376.
- the Ngram grammar information stored in the grammar storage unit 376 in this way is used for speech recognition in the speech recognition unit 377 as in the third embodiment.
- the class weight correction unit 381 using the recognition history information, corrects the Ngram grammar information. This makes it possible to perform speech recognition on objects appearing in the call to suit the interests of the viewer. Therefore, additional information associated with a broadcasted program or an object appearing in a commercial can be specified so as to be suitable for the interest of the viewer when speaking. This is explained in detail below.
- the broadcast content broadcasted from the broadcast station 10 is broadcasted, and additional information associated with the object appearing in the broadcast content is provided. Additional information including keyword information for identification and Ngram grammar information will also be broadcast.
- step 420 the broadcast receiving unit 313 receives the broadcast and stores the Ngram grammar information in the grammar storage unit 3776.
- Ngram grammar information has been described in the third embodiment, and a description thereof will be omitted.
- P (CiICM) in Equation 4 is corrected using the recognition history information of the recognition history storage unit 365.
- FIG. 24 shows an example of P (C i I C i-i) in Equation 4. For example, in FIG. 24, it can be seen that the probability that the class of clothing appears after the word class of referential word is 0 ⁇ 30.
- step 4 21 when the broadcast receiving unit 3 13 receives the additional information, it stores it in the additional information storage unit 3 17.
- the received additional information is the additional information of the jacket as in the third embodiment.
- the class weight correction unit 3 811 determines the frequency of occurrence of a given word class after a given word class in the Ngram grammar information expression format. Is corrected using the recognition history information stored in the recognition history storage unit 365. That is, P (C i IC ii) is corrected using the recognition history information stored in the recognition history storage unit 365.
- FIG. 25 shows a diagram for explaining the operation of step 422 and step 423.
- the operations of step 422 and step 423 will be specifically described with reference to FIG.
- the keyword corresponding to the keyword information included in the additional information is a jacket.
- the recognition history storage unit 365 stores the recognition history information of FIG.
- recognition history information as shown in 451 is stored.
- the recognition history information 451 is composed of a word whose speech has been recognized and a word class including the word. That is, the classifying unit 382 detects a word class including the word recognized as a result of the voice recognition performed by the voice recognition unit 377 using the synonym dictionary 374. Then, the classifying unit 382 stores the recognized word and the word class including the word in the recognition history storage unit 363 in advance. As described above, the recognition history information 451 is generated by the classifying unit 382.
- the class weight correction unit 3811 identifies, using the synonym dictionary 3734, a word class [clothing] that includes a jacket that is a keyword corresponding to the keyword information of the additional information.
- the words belonging to the word class [clothing] are extracted from the recognition history information 451. As shown in the recognition history information 451, two jackets and two puffers are extracted as words belonging to the word class [clothing].
- n word classes are defined in the synonym dictionary 374 as shown in a set of classes 450.
- the broadcast receiving unit 3 1 3 receives the Ngram grammar information, and the grammar storage unit It is assumed that P (Ci I Ci-i) in Equation 4 when stored in 3 76 is in the initial state 4 52.
- P (Ci I Ci-i) in Equation 4 when stored in 3 76 is in the initial state 4 52.
- the probability that a word included in the word class [clothing] appears after a word included in the word class [indicative] is 0.7, and a word class included after the word included in the word class [indicative].
- the probability that [furniture] appears is 0.3.
- the class weight correction unit 381 adds the word class to the probability that a word included in the word class [clothing] appears after a word included in the certain word class (P ([clothing] ICI)). Add the value obtained by dividing the number of occurrences of words included in [clothing] in the recognition history information 45 1 by the total number of assumed occurrences. That is, when Ci is a word class including a keyword corresponding to the keyword information of the additional information, the probability that a word included in Ci appears after a word included in a certain word class is determined by the probability that the word included in word class Ci is Add the value obtained by dividing the number of appearances in recognition history information 4 5 1 by the total number of assumed words. '
- the class weight correction unit 3811 calculates P (Cj ICM) from ((P (Cj ICM before correction)) x ( ⁇ P (Cj I Ci-i) of word class Cj without knowledge history))) x ((total number of words belonging to word class [clothing] in recognition history information 4 5 1) / (expected occurrence) The total number of words)) is subtracted.
- Equation 4 From P ([furniture] I [indicative]) in the initial state 4 52, it can be seen that (0.3 / 0.3) X (4/100) has been subtracted. In this way, P (Cj I C.) In Equation 4 is corrected, as shown by 453 after the adaptation of FIG.
- step 424 the class weight correction unit 3811 corrects P (Ci I Ci »1) in equation 4 and associates the Ngram grammar information shown in equation 4 with the additional information to store grammar. Store in part 3 7 6.
- the speech recognition unit 3777 recognizes the speech uttered by the viewer using the Ngram grammar information stored in the grammar storage unit 3776. .
- the speech recognition unit 3777 uses the corrected Ngram grammar information stored in the grammar storage unit 3776 to perform continuous speech recognition. I do. As a result, the sentence "that jacket is good” is recognized.
- the Ngram grammar information is used to divide a sequence of readings that have been recognized in speech recognition into words. '
- the speech recognition unit 377 7 S uses the Ngram grammar information to recognize the words “Ano”, “Jacket”, and “Nice”. Then, the speech recognition unit 3777 next specifies the jacket additional information because the jacket, which is the keyword corresponding to the keyword information included in the additional information, matches the jacket, which is the word that was speech-recognized. . Then, the additional information of the identified jacket is stored in the additional information storage unit 317. The subsequent operations relating to the processing of the additional information are the same as those in the first embodiment, and thus description thereof will be omitted. '
- the class weight correction unit 3 8 1 calculates P (Ci I Ci Since 1) is corrected, continuous speech suitable for the viewer's hobby becomes easier to recognize. Accordingly, additional information associated with a broadcasted program or an object appearing in a commercial can be specified so as to be suitable for the viewer's hobby.
- N-gram grammar information has been described as being sent from the broadcast station 10. However, as in Embodiment 3, N-gram grammar information should be selected using a scene code or the like. Can also be. Conversely, instead of selecting the Ngram grammar information from the scene code in the third embodiment, the Ngram grammar information may be sent from the broadcasting station as described in the fourth embodiment.
- language models other than Ngram include, for example, a hidden Markov model (hiddenMarkovmodel), a stochastic context-free grammar (probabililisticccontext—freegrammar).
- hiddenMarkovmodel hidden Markov model
- stochastic context-free grammar probabililisticccontext—freegrammar
- a language model other than Ngram for example, in a hidden Markov model, if the “state” that outputs a recognized word based on the recognition result is S 1, for each state S i having an arc that transitions to S 1, S Increase the transition probability from i to S1.
- a stochastic context-free grammar if the "non-terminal symbol” that expands the recognized word (terminal symbol) is C1, the probability of a generation rule that expands a symbol string including C1 may be increased. .
- the broadcast station 10 of the present embodiment is an example of the first device of the present invention
- the TV / STB 310 of the present embodiment is an example of the second device of the present invention.
- the broadcast receiving section 3 13 of the embodiment is an example of the receiving means of the present invention
- the class weight correcting section 3 81 of the present embodiment is an example of the correcting means of the present invention.
- the voice recognition unit 377 is an example of the voice recognition unit of the present invention.
- the voice recognition unit 377 of the present embodiment is an example of the specifying unit of the present invention.
- the display unit 3 18 of the present embodiment is It is an example of the display means of the present invention.
- FIG. 1 is a block diagram showing a conceptual configuration of a shopping support system according to the fifth embodiment of the present invention.
- the recognition vocabulary storage unit 35 1 is changed to a time / language model information storage unit 2005, and a speech recognition unit 3 52 Is equivalent to a speech recognition unit 377. Therefore, the description of FIG. 1 is omitted because it is the same as in the first embodiment.
- Figure 29 shows a functional block diagram showing details of the shopping support system.
- the TV / STB 310 has a broadcast receiving unit 3 13, a control unit 200 1, a sound output unit 200 3, an image display unit 2004, a time selection input means 2002, time and language model information. It comprises a storage unit 2005, an information selection unit 2006, a speech recognition unit 377, a microphone 321, and a transmission unit 319.
- the broadcast receiving unit 3 13, the transmitting unit 3 19, the remote controller 3 20, and the microphone phone 3 21 are the same as those in the first embodiment, and a detailed description thereof will be omitted.
- the control unit 2001 controls the sound output unit 2003, the image display unit 2004, the information selection unit 2006, and the like.
- the sound signal output unit 2003 outputs a sound signal output from the control unit 2001 as sound from a speaker included in the sound signal output unit 2003. It is a step.
- the image display unit 204 is means for displaying the video signal output from the control unit 2000 on a display of the image display unit 204.
- the time selection input means 2002 includes a button switch, and when a user of the shopping support system is interested in watching the program, a time position at that time is designated.
- the time / language model information storage unit 2000 stores the time position designated by the time selection input means 2000 and the language model information corresponding to the time position.
- ⁇ Speech recognition unit 377 7 is a means for recognizing speech uttered by the user of the shopping support system using Ngram grammar information.
- the information selection unit 2006 adds the additional information according to the degree of matching between the word recognized by the voice recognition unit 3777 by voice recognition and the keyword corresponding to the keyword information included in the additional information. It is a means to select.
- the information selection unit 2006 includes a recognition vocabulary generation unit 371, a synonym dictionary 374, a vocabulary weight correction unit 3753, and a recognition history storage unit 3663 according to the third embodiment. It has various functions such as an additional information storage unit 317.
- the transmitting section 319 is means for transmitting the purchase information included in the selected additional information to the broadcasting station together with the identification number of the corresponding additional information.
- TV / STB 310 of the present embodiment has a built-in hard disk for recording a program being viewed.
- FIG. 30 is a flowchart showing the operation of TV / STB 310 of the present embodiment. Hereinafter, the operation will be described based on FIG.
- Broadcasting station 10 broadcasts program content 20007, which is the content of the broadcast, as well as an attachment associated with the object appearing in the broadcast content.
- Program additional information (product information) 200 which is additional information that includes key word information for identifying the target object
- program additional information (N-gram grammar) 209 which is N-gram grammar information 09 will be broadcast.
- the broadcast receiver 3 13 receives this broadcast. That is, unlike the third embodiment, in this embodiment, the program additional information (Ngram grammar) 209 is also broadcast from the broadcast station.
- the control unit 20001 converts the program content 2 0 7 received by the broadcast receiving unit 3 13 into the program content 2 0 1 0 to the audio signal output unit 2 0 3 and the image display unit 2 0 4.
- the audio signal output unit 2003 controls the audio signal output unit 2003 to output the audio signal of the program content 21010 from the speaker, and the image display unit 204 outputs the video signal of the program content 21010. Control to display on the display.
- the control unit 2001 transmits broadcast information such as program content 2000, program additional information (product information) 2008, and program additional information (Ngram grammar) 200. Control is performed so that recording is temporarily made on the built-in hard disk.
- the user operates the time selection input means 202 to paste a time-based tag.
- the time selection input means 200 0 2 is used for inputting a sticky note input by pressing the button switch by the user, and inputting a command for attaching a sticky note 10 seconds before the time when the command is input.
- the time and the time 10 seconds after the time at which the instruction to attach the tag is input are output to the control unit 201 as the time position (step 501).
- the control unit 20001 determines the time position and the program additional information (N-gram grammar) 2 209 included in the time position. In association with this, the time information is stored in the time / language model information storage unit 205 as an N-gram grammar 20011 corresponding to the time (step 502).
- the control unit 2001 sets the time position stored in the time / language model information storage unit 205.
- the Ngram grammar 2 Oil corresponding to the time is read out.
- the audio signal and the video signal of the program content included in the read time position are extracted from the internal hard disk, and the audio signal output unit 203 and the audio signal output unit 203 are respectively extracted.
- the image is output to the image display unit 204 (step 503).
- the scene included in the time position stored in the time / language model information storage unit 205 is a scene in which a character of a drama wearing clothes is reflected
- the scene showing the character of the drama wearing the clothes for the specified time width, that is, 20 seconds, is presented to the user again.
- control unit 20001 outputs the Ngram grammar information corresponding to the read time position to the information selection unit 2000.
- the information selection unit 2006 outputs the Ngram grammar information to the speech recognition unit 3777.
- control unit 20001 extracts the program additional information (product information) 2008 included in the read time position from the built-in disk and the disc, and outputs the information to the information selection unit 2000.
- the user looks at the scene specified at the time position presented again and inputs a voice specifying the clothes worn by the characters to the microphone 3 21 (step 504). For example, the user says, “Oh, clothes are good.” 3 2 1 'Then, the speech recognition unit 377 uses the Ngram grammar information which is the program additional information (Ngram grammar) 200 read from the time / language model information storage unit 205, and Recognize the voice signal saying "Ah, clothes are good” (Step 505).
- Ngram grammar program additional information
- the voice recognition unit 3777 is read from the time / language model information storage unit 2005, and as in the third embodiment. Recognize continuous speech using optimized Ngram grammar information. Note that the method of optimizing the Ngram grammar information is the same as that of the third embodiment, and thus a detailed description is omitted. As a result, the sentence "that clothes is good” is recognized.
- the Ngram grammar information is used to divide a sequence of readings that have been recognized during speech recognition into words.
- the speech recognition unit 377 recognized the words “that”, “clothes”, and “good” by using the Ngram grammar information. Then, the voice recognition unit 377 7 outputs the word strings “a”, “clothes”, and “nice” to the information selection unit 2006.
- the information selection unit 2006 determines that the clothing corresponding to the keyword corresponding to the keyword information included in the extracted additional information (product information) 201 13 matches the clothing recognized as the speech-recognized word.
- the additional information of is specified.
- the additional information of the specified clothes is output to the transmission section 319 as the selected information 201.
- the transmitting section 319 transmits the purchase information included in the selected information 201 to the broadcasting station together with the identification number of the corresponding additional information (step 506).
- time selection input means 200 includes a touch panel
- the user may touch the sticky button on the touch panel when an object of interest appears on the display while watching the program.
- time selection input In the case where the means 2000 includes a microphone, the user only has to say "paste a sticky note" when something interesting is displayed on the display while watching the program.
- the Ngram grammar information read out from the time 'language model information storage unit 205 by the information selection unit 20006 is optimized by the same method as in the third embodiment.
- the present invention is not limited to this, and may be optimized by the same method as in the fourth embodiment.
- the time 'language model information storage unit 205 stores the time position and the N-gram grammar information, which is the program additional information (N-gram grammar) 209, as time information and time. It has been described that the data is stored as the N-gram grammar 2 0 1 1, but the present invention is not limited to this.
- the time 'language model information storage unit 20005 stores only the time position, and does not have to store the Ngram grammar information. In this case, in step 503, the control unit 2001 stores the Ngram grammar information included in the read time position in the program additional information (Ngram grammar) stored in the internal hard disk. It suffices to extract from 209 and output it to the information selector 2006.
- the time / language model information storage unit 205 stores the time position and the N-gram grammar information which is the program additional information (N-gram grammar) 200 9 into the time information and the time. N Gram. Grammar 2 0 1 1 This is described as being stored as, but is not limited to this.
- the time 'language model information storage unit 20005 stores the time position and the program additional information (product information) included in the time position in addition to the Ngram grammar information which is the program information (N-gram grammar) 200. 2 008 may be stored.
- the control unit 2001 stores the additional information (product information) 2008 contained in the read time position in the time and language model information storage unit 2005. , And output it to the information selection unit 2006.
- the program additional information (N-gram grammar) 209 is transmitted from the broadcasting station 10, but instead of the program additional information (N-gram grammar) 209
- the recognized vocabulary set described in the first and second embodiments may be broadcast from the broadcast station 10.
- the control unit 2001, the speech recognition unit 3777, and the information selection unit 2006 handle the recognized vocabulary set instead of the Ngram grammar information, and the information selection unit 200
- the operation of the speech recognition unit 36 and the speech recognition unit 377 7 is to specify the additional information (product information) 2 08 using the recognition vocabulary set as in the first and second embodiments. I do.
- all of the program additional information (product information) 2008 is recorded on the built-in hard disk, and the program additional information included in the time position designated by the time selection input means 200 2 (Commodity information) Although it has been described that only 2008 is presented, the present invention is not limited to this. Only the program additional information (product information) 208 included in the time position designated by the time axis selection input means 200 2 may be stored and presented.
- the operation of specifying the additional information (product information) after the end of the program or after the interruption of the program rather than during the viewing of the program is performed.
- the additional information (product information) can be specified without interrupting the information.
- FIG. 1 is a block diagram showing a conceptual configuration of a shopping support system according to the sixth embodiment of the present invention.
- the recognition vocabulary storage unit 35 1 is changed to a product information / language model information storage unit 201, and speech recognition is performed. This is equivalent to a part obtained by replacing the part 352 with the voice recognition part 377. Therefore, the description of FIG. 1 overlaps with the first embodiment. Omitted.
- Figure 31 shows a functional block diagram showing the details of the shopping support system (hereinafter referred to as the shopping support system).
- TV / STB 310 has a broadcast receiving unit 3 13, a control unit 200 1, a sound output unit 200 3, an image display unit 2004, a time selection input unit 200 2, product information and a language model. It comprises an information storage section 2015, an information selection section 2016, a voice recognition section 377, a microphone 321, and a transmission section 319.
- the broadcast receiving unit 3 13, the transmitting unit 3 19, the remote controller 3 20, and the microphone phone 3 21 are the same as those in the first embodiment, and a detailed description thereof will be omitted.
- the control unit 2001 controls the sound output unit 2003, the image display unit 2004, the information selection unit 2006, and the like.
- the sound signal output unit 2003 is a means for outputting the sound signal output from the control unit 2001 as sound from a speaker included in the sound signal output unit 2003.
- the image display unit 2004 is means for displaying the video signal output from the control unit 2001 on a display of the image display unit 2004.
- the time selection input means 2002 includes a button switch, and is a means for designating a time position at that time when a user of the shopping support system is interested while watching the program.
- Language model information storage unit 20 15 stores language model information (Ngram grammar information) and product information as additional information corresponding to the time position designated by time selection input means 20 2. is there.
- the speech recognition unit 377 is means for recognizing a speech uttered by a user of the shopping support system using the Ngram grammar information.
- the information selection unit 20 16 is activated by the speech recognition unit 3 77 7 This is means for selecting additional information according to the degree of matching between the recognized word and a keyword corresponding to the keyword information included in the additional information.
- the information selection unit 2006 includes a recognition vocabulary generation unit 371, a synonym dictionary 374, a vocabulary weight correction unit 3753, and a recognition history storage unit 3663 according to the third embodiment. It has various functions such as an additional information storage unit 317.
- the transmitting section 319 is means for transmitting the purchase information included in the selected additional information to the broadcasting station together with the identification number of the corresponding additional information.
- the TVZSTB 310 of the present embodiment may have a built-in hard disk for recording a program or the like being watched as in the fifth embodiment, or may have no built-in hard disk. .
- FIG. 31 is a flowchart showing the operation of TVZS TB 310 of the present embodiment. The operation will be described below with reference to FIG.
- Broadcasting station 10 broadcasts program content 20007, which is the content of the broadcast, and identifies the object by using additional information associated with the object appearing in the broadcast content.
- Program additional information (product information) 209 which is additional information including key word information for performing, and program additional information (N gram grammar) 209, which is N-gram grammar information, are broadcast.
- the broadcast receiver 3 13 receives this broadcast. That is, unlike the third embodiment, in the present embodiment, the program additional information (Ngram grammar) 209 is also broadcast from the broadcast station.
- the control unit 200 1 outputs the program content 200 7 received by the broadcast receiving unit 3 13 to the audio signal output unit 200 3 and the image display unit 204 as the program content 201.
- the audio signal output unit 2003 controls the audio signal output unit 2003 to output the audio signal of the program content 21010 from the speaker. 4 controls so that the video signal of the program content 210 0 is displayed on the display. .
- Step 511 is the same as the operation of Step 501 of the fifth embodiment.
- the control unit 20001 receives the program information (product information) 2008 included in the time position,
- the N-gram grammar information as product information corresponding to the selected time and N gra ⁇ grammar 2 0 17 as product information and language model information storage unit 20 Store in 15 (step 5 1 2).
- the control unit 2001 executes the Ngram grammar stored in the product information / language model information storage unit 205.
- the information and the merchandise information are read out, and the merchandise information is output as a list to the image display unit 204.
- the image display unit 204 displays a list of product information on a display.
- Figure 33 shows an example of product information displayed in this way. That is, the product information of the product in the range in which the time selection input means 2002 specifies the time position is displayed as shown in FIG. In this way, the user is presented with the product information specifying the time position.
- control unit 20001 outputs the read Ngram grammar information and the product information to the information selection unit 2000.
- the information selection unit 2000 outputs this Ngram grammar information to the speech recognition unit 3777.
- the user inputs a voice specifying the clothes into the microphone 3 21 while looking at the list of product information shown in Fig. 33 (step 514). For example, the user speaks into the microphone 321, "Oh, clothes are good.”
- the operations after step 5 14 are the same as the operations in the fifth embodiment, and therefore, the description is omitted.
- the operation of specifying the additional information (product information) after the end of the program or after the interruption of the program rather than during the viewing of the program is performed.
- the additional information (product information) can be specified without interrupting the information.
- FIG. 1 is a block diagram showing a conceptual configuration of a shopping support system according to the seventh embodiment of the present invention.
- the recognition vocabulary storage unit 35 1 is changed to a speech / product information / language model information storage unit 201. This corresponds to a unit obtained by changing the unit 3 52 to the voice recognition unit 3 7 7. Therefore, the description of FIG. Figure 34 shows a functional block diagram showing the details of the shopping support system (hereinafter referred to as the shopping support system).
- the TV / STB 310 has a broadcast receiving section 3 13, a control section 20 18, a sound output section 2003, an image display section 2004, a voice, product information, and a language model information storage section. 20 19, information selection section 2020, voice recognition section 377, microphone 321, and transmission section 319.
- the broadcast receiver 3 13, the transmitter 3 19, the remote controller 3 20, and the microphone 3 21 are the same as in the first embodiment, Detailed description is omitted.
- the control unit 210 is a means for controlling the sound output unit 203, the image display unit 204, the information selection unit 206, and the like.
- the sound signal output unit 2003 is a means for outputting the sound signal output from the control unit 20001 as a sound from a speaker included in the sound signal output unit 2000. '
- the image display unit 204 is means for displaying the video signal output from the control unit 210 on a display of the image display unit 204.
- Voice ⁇ Product information ⁇ Language model information storage unit 201 is included for 20 seconds including the point when the user of the shopping support system utters into the microphone 3 21 while watching the program. This is a means to store language model information (N-gram grammar information), product information, and voice uttered by the user as additional information.
- the speech recognition unit 377 is means for recognizing a speech uttered by a user of the shopping support system using the Ngram grammar information.
- the information selection unit 202 selects the additional information according to the degree of matching between the word recognized by the voice recognition unit 377 and the keyword corresponding to the keyword information included in the additional information. It is a means to do.
- the information selection unit 202 is a recognition vocabulary generation unit 371, a synonym dictionary 374, a vocabulary weight correction unit 375, and a recognition history storage unit 366 of the third embodiment. It has various functions such as an additional information storage unit 317.
- the transmitting section 319 is means for transmitting the purchase information included in the selected additional information to the broadcasting station together with the identification number of the corresponding additional information.
- the TVSTB 310 of the present embodiment may have a built-in hard disk for recording the program or the like being watched as in the fifth embodiment, but may not have a built-in hard disk. .
- the operation of the present embodiment will be described focusing on differences from the fifth embodiment and the sixth embodiment.
- FIG. 35 is a flowchart showing the operation of TV / STB 310 of the present embodiment. The operation will be described below with reference to FIG.
- Broadcasting station 10 broadcasts program content 20007, which is the content of the broadcast, and identifies the object by using additional information associated with the object appearing in the broadcast content.
- Program additional information (product information) 209 which is additional information including key word information for performing, and program additional information (N gram grammar) 209, which is N-gram grammar information, are broadcast.
- the broadcast receiver 3 13 receives this broadcast. That is, unlike the third embodiment, in the present embodiment, the program additional information (Ngram grammar) 209 is also broadcast from the broadcast station.
- the control section 210 changes the program content 2 0 7 received by the broadcast receiving section 3 13 into the program content 2 0 1 0 to the audio signal output section 2 0 3 and the image display section 2 0 4.
- the audio signal output unit 2003 controls the audio signal output unit 2003 to output the audio signal of the program content 21010 from the speaker, and the image display unit 204 outputs the video signal of the program content 21010. It is controlled so that it is displayed on the display.
- control unit 21018 compares the input voice input in step 5 21, the product information included in 20 seconds including the time position when the input voice was input, and the Ngram
- the grammar information is stored in the voice, product information, and language model information storages (step 5222).
- the control unit 208 is configured to output the program additional information (product information) 208 included during the 20 seconds including the time when the input voice is input, and the program additional information (program additional information).
- the product information corresponding to the selected time is the Ngram grammar information 2 0 9 ′ and the Ngram grammar 2 0 17 as speech, product information, and language model information storage unit 2 0 1 Store in 9.
- the control unit 210 stores the input voice input in step 521 in the voice / product information / language model information storage unit 210 as the input voice 2202 when the time is selected.
- control unit 523 does not interrupt the viewing of the program, and outputs the input speech 2022 when the time is selected, which is stored in the speech, product information, and language model information storage unit 201, without interruption.
- the speech and recognition unit 377 is controlled to input speech. .
- the speech recognition section 377 performs speech recognition (step 523).
- the information selection unit 202 specifies the product information when the product information can be specified. This specific operation of the product information is performed in the same manner as in the third embodiment. If the operation of step 5 23 is performed, the viewing of the program is not interrupted.
- step 528 if the information selection unit 202 can specify the product information, the process proceeds to step 528, and if the product information cannot be specified, Proceed to step 5 25 (step 5 2 4).
- the case where the product information can be specified is, for example, a case where the input voice 202 when the time is selected indicates a specific product such as "that clothes is good”.
- the case where the information cannot be specified is a case where the input voice 202 when the time is selected does not indicate a specific product, for example, "that, good”.
- step 528 the control section 21018 sets the information selection section 202, the sound output section 200 so as to present the specified product information to the user after the program viewing ends or after the program viewing is stopped. 0 3, Controls the image display unit 204. According to this control, the specified product information is displayed on the display of the image display unit 204, and the process proceeds to step 530.
- step 525 after the end of the program viewing or after the program viewing is interrupted, the control unit 210 selects the product included in the 20 seconds including the time when the input sound 2202 at the time of the time selection is input.
- the information is read from the voice, product information, and language model information storage unit 201 and output to the image display unit 204 as a list of product information.
- the rain image display section displays a list of product information.
- Fig. 33 shows an example of product information displayed in this way. That is, the product information included in the 20 seconds including the time when the input voice 2202 at the time of selection is input is displayed as shown in FIG. In this way, the product information specifying the time position is presented to the user.
- the user inputs a voice for specifying the product information to be specified toward the microphone 321, while looking at the list in FIG. 33 (step 526). For example, when it is desired to specify clothes, a voice specifying the clothes, such as "Oh, clothes are good,” is uttered into the microphone 3 21.
- the speech recognition unit 377 uses the Ngram grammar information included in the 20 seconds including the time when the input speech at the time of selection 202 was input as speech 'product information and language model information storage. It reads out from the section 201 and performs speech recognition using the read-out Ngram grammar information (step 527). That is, when the user utters “that clothes are good”, the speech recognition unit 377 is read out from the time / language model information storage unit 205, and the same as in the third embodiment. Continuous speech recognition using Ngram grammar information optimized in this way. The method of optimizing the Ngram grammar information is the same as that of the third embodiment, and a detailed description will be omitted. As a result, the sentence "that clothes is good" is recognized.
- the Ngram grammar information is used to divide a sequence of readings that have been recognized during speech recognition into words.
- the speech recognition unit 377 recognized the words “that”, “clothes”, and “good” by using the Ng ram grammar information. Then, the voice recognition unit 377 outputs the word strings “a”, “clothes”, and “nice” to the information selection unit 202.
- the information selection unit 2006 matches the clothing corresponding to the keyword information included in the speech / product information / language model information storage unit 210/19 with the speech-recognized word, the clothing is selected.
- the additional information of is specified.
- the information selecting section 202 outputs the specified additional information to the transmitting section 319 as the selected information 203.
- the transmitting unit 319 transmits the purchase information included in the selected information 201 to the broadcast station together with the identification number of the corresponding additional information (step 530).
- the voice is input after looking at the list shown in FIG. 33 in step 526.
- the scene specified by the time position is input. May be input after seeing again.
- the operation of presenting and specifying additional information (product information) after the end of the program or after the interruption of the program rather than during the viewing of the program is performed.
- the additional information (product information) can be specified without interrupting the viewer's viewing of the program.
- the present embodiment has been described as operating according to the flowchart shown in FIG. 35, the present invention is not limited to this, and may operate according to the flowchart shown in FIG. In the flowchart shown in FIG. 36, the insertion position of step 522 is different from that of the flowchart shown in FIG. That is, in FIG. 35, step 5 22 was performed before step 5 24, whereas in FIG. 36, step 5 2 was performed only when the product information could not be identified by voice recognition in step 5 24. Two have been done. Even if the product information corresponding to the time position where the voice input is made and the Ngram grammar are stored only when the product information cannot be specified by the voice recognition, the same effect as in the present embodiment can be obtained. .
- FIG. 26 is a functional block diagram showing a part of the shopping support system according to the related art 1 of the present invention in which program additional information for shopping is automatically created at the same time as the program creation.
- FIG. 27 is a flowchart showing the operation of the shopping support system according to the related art 1 of the present invention in which the program additional information is automatically created at the same time as the program creation.
- FIG. 26 the program recording device 110 and the additional information code transmitter 100 are shown.
- the additional information code transmitter 1 0 2 0 is a transmitter for transmitting the code number of the program additional information by radio waves or infrared rays.
- the program recording device 101 is a microphone 1101, a camera 101, a receiving unit 101, an additional information collating database 100, an information collating unit 101, a program additional information database 10 15 and a program storage unit 10 16.
- Receiving section 1 0 1 3 receives additional information code transmitter 1 0 20 signal Means.
- the additional information collating database 1104 is a database in which a code number of the program additional information and collation information of the program additional information are recorded.
- the information collating unit 1007 based on the contents of the additional information collating database 1004, corresponds to the additional information code received by the receiving unit 1013 in the image and audio signals input from the camera and microphone. It is a means to determine whether an object, creature, or person is recorded.
- the program additional information database 101 is a database that stores additional information to be recorded in a program.
- the program storage unit 116 is a means for synchronously recording images, audio signals, and program additional information.
- an additional information code transmitter 102 is attached to an object, a living thing, or a person having the corresponding additional information (step 1031).
- input the image and sound signals from the camera 101 and the microphone 101 and at the same time, receive the signal transmitted by the additional information code transmitter from the receiver 103 (step 1032). .
- the information collating unit 101 determines whether there is a signal from the transmitter and whether the received signal contains an additional information code (step 103). If there is no transmitter signal or no additional information code is included in the received signal in step 103, the image and sound signals input from the camera 101 and microphone 101 Record only (step 1 0 4 0). TJP2003 / 017015
- the collation information corresponding to the additional information code is extracted from the additional information collation database 1004 (step 11034).
- the information collating unit 101 determines whether there is any matching information in the images and sound signals input from the camera 101 and the microphone 101 (Step 10). 3 5).
- step 1035 If it is determined in step 1035 that there is no matching information in the input image and sound signal, the image and sound signal input from camera 1012 and microphone 1011 Only record (step 1004).
- step 1035 If it is determined in step 1035 that the input image and sound signal correspond to the collation information, the corresponding program additional information is extracted from the program additional information database 1005, and the image and sound signals are extracted. Recording is performed in synchronization with the acoustic signal (step 11036).
- Figure 28 shows a shooting site producing broadcast content such as programs and commercials.
- Camera 1 0 1 2 is installed at the shooting site, and camera 1 0 1 2 can move the installation location.
- the camera 101 can move freely from the position of the camera 101a to the position of the camera 101b.
- fixed position transmitters 130a, 130b, and 130c are installed at different fixed positions at the shooting site. These fixed position transmitters 103a, 103b, and 103c form three-dimensional fixed coordinates. In FIG. 28, three fixed position transmitters 10030a, 13030b, and 13030c are described as being installed at fixed positions, but the present invention is not limited to this. The above fixed position transmitter may be installed at a fixed position.
- Camera 1 0 1 2 can move and change posture, but position is fixed By receiving signals from each of the transmitters 103a, 103b, and 103c, it is possible to calculate the information on the position and orientation of the camera 102 on its own coordinates. I can do it.
- the additional information code transmitter 1 0 2 0 is a fixed position transmitter 1 0 '3 0 a
- the additional information code transmitter 102 transmits its own position on the coordinates.
- the camera 101 has a position and orientation on the coordinates of the camera 102 itself, a position on the coordinates of the additional information code transmitter 102, and a focal length as internal information of the camera 101. It is determined whether or not the additional information code transmitter 1 0 0 0 is within the shooting range of the camera 1 0 1 2 from the angle of view and the viewing angle.
- the camera 1 0 1 2 has the additional information code transmitter 1 0 2 0
- camera 1 0 1 2 has additional information code transmitter 1 0
- the additional information code sent from the additional information code transmitter 102 is sent to the information inquiry unit 11017. Is not output. By doing so, the information inquiry unit 11017, when the additional information code 102 is sent, transmits the program additional information corresponding to the additional information code 102 as video and audio. By synchronizing and recording, it is possible to automatically create a broadcast content that broadcasts the program additional information associated with the target only when the target is captured in the video.
- the creator checks the entire scene after the program is created, and adds and records the program additional information to the program. No longer needed, program creation Work time and work cost can be reduced.
- the additional information code transmitter 1 0 2 0 transmitted the code number of the additional information, but transmitted the additional information collation data, and the information collation unit 1 0 1 6 It is also possible to perform collation with the image and the audio signal based on the received data without using the data.
- the information collating unit 11017 extracts the program ancillary information corresponding to the code number from the program ancillary information database and records it in synchronization with the image and the sound signal. Tag information for linking with additional information may be recorded.
- the program of the present invention is a program for causing a computer to execute the functions of all or a part of the above-described second device of the present invention (or device, element, or the like) by a computer. It is a program that works and operates.
- the recording medium of the present invention carries a program for causing a computer to execute all or a part of the functions of all or a part of the above-described second apparatus of the present invention (or an apparatus, an element, or the like). And a program readable by a computer, and wherein the read program executes the function in cooperation with the computer.
- the “functions of the means (or device, element, etc.)” of the present invention means all or a part of the functions of the means, and the “steps (or processes, operations, actions, etc.)” of the present invention.
- the operation of “)” means the operation of all or part of the above steps.
- one use form of the program of the present invention may be a form in which the program is recorded on a computer-readable recording medium and operates in cooperation with the computer. .
- One use form of the program of the present invention is a form in which the program is transmitted through a transmission medium, read by a computer, and operates in cooperation with the computer.
- the data structure of the present invention includes a database, a data format, a data table, a data list, a data type, and the like.
- the recording medium includes ROM and the like
- the transmission medium includes a transmission medium such as the Internet, light, radio waves, and sound waves.
- the computer of the present invention described above is not limited to pure hardware such as CPU, but may include firmware, OS, and peripheral devices.
- the configuration of the present invention may be implemented as software or as a hardware.
- the present invention provides a broadcast receiving method, a broadcast receiving system, and a broadcast receiving method that can obtain a broadcast program or an object appearing in a commercial more easily and without difficulty.
- An apparatus, a second apparatus, a recording medium, and a program can be provided.
- the present invention provides a broadcast receiving method and a broadcast receiving system, which can be easily and easily obtained without being troublesome so as to be suitable for expression when a viewer utters a broadcasted program or an object appearing in a commercial.
- a first device, a second device, a recording medium, and a program are examples of the present invention.
- the present invention also provides for the use of objects appearing in broadcasted programs and commercials. 17015
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Human Computer Interaction (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Social Psychology (AREA)
- Marketing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Acoustics & Sound (AREA)
- Entrepreneurship & Innovation (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Game Theory and Decision Science (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/542,409 US7698138B2 (en) | 2003-01-15 | 2003-12-26 | Broadcast receiving method, broadcast receiving system, recording medium, and program |
AU2003296157A AU2003296157A1 (en) | 2003-01-15 | 2003-12-26 | Broadcast reception method, broadcast reception system, recording medium, and program |
JP2004566305A JPWO2004064393A1 (ja) | 2003-01-15 | 2003-12-26 | 放送受信方法、放送受信システム、記録媒体、及びプログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2003007442 | 2003-01-15 | ||
JP2003-7442 | 2003-01-15 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2004064393A1 true WO2004064393A1 (ja) | 2004-07-29 |
Family
ID=32709113
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2003/017015 WO2004064393A1 (ja) | 2003-01-15 | 2003-12-26 | 放送受信方法、放送受信システム、記録媒体、及びプログラム |
Country Status (5)
Country | Link |
---|---|
US (1) | US7698138B2 (ja) |
JP (1) | JPWO2004064393A1 (ja) |
CN (1) | CN1757229A (ja) |
AU (1) | AU2003296157A1 (ja) |
WO (1) | WO2004064393A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006163710A (ja) * | 2004-12-06 | 2006-06-22 | Nec Corp | 番組情報蓄積装置及び方法並びに番組情報蓄積用プログラム |
JP2006285115A (ja) * | 2005-04-05 | 2006-10-19 | Hitachi Ltd | 情報提供方法および情報提供装置 |
JP2013140520A (ja) * | 2012-01-05 | 2013-07-18 | Fujitsu Ltd | 画像再生装置、画像再生プログラム、及び画像再生方法 |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7437296B2 (en) * | 2003-03-13 | 2008-10-14 | Matsushita Electric Industrial Co., Ltd. | Speech recognition dictionary creation apparatus and information search apparatus |
EP1699042B1 (en) * | 2003-12-26 | 2010-02-17 | Kabushiki Kaisha Kenwood | Device control device, method and program |
JP2007178927A (ja) * | 2005-12-28 | 2007-07-12 | Canon Inc | 情報検索装置および方法 |
US20080208589A1 (en) * | 2007-02-27 | 2008-08-28 | Cross Charles W | Presenting Supplemental Content For Digital Media Using A Multimodal Application |
JP5459214B2 (ja) * | 2008-08-20 | 2014-04-02 | 日本電気株式会社 | 言語モデル作成装置、言語モデル作成方法、音声認識装置、音声認識方法、プログラム、および記録媒体 |
JP2010072507A (ja) * | 2008-09-22 | 2010-04-02 | Toshiba Corp | 音声認識検索装置及び音声認識検索方法 |
US20120017155A1 (en) * | 2010-07-19 | 2012-01-19 | John Lynch | Instant delayed gratification presentation-interactive electronic commerce |
US8688453B1 (en) * | 2011-02-28 | 2014-04-01 | Nuance Communications, Inc. | Intent mining via analysis of utterances |
US9172999B2 (en) * | 2012-08-08 | 2015-10-27 | Verizon Patent And Licensing Inc. | Behavioral keyword identification based on thematic channel viewing |
CN104093079B (zh) | 2014-05-29 | 2015-10-07 | 腾讯科技(深圳)有限公司 | 基于多媒体节目的交互方法、终端、服务器和*** |
WO2017199486A1 (ja) * | 2016-05-16 | 2017-11-23 | ソニー株式会社 | 情報処理装置 |
CN107665710B (zh) * | 2016-07-27 | 2021-02-09 | 上海博泰悦臻网络技术服务有限公司 | 移动终端语音数据处理方法及装置 |
WO2019188269A1 (ja) | 2018-03-27 | 2019-10-03 | ソニー株式会社 | 情報処理装置、情報処理方法、送信装置、及び送信方法 |
FR3095563A1 (fr) * | 2019-04-26 | 2020-10-30 | Orange | Commande d’un service utilisant le traitement d’un flux comprenant des données multimédias |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0916191A (ja) * | 1995-06-29 | 1997-01-17 | Asahi Chem Ind Co Ltd | ナビゲータ用音声認識装置および方法 |
JP2001022373A (ja) * | 1999-07-02 | 2001-01-26 | Alpine Electronics Inc | 音声認識方法 |
JP2001229180A (ja) * | 2000-02-17 | 2001-08-24 | Nippon Telegr & Teleph Corp <Ntt> | コンテンツ検索装置 |
JP2001258011A (ja) * | 2000-03-08 | 2001-09-21 | Sony Corp | データ送信方法および装置、データ受信方法および装置、データ表示方法および装置、並びに情報サービス方法および装置 |
JP2002290859A (ja) * | 2001-03-26 | 2002-10-04 | Sanyo Electric Co Ltd | ディジタル放送受信装置 |
JP2002330422A (ja) * | 2001-04-27 | 2002-11-15 | Sony Corp | デジタル放送を用いた商品販売ビジネスの方法、およびデジタル放送受信装置 |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6323911B1 (en) * | 1995-10-02 | 2001-11-27 | Starsight Telecast, Inc. | System and method for using television schedule information |
JPH09186943A (ja) | 1996-01-08 | 1997-07-15 | Canon Inc | データ受信方法とその装置 |
US6961700B2 (en) * | 1996-09-24 | 2005-11-01 | Allvoice Computing Plc | Method and apparatus for processing the output of a speech recognition engine |
US6131086A (en) * | 1997-04-02 | 2000-10-10 | Walker Digital, Llc | Method and system for allowing viewers to purchase program products |
JPH11110385A (ja) | 1997-10-01 | 1999-04-23 | Nippon Hoso Kyokai <Nhk> | 言語処理装置および方法 |
JPH11252533A (ja) | 1998-03-05 | 1999-09-17 | Toshiba Corp | 情報表示装置 |
US7536706B1 (en) * | 1998-08-24 | 2009-05-19 | Sharp Laboratories Of America, Inc. | Information enhanced audio video encoding system |
JP3979556B2 (ja) | 1998-12-22 | 2007-09-19 | パイオニア株式会社 | 番組選択装置及び番組選択方法 |
US6314398B1 (en) | 1999-03-01 | 2001-11-06 | Matsushita Electric Industrial Co., Ltd. | Apparatus and method using speech understanding for automatic channel selection in interactive television |
JP2002010207A (ja) | 2000-06-26 | 2002-01-11 | Matsushita Electric Ind Co Ltd | 放送情報受信装置、放送情報送信装置、放送情報受信方法及び放送情報送信方法 |
JP2002091477A (ja) | 2000-09-14 | 2002-03-27 | Mitsubishi Electric Corp | 音声認識システム、音声認識装置、音響モデル管理サーバ、言語モデル管理サーバ、音声認識方法及び音声認識プログラムを記録したコンピュータ読み取り可能な記録媒体 |
US20020143550A1 (en) * | 2001-03-27 | 2002-10-03 | Takashi Nakatsuyama | Voice recognition shopping system |
US6760705B2 (en) * | 2001-05-31 | 2004-07-06 | Motorola, Inc. | Virtual speech interface system and method of using same |
ATE550755T1 (de) | 2001-08-28 | 2012-04-15 | Panasonic Corp | Empfangsverfahren für funkübertragungen |
US7324947B2 (en) * | 2001-10-03 | 2008-01-29 | Promptu Systems Corporation | Global speech user interface |
US8261306B2 (en) * | 2001-12-11 | 2012-09-04 | Koninklijke Philips Electronics N.V. | System for and method of shopping through television |
US20060206339A1 (en) * | 2005-03-11 | 2006-09-14 | Silvera Marja M | System and method for voice-enabled media content selection on mobile devices |
-
2003
- 2003-12-26 JP JP2004566305A patent/JPWO2004064393A1/ja not_active Withdrawn
- 2003-12-26 CN CNA2003801099175A patent/CN1757229A/zh active Pending
- 2003-12-26 AU AU2003296157A patent/AU2003296157A1/en not_active Abandoned
- 2003-12-26 WO PCT/JP2003/017015 patent/WO2004064393A1/ja active Application Filing
- 2003-12-26 US US10/542,409 patent/US7698138B2/en not_active Expired - Fee Related
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0916191A (ja) * | 1995-06-29 | 1997-01-17 | Asahi Chem Ind Co Ltd | ナビゲータ用音声認識装置および方法 |
JP2001022373A (ja) * | 1999-07-02 | 2001-01-26 | Alpine Electronics Inc | 音声認識方法 |
JP2001229180A (ja) * | 2000-02-17 | 2001-08-24 | Nippon Telegr & Teleph Corp <Ntt> | コンテンツ検索装置 |
JP2001258011A (ja) * | 2000-03-08 | 2001-09-21 | Sony Corp | データ送信方法および装置、データ受信方法および装置、データ表示方法および装置、並びに情報サービス方法および装置 |
JP2002290859A (ja) * | 2001-03-26 | 2002-10-04 | Sanyo Electric Co Ltd | ディジタル放送受信装置 |
JP2002330422A (ja) * | 2001-04-27 | 2002-11-15 | Sony Corp | デジタル放送を用いた商品販売ビジネスの方法、およびデジタル放送受信装置 |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006163710A (ja) * | 2004-12-06 | 2006-06-22 | Nec Corp | 番組情報蓄積装置及び方法並びに番組情報蓄積用プログラム |
JP2006285115A (ja) * | 2005-04-05 | 2006-10-19 | Hitachi Ltd | 情報提供方法および情報提供装置 |
JP4736511B2 (ja) * | 2005-04-05 | 2011-07-27 | 株式会社日立製作所 | 情報提供方法および情報提供装置 |
JP2013140520A (ja) * | 2012-01-05 | 2013-07-18 | Fujitsu Ltd | 画像再生装置、画像再生プログラム、及び画像再生方法 |
Also Published As
Publication number | Publication date |
---|---|
US7698138B2 (en) | 2010-04-13 |
JPWO2004064393A1 (ja) | 2006-05-18 |
AU2003296157A1 (en) | 2004-08-10 |
US20060259299A1 (en) | 2006-11-16 |
CN1757229A (zh) | 2006-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2004064393A1 (ja) | 放送受信方法、放送受信システム、記録媒体、及びプログラム | |
JP3762926B2 (ja) | 放送受信方法、放送システム、プログラム及び記録媒体 | |
US6553345B1 (en) | Universal remote control allowing natural language modality for television and multimedia searches and requests | |
KR101644789B1 (ko) | 방송 프로그램 연관 정보 제공 장치 및 방법 | |
US6513006B2 (en) | Automatic control of household activity using speech recognition and natural language | |
US8738371B2 (en) | User interactive apparatus and method, and computer program utilizing a direction detector with an electromagnetic transmitter for detecting viewing direction of a user wearing the transmitter | |
US8442389B2 (en) | Electronic apparatus, reproduction control system, reproduction control method, and program therefor | |
CN102378050B (zh) | 使用文本转语音转换的广播*** | |
US20110060592A1 (en) | Iptv system and service method using voice interface | |
KR20100067174A (ko) | 음성 인식을 이용한 메타데이터 검색기, 검색 방법, iptv 수신 장치 | |
CN106210901B (zh) | 显示装置 | |
CN113194346A (zh) | 一种显示设备 | |
JP2003255992A (ja) | 対話システムおよびその制御方法 | |
JPWO2007069512A1 (ja) | 情報処理装置及びプログラム | |
JP2001022374A (ja) | 電子番組ガイドの操作装置および電子番組ガイドの送信装置 | |
US20220293106A1 (en) | Artificial intelligence server and operation method thereof | |
US20210133609A1 (en) | Artificial intelligence device | |
JP4367713B2 (ja) | 放送受信方法、放送受信システム、第1装置、第2装置、音声認識方法、音声認識装置、プログラム及び記録媒体 | |
JP5330005B2 (ja) | デジタルフォトフレーム、情報処理システム及び制御方法 | |
US20230282209A1 (en) | Display device and artificial intelligence server | |
JP2017182275A (ja) | 情報処理装置、情報処理方法、及びプログラム | |
JP2005141328A (ja) | 予知ロボット装置、予知ロボットの制御方法、及び予知ロボットシステム | |
JP2010044614A (ja) | キーフレーズ抽出装置、シーン分割装置およびプログラム | |
US20230054251A1 (en) | Natural language processing device | |
WO2020240996A1 (ja) | 情報処理装置、情報処理方法、および、プログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): BW GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
DFPE | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101) | ||
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2004566305 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2006259299 Country of ref document: US Ref document number: 10542409 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 20038A99175 Country of ref document: CN |
|
122 | Ep: pct application non-entry in european phase | ||
WWP | Wipo information: published in national office |
Ref document number: 10542409 Country of ref document: US |