WO2023045459A1 - 接收装置及选台*** - Google Patents

接收装置及选台*** Download PDF

Info

Publication number
WO2023045459A1
WO2023045459A1 PCT/CN2022/101496 CN2022101496W WO2023045459A1 WO 2023045459 A1 WO2023045459 A1 WO 2023045459A1 CN 2022101496 W CN2022101496 W CN 2022101496W WO 2023045459 A1 WO2023045459 A1 WO 2023045459A1
Authority
WO
WIPO (PCT)
Prior art keywords
broadcasting station
character string
station name
information
replacement
Prior art date
Application number
PCT/CN2022/101496
Other languages
English (en)
French (fr)
Inventor
松原伸三
Original Assignee
海信视像科技股份有限公司
东芝视频解决方案株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 海信视像科技股份有限公司, 东芝视频解决方案株式会社 filed Critical 海信视像科技股份有限公司
Priority to CN202280007590.3A priority Critical patent/CN116547975A/zh
Publication of WO2023045459A1 publication Critical patent/WO2023045459A1/zh

Links

Images

Classifications

    • 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
    • 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
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • 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]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/27—Server based end-user applications

Definitions

  • Embodiments of the present invention relate to a receiving device and a channel selection system.
  • the receiving device for switching broadcasting stations based on a user's utterance.
  • the receiving device selects a broadcasting station corresponding to the broadcasting station name uttered by the user.
  • Patent Document 1 Japanese Patent Laid-Open No. 2003-223183
  • Patent Document 2 Japanese Patent Laid-Open No. 2004-260544
  • Patent Document 3 Japanese Patent Laid-Open No. 2007-010884
  • broadcasting stations sometimes have various titles that differ from the official broadcasting station name.
  • the receiving device cannot recognize the titles, resulting in channel selection failure.
  • the problem to be solved by this application is to provide a receiving device and a channel selection system capable of improving the accuracy of channel selection of broadcasting stations.
  • a receiving device is a broadcasting station that switches broadcasts based on a user's utterance, and includes: a receiving unit that receives the user's uttered voice as a voice signal; a storage unit that stores a database including information on broadcasting station names; a processing unit that retrieves a broadcasting station name corresponding to the sound signal from the database; and a communication unit that transmits character string information based on the sound signal to a replacement reading server, and receives from the replacement reading server Receive the replacement reading result of the character string information, the replacement reading server stores a replacement reading dictionary, and the address of the broadcast station name is the address information and the broadcast station name corresponding to the address. The replacement reads the dictionary.
  • FIG. 1 is a diagram showing an example of the configuration of a channel selection system according to Embodiment 1;
  • FIG. 2 is a diagram showing an example of a hardware configuration of a television device according to Embodiment 1;
  • FIG. 3 is a diagram showing an example of a functional configuration of a television device according to Embodiment 1;
  • FIG. 4 is a schematic diagram illustrating an example of functions of the television set according to Embodiment 1;
  • FIG. 5 is a flowchart showing an example of the procedure of channel selection processing of the television device according to Embodiment 1;
  • FIG. 6 is a schematic diagram illustrating an example of functions of a television set according to Embodiment 2;
  • FIG. 7 is a flowchart showing an example of the procedure of channel selection processing of the television device according to Embodiment 2;
  • FIG. 8 is a schematic diagram illustrating an example of functions possessed by a television device according to a modified example of Embodiment 2;
  • FIG. 9 is a flowchart showing an example of a procedure of channel selection processing of a television device according to a modified example of Embodiment 2;
  • FIG. 10 is a schematic diagram illustrating an example of functions of a television set according to Embodiment 3.
  • FIG. 11 is a flowchart showing an example of the procedure of channel selection processing including update processing of the broadcasting station database in the television device according to Embodiment 3;
  • FIG. 12 is a schematic diagram illustrating an example of functions of a television set according to a modified example of Embodiment 3;
  • FIG. 13 is a flowchart showing an example of a procedure of update processing of a broadcasting station database of a television device according to a modification of Embodiment 3.
  • FIG. 13 is a flowchart showing an example of a procedure of update processing of a broadcasting station database of a television device according to a modification of Embodiment 3.
  • 1...tunnel selection system 10, 20, 20a, 30, 30a...television device, 11...receiving part, 12, 22, 22a, 32, 32a...sound processing part, 13...display control part, 14...equipment control part, 15, 25, 25a, 35a...communication unit, 16...storage unit, 17...broadcasting station database, 40...network, 50...voice recognition server, 60...replacement reading server, 64...replacement reading dictionary.
  • FIG. 1 is a diagram showing an example of the configuration of a channel selection system 1 according to Embodiment 1.
  • the channel selection system 1 includes a television device 10 , a voice recognition server 50 , and a replacement reading server 60 , and provides voice recognition services to users of the television device 10 , for example.
  • the voice recognition service the user can perform an operation of selecting a broadcast station broadcast by the television device 10 by voice, for example.
  • the television device 10 , the voice recognition server 50 , and the replacement reading server 60 are connected to each other wirelessly or wiredly via a network 40 such as the Internet, for example.
  • the television device 10 as a receiving device can receive, for example, a broadcast signal from a broadcasting station and receive various programs.
  • the television device 10 has a voice recognition function, and upon detecting a broadcasting station name or a title of a broadcasting station issued by a user, switches broadcasting stations based on the voice recognition service.
  • the voice recognition function of the television device 10 is dedicated to detecting the user's voice. After the voice recognition service is started, the television device 10 provides the voice recognition service to the user using, for example, the voice recognition function of the voice recognition server 50 and the replacement reading function of the replacement reading server 60 .
  • the television device 10 transmits the detected voice signal to the voice recognition server 50 , and receives character string information in which the voice signal is converted into a character string corresponding to the voice recognition result by the voice recognition server 50 .
  • the television device 10 transmits the character string information received from the voice recognition server 50 to the replacement reading server 60, and the character string information receiving the replacement reading result by the replacement reading server 60 is read as a replacement Information about the corresponding broadcasting station name.
  • the voice recognition server 50 and the replacement reading server 60 are configured as, for example, a cloud server or the like placed on the cloud. At least one of the voice recognition server 50 and the replacement reading server 60 can also be configured to have a CPU (Central Processing Unit, central processing unit), a ROM (Read Only Memory, read-only memory), and a RAM (Random Access Memory, random access memory). One or more computers with physical structure such as memory).
  • a CPU Central Processing Unit, central processing unit
  • ROM Read Only Memory, read-only memory
  • RAM Random Access Memory, random access memory
  • the voice recognition function of the voice recognition server 50 and the replacement reading function of the replacement reading server 60 are realized by executing a program stored in a ROM or the like by a CPU constituting a cloud server or a computer, for example.
  • the voice recognition server 50 includes a voice recognition unit 51 , a communication unit 52 , and a storage unit 53 as functional units for realizing the voice recognition function.
  • the voice recognition unit 51 recognizes the voice signal uttered by the user received from the television device 10 via the communication unit 52 through analysis using, for example, natural language processing. At this time, the voice recognition unit 51 refers to the voice dictionary 54 of the storage unit 53 . The voice recognition unit 51 converts the recognized voice signal into character string information corresponding thereto.
  • the communication unit 52 performs communication with the television device 10 .
  • the communication unit 52 receives a user's voice signal from the television device 10 .
  • the communication unit 52 transmits the character string information to the television device 10 .
  • the storage unit 53 stores various parameters and information necessary for the voice recognition server 50 to realize the above functions.
  • the storage unit 53 includes a voice dictionary 54 storing voice data for analyzing voice signals from the user.
  • the voice data contained in the voice dictionary 54 includes information on various elements such as phonemes and features that can be included in the voice signal from the user, and the voice recognition unit 51 compares the voice data with the voice signal from the user as a key for recognizing the voice. index.
  • the phonemes and features that can be included in the voice signal from the user can be based on the character strings included in the titles of existing broadcasting stations.
  • the user's utterance is, for example, "e nie e ti kie", it can be easily converted into the correct character string of "NHK”.
  • the user's utterance is "hu ji te re bi”
  • it is not converted to "Fuji te re bi” etc., but to the correct character string of "hu ji te re bi”.
  • the plurality of voice data may include various voice data based on gender and age, such as for men, for women, and for children.
  • the storage unit 53 is configured as, for example, a large-capacity storage device. Thereby, the storage unit 53 can store, for example, the voice dictionary 54 having a huge amount of voice data as described above, and the voice recognition server 50 can perform high-precision voice recognition.
  • the replacement reading server 60 When the content of the user's utterance detected by the television device 10 is the title of the broadcasting station, the replacement reading server 60 replaces and reads it into the official broadcasting station name.
  • the replacement reading server 60 includes a replacement reading processing unit 61 , a communication unit 62 , and a storage unit 63 as functional units for realizing such a replacement reading function.
  • the replacement reading processing unit 61 analyzes the character string information received from the television device 10 via the communication unit 62 and replaces and reads it into an official broadcasting station name. At this time, the replacement reading processing unit 61 refers to the replacement reading dictionary 64 of the storage unit 63 .
  • the communication unit 62 performs communication with the television device 10 .
  • the communication unit 62 receives from the television device 10 character string information in which the user's voice signal is converted into a character string. Furthermore, the communication unit 62 transmits the broadcasting station name corresponding to the character string information to the television device 10 .
  • the storage unit 63 stores various parameters and information necessary for the replacement reading server 60 to realize the above functions.
  • the storage unit 63 includes an alternative reading dictionary 64 storing data for analyzing character string information.
  • the replacement reading dictionary 64 stores, for example, information on various names of broadcasting stations.
  • FIG. 2 is a diagram showing an example of the hardware configuration of the television device 10 according to the first embodiment.
  • television set 10 includes antenna 101, input terminals 102a to 102c, tuner 103, demodulator 104, demultiplexer 105, A/D (analog/digital) converter 106, selector 107, Signal processing section 108, speaker 109, display panel 110, operation section 111, light receiving section 112, IP communication section 113, CPU 114, memory (memory) 115, memory (storage) 116, microphone 117, and audio frequency (audio) I/ F (interface) 118 .
  • the antenna 101 receives broadcast signals of digital broadcasts, and supplies the received broadcast signals to the tuner 103 via the input terminal 102a.
  • the tuner 103 selects a broadcast signal of a desired channel among the broadcast signals supplied from the antenna 101 , and supplies the selected broadcast signal to the demodulator 104 .
  • the demodulator 104 demodulates the broadcast signal supplied from the tuner 103 and supplies the demodulated broadcast signal to the demultiplexer 105 .
  • the demultiplexer 105 separates the broadcast signal supplied from the demodulator 104 and generates an image signal and a sound signal, and supplies the generated image signal and sound signal to the selector 107 .
  • the selector 107 selects one of a plurality of signals supplied from the demultiplexer 105 , the A/D converter 106 , and the input terminal 102 c, and supplies the selected one signal to the signal processing section 108 .
  • the signal processing unit 108 performs predetermined signal processing on the image signal supplied from the selector 107 , and supplies the processed image signal to the display panel 110 . Also, the signal processing unit 108 performs predetermined signal processing on the audio signal supplied from the selector 107 , and supplies the processed audio signal to the speaker 109 .
  • the speaker 109 outputs sound or various voices based on the sound signal supplied from the signal processing unit 108 .
  • the speaker 109 changes the volume of the output sound or various voices based on the control of the CPU 114.
  • the display panel 110 as a display unit displays video such as still images and moving images, other images, text information, etc. based on the image signal supplied from the signal processing unit 108 or the control of the CPU 114.
  • the input terminal 102b receives analog signals such as image signals and audio signals input from the outside.
  • the input terminal 102c receives digital signals such as image signals and audio signals input from the outside.
  • the input terminal 102c can input a digital signal from a recorder or the like equipped with a drive device that drives a storage medium for recording and playback such as BD (Blu-ray Disc) (registered trademark) to perform recording and playback.
  • BD Blu-ray Disc
  • the A/D converter 106 supplies the selector 107 with a digital signal generated by performing A/D conversion on the analog signal supplied from the input terminal 102b.
  • the operation unit 111 receives user's operation input.
  • the light receiving unit 112 receives infrared rays from the remote controller 119 .
  • the IP communication unit 113 is a communication interface for performing IP (Internet Protocol) communication via the network 40 .
  • the CPU 114 as a control unit controls the entire television set 10.
  • the memory 115 is a ROM for storing various computer programs executed by the CPU 114, a RAM for providing a work area (area) to the CPU 114, and the like.
  • the ROM stores a voice recognition program for the television device 10 to detect a user's voice, an application program for providing a voice recognition service, and the like.
  • the memory 116 is HDD (Hard Disk Drive, hard disk drive) or SSD (Solid State Drive, solid state drive), etc.
  • the memory 116 stores, for example, the signal selected by the selector 107 as recorded data.
  • the microphone 117 serving as a voice input unit acquires the voice uttered by the user, and sends it to the audio I/F 118.
  • the audio I/F 118 converts the sound acquired by the microphone 117 into an analog/digital signal, and sends it to the CPU 114 as a sound signal.
  • FIG. 3 is a diagram showing an example of the functional configuration of the television device 10 according to the first embodiment.
  • the above-mentioned CPU 114 executes a program stored in, for example, the ROM, so that the voice recognition function of the television device 10 and the like can be realized.
  • the program executed in the television device 10 has a modular structure including each functional unit described below.
  • the television device 10 includes a reception unit 11 , an audio processing unit 12 , a display control unit 13 , a device control unit 14 , a communication unit 15 , and a storage unit 16 as functional units realizing the functions of the television device 10 .
  • the receiving unit 11 receives various inputs from the user. For example, the receiving unit 11 receives the user's voice input into the microphone 117 as a voice signal via the audio I/F 118 . In addition, for example, the reception unit 11 receives various instructions by operation input from the operation unit 111 or the remote controller 119 .
  • the audio processing unit 12 as a processing unit performs processing related to the user's voice received by the receiving unit 11 .
  • the voice processing unit 12 transmits the voice signal received by the receiving unit 11 to the voice recognition server 50 via the communication unit 15 .
  • the audio processing unit 12 searches the broadcast station name corresponding to the audio signal from the broadcast station database 17 stored in the storage unit 16 based on the replacement reading result received from the replacement reading server 60 via the communication unit 15 .
  • the audio processing unit 12 selects the broadcast station as a switching target broadcast station.
  • the display control unit 13 controls various displays displayed on the display panel 110 . For example, when the receiving unit 11 acquires a user's operation using the remote control 119 , the display control unit 13 displays an operation screen corresponding to the operation on the display panel 110 . Also, when the voice recognition service is started by detecting the voice uttered by the user, the display control unit 13 displays a message, an icon, or the like in response to the voice on the display panel 110 . These messages, icons, and the like are, for example, displaying the content of the selected broadcasting station.
  • the device control unit 14 controls each unit of the television device 10 .
  • the device control unit 14 controls each unit of the television device 10 based on commands included in the user's voice to switch the broadcasting station broadcasted by the television device 10 to the selected broadcasting station during voice recognition service provision.
  • the communication unit 15 controls communication with external devices via the network 40 .
  • the communication unit 15 controls the communication between the voice recognition server 50 and the replacement reading server 60 and the television device 10 when providing the voice recognition service.
  • the communication unit 15 receives information about broadcasting stations included in the broadcasting signal, obtains the broadcasting station names of the broadcasting stations receivable in the area where the television device 10 is installed, and stores them in the broadcasting station database 17 of the storage unit 16 at all times.
  • the storage unit 16 stores various parameters, information, and the like required to realize the functions of the television device 10 as described above.
  • the storage unit 16 includes a broadcasting station database 17 that stores official broadcasting station name information used to identify broadcasting stations based on voice signals from users. Channel selection information. As described above, the information on the broadcasting station name in the broadcasting station database 17 is constantly updated by the communication unit 15 .
  • FIG. 4 is a schematic diagram illustrating an example of functions of the television device 10 according to the first embodiment.
  • the receiving unit 11 receives the voice uttered by the user as a voice signal (processing P11 ), and passes it to the voice processing unit 12 (processing P12 ).
  • the audio processing unit 12 further transmits the audio signal to the communication unit 15 (processing P13).
  • the communication unit 15 transmits the transmitted audio signal to the voice recognition server 50, and receives character string information converted from the audio signal into a character string (process P14).
  • the voice recognition unit 51 analyzes the voice signal received from the television device 10 and converts it into a character string, and generates character string information as a voice recognition result.
  • the voice recognizer 51 extracts "te re a sa" as a part corresponding to the name of the broadcasting station from the voice signal of "te re a sa ni site" received by the television device 10, and converts it to A character string converted to "te re ⁇ ".
  • the communication unit 15 transmits the character string information received from the voice recognition server 50 to the replacement reading server 60, and receives information on the name of the broadcasting station whose character string information is replaced and read (process P15).
  • the replacement processing unit 61 analyzes the character string information received from the television device 10 and replaces and reads it with an official broadcasting station name, and generates broadcasting station name information as a replacement reading result.
  • the replacement reading processing unit 61 refers to the replacement reading dictionary 64 stored in the storage unit 63 .
  • Various titles of broadcasting stations ie, title information, are stored in the replacement reading dictionary 64 in association with corresponding broadcasting station names.
  • one piece of title information may be associated with one broadcasting station, or when one broadcasting station has a plurality of titles, a plurality of pieces of title information may be associated with one broadcasting station.
  • the broadcasting station to be replaced and read for example, broadcasting stations covering the whole country may be used. Accordingly, regardless of where the television device 10 is installed, it is possible to respond to a replacement reading request from the television device 10 .
  • the name of the broadcasting station there may be a common name, an abbreviation, an alias, an old name, etc. of the broadcasting station.
  • NHK E te re can have abbreviations such as E te re and aliases such as education te re bi. Therefore, in the replacement reading dictionary 64, the information of character strings such as "E te re" and "education te re bi" which are titles to be replaced and read are associated with "NHK E te re" which is the official broadcasting station name. save.
  • the replacement reading processing unit 61 searches the replacement reading dictionary 64 for a replacement reading target character string that matches the character string information of “te re ⁇ ” received from the television device 10 .
  • a character string of "te re asa” is associated with “te re bi Asahi” together with a character string such as "Channel 5".
  • the replacement reading processing unit 61 generates information of a broadcast station name in which "te re asa" is replaced and read as "te re bi Asahi”.
  • the replacement reading target character string of the replacement reading dictionary 64 may not include A character string matching the character string information received from the television device 10 is included.
  • the alternative reading server 60 transmits an alternative reading result that there is no matching broadcast station name to the television device 10 .
  • the communication unit 15 passes the replacement reading result received from the replacement reading server 60 to the audio processing unit 12 (process P16).
  • the audio processing unit 12 searches the broadcasting station database 17 of the storage unit 16 for the broadcasting station name that matches the replacement reading result ( Process P17).
  • the broadcasting station database stores information on the official names of each broadcasting station, such as "NHK General TV”, “NHK E te re”, “Nippon te re bi”, and “te re bi Asahi”.
  • the audio processing unit 12 selects te re bi Asahi that matches "te re bi Asahi" included in the replacement read result from the broadcasting station database 17.
  • the device control unit 14 of the television device 10 controls each part of the television device 10, and switches the broadcasting station broadcast by the television device 10 to te re bi Asahi.
  • the voice processing unit 12 searches the broadcasting station database 17 and recognizes it from the voice. The name of the broadcasting station matched by the character string information received by the server 50. When there is a matching broadcast station name, the audio processing unit 12 selects the broadcast station name, and the device control unit 14 switches the broadcast station broadcast by the television device 10 to the selected broadcast station.
  • the broadcasting station database 17 does not have any information related to the broadcasting station name from the replacement reading server 60 or the character string information from the voice recognition server 50. In the case of a matching broadcasting station name, it means that the broadcasting station selection failed, and the switching of the broadcasting station will not be performed.
  • the display control unit 13 displays a channel selection failure on the display panel 110 .
  • FIG. 5 is a flowchart showing an example of the procedure of the channel selection process of the television device 10 according to the first embodiment.
  • the receiving unit 11 receives the voice uttered by the user as a voice signal (step S101 ).
  • the communication unit 15 transmits the audio signal received by the receiving unit 11 to the voice recognition server 50 (step S102).
  • the voice recognition unit 51 analyzes the voice signal, and generates character string information in which the recognized voice signal is converted into a character string.
  • the communication unit 15 of the television device 10 receives character string information corresponding to the voice signal from the voice recognition server 50 as a voice recognition result (step S103 ).
  • the communication unit 15 transmits the received character string information to the replacement reading server 60 (step S104).
  • the replacement reading processing unit 61 refers to the replacement reading dictionary 64 to search for a broadcast station name corresponding to the character string information. When there is a corresponding broadcast station name, the replacement reading processing unit 61 generates information of broadcast station names including the broadcast station name as a replacement reading result. When there is no corresponding broadcast station name, the replacement reading processing unit 61 generates information that there is no matching broadcast station name as a replacement reading result.
  • the communication unit 15 of the television device 10 receives the replacement reading result from the replacement reading server 60 (step S105 ).
  • the audio processing unit 12 searches the broadcasting station database 17 based on the replacement reading result (step S106).
  • the audio processing unit 12 searches the broadcast station database 17 for a broadcast station name that matches the replacement read result.
  • the voice processing unit 12 searches the broadcasting station database 17 for a broadcasting station name that matches the character string information received from the voice recognition server 50 .
  • the audio processing unit 12 determines whether or not there is a broadcast station name that matches the replacement read result or the character string information based on the search result of the broadcast station database 17 (step S107 ). If there is a matching broadcast station name (step S107: Yes), the device control unit 14 switches to the broadcast station (step S108). If there is no matching broadcast station name (step S107: No), the display control unit 13 displays on the display panel 110 that the broadcast station cannot be switched (step S109).
  • broadcasting stations may have various titles other than the official broadcasting station name, and when the user utters the title of the broadcasting station, it may not be recognized by the television device and channel selection may fail.
  • the voice recognition server 50 converts the expression into an expression different from the official name of the broadcasting station, the television device cannot recognize it.
  • the voice recognition server 50 converts it into a character string based on the old name. Since the broadcasting station database of the TV device is updated with the latest data at any time, the TV device cannot recognize the character string converted from the old name in the above case, resulting in channel selection failure.
  • the character string information based on the audio signal is sent to the replacement reading server 60 storing the replacement reading dictionary 64 including the address information of the broadcasting station name, and the character string information is received from the replacement reading server 60. Replacement read result of string information.
  • the accuracy of channel selection of broadcasting stations by the television device 10 can be improved. There is no need to store title information in the broadcasting station database 17 of the television device 10 or to reinstall the software of the television device 10 in order to add title information.
  • FIG. 6 is a schematic diagram illustrating an example of functions of the television device 20 according to the second embodiment.
  • symbol is attached
  • the voice signal and character string information converted into a character string are exchanged between the communication unit 25 and the voice recognition server 50 (Processes P11 to P14).
  • the communication unit 25 passes the character string information received from the voice recognition server 50 to the voice processing unit 22 (process P21).
  • the audio processing unit 22 searches the broadcasting station database 17 of the storage unit 16 for a broadcasting station name matching the character string information (processing P22).
  • the sound processing unit 22 selects the broadcast station, and the equipment control unit 14 (referring to FIG. 3 ) of the television device 20 controls each part of the television device 20 to switch the broadcast station broadcast by the television device 20 to the selected one. Broadcasting station.
  • the audio processing unit 22 cannot find a broadcasting station name that matches the character string information of "te re morning" received from the voice recognition server 50 from the broadcasting station database 17.
  • the communication unit 25 receives from the audio processing unit 22 information that there is no broadcast station name matching the character string information in the broadcast station database 17 (processing P23 ). Subsequent processing is the same as in the case of the television device 10 according to Embodiment 1 described above.
  • the communication unit 25 transmits the character string information received from the voice recognition server 50 to the replacement reading server 60, and receives the replacement reading result from the replacement reading server 60 (process P25).
  • the sound processing unit 22 selects the matching broadcasting station name from the broadcasting station database 17 (processing P26, P27), and the device control unit 14 switches the broadcasting station broadcasted by the television device 20. for the selected radio station.
  • the display control unit 13 displays the failure of the station selection on The display panel 110 of the television device 20 .
  • FIG. 7 is a flowchart showing an example of the procedure of the channel selection process of the television device 20 according to the second embodiment.
  • steps S201 to S203 is the same as the processing of steps S101 to S103 shown in FIG. 5 of Embodiment 1 described above. That is, the user's voice signal is sent to the voice recognition server 50 and the character string information converted into a character string is received (steps S201 to S203).
  • the audio processing unit 22 searches the broadcast station database 17 for a broadcast station name matching the character string information (step S204). Furthermore, the audio processing unit 22 determines whether there is a broadcast station name matching the character string information based on the search result of the broadcast station database 17 (step S205 ). If there is a matching broadcast station name (step S205: Yes), the device control unit 14 switches to the broadcast station (step S211).
  • step S205 If there is no matching broadcast station name (step S205: No), the communication unit 25 sends the character string information received from the voice recognition server 50 to the replacement reading server 60 (step S206), and receives the replacement from the replacement reading server 60. Read the result (step S207).
  • the audio processing unit 22 determines whether or not the broadcasting station name is included in the replacement reading result received by the communication unit 25 (step S208). When the broadcast station name is not included (step S208: No), the display control unit 13 displays on the display panel 110 that the broadcast station cannot be switched (step S212).
  • the audio processing unit 22 searches the broadcast station database 17 for a broadcast station name that matches the broadcast station name included in the replacement read result (step S209).
  • the audio processing unit 22 determines whether or not there is a matching broadcast station name based on the search result of the broadcast station database 17 (step S210 ). When there is a matching broadcast station name (step S210: Yes), the device control unit 14 performs switching to the broadcast station (step S211).
  • step S210: No the display control unit 13 displays on the display panel 110 that the broadcast station cannot be switched (step S212).
  • the communication unit 25 transmits the character string information to the replacement reading server 60. . In this way, the communication unit 25 waits for the search result of the audio processing unit 22 based on the character string information, and then makes a replacement reading request to the replacement reading server 60 as necessary.
  • the number of accesses to the replacement reading server 60 can be reduced, and the workload of the television device 20 and the replacement reading server 60 can be reduced.
  • the processing time until the broadcasting station is selected can be shortened in accordance with the search time in the replacement reading server 60 .
  • a television device 20 a according to a modified example of Embodiment 2 will be described with reference to FIGS. 8 and 9 .
  • the timing at which the television device 20 a of the modified example transmits the character string information to the replacement reading server 60 is different from that of the second embodiment described above.
  • FIG. 8 is a schematic diagram illustrating an example of functions of a television device 20a according to a modification of Embodiment 2. As shown in FIG. In addition, in the following description, the same code
  • the voice signal and the character string information converted into a character string are exchanged (processing) between the communication unit 25a and the voice recognition server 50 . P11 ⁇ P14).
  • the communication unit 25a passes the character string information received from the voice recognition server 50 to the voice processing unit 22a (process P21).
  • the audio processing unit 22a searches the broadcasting station database 17 of the storage unit 16 for a broadcasting station name matching the character string information (processing P22a).
  • the communication unit 25a transmits the character string information received from the voice recognition server 50 to the replacement reading server 60 in parallel with the search process of the voice processing unit 22a without waiting for the search result of the broadcasting station database 17 by the voice processing unit 22a. , the exchange with the replacement reading server 60 is started (processing P25a).
  • Access to the replacement reading server 60 via the communication unit 25a and reading processing in the replacement reading server 60 take more time than searching the broadcasting station database 17 of the voice processing unit 22a based on character string information. Therefore, it can be considered that the search result of the audio processing unit 22 a is obtained before the communication unit 25 a receives the replacement reading result from the replacement reading server 60 .
  • the communication part 25 When the communication part 25 is in the process of exchanging with the replacement reading server 60, and there is a broadcast station name matching the character string information in the broadcasting station database 17, the communication part 25 cancels the replacement reading server 60. Replacement reading of string information.
  • the communication part 25 When the communication part 25 is in the process of exchanging with the replacement reading server 60, and there is no broadcasting station name matching the character string information in the broadcasting station database 17, the communication part 25 does not need to cancel the replacement reading server 60. The replacement reading of the character string information of , and waits to receive the replacement reading result.
  • Subsequent processing is the same as in the case of the television device 20 according to Embodiment 2 described above. That is, if the communication unit 25a receives the replacement reading result, the voice processing unit 22a selects the matching broadcasting station name from the broadcasting station database 17 if the replacement reading result includes the broadcasting station name (processing P26, P27) , the device control unit 14 switches the broadcast station broadcast by the television device 20a to the selected broadcast station.
  • the display control unit 13 displays the failure of the station selection on the television device. 20 display panel 110 .
  • FIG. 9 is a flowchart showing an example of the procedure of the channel selection process performed by the television device 20 a according to the modified example of the second embodiment.
  • steps S201 to S204 is the same as the processing of steps S201 to S204 shown in FIG. 7 of the second embodiment described above. That is, the user's voice signal is transmitted to the voice recognition server 50 and the character string information converted into a character string is received, and the search of the broadcast station database 17 based on the character string information is started (steps S201 to S204 ).
  • the communication unit 25a transmits the character string information received from the voice recognition server 50 to the replacement reading server 60 (step S204a).
  • the audio processing unit 22a determines whether there is a broadcast station name matching the character string information based on the search result of the broadcast station database 17 based on the character string information (step S205). When there is a matching broadcast station name (step S205: Yes), the communication unit 25a cancels access to the replacement reading server 60 (step S207a), and the device control unit 14 switches to the broadcast station (step S211).
  • step S205: No When there is no broadcast station name matching the character string information (step S205: No), the subsequent processing is the same as the processing starting from step S207 in FIG. 7 of the second embodiment described above.
  • the communication unit 25a waits for the replacement reading process of the replacement reading server 60 to receive the replacement reading result, and if the replacement reading result includes the name of the broadcasting station, the audio processing unit 22a executes the broadcasting station database 17 based on the replacement reading result. If there is a matching broadcasting station name in the search, the device control unit 14 switches to the broadcasting station (steps S207 to S211).
  • the display control unit 13 displays on the display panel 110 that the broadcast station cannot be switched (steps S208, S212).
  • the communication unit 25 a transmits the character string information to the replacement reading server 60 in parallel with searching for a broadcasting station name matching the character string information received from the voice recognition server 50 .
  • the search process of the voice processing part 22a and the search process of the alternative reading server 60 can be performed simultaneously, and the processing time until selection of a broadcasting station can be further shortened.
  • the communication unit 25 a cancels the replacement reading of the character string information in the replacement reading server 60 when the broadcasting station name matching the character string information exists in the broadcasting station database 17 . Accordingly, it is possible to further reduce the workload of the replacement reading server 60, or to further shorten the processing time until selection of a broadcasting station.
  • the television device according to the third embodiment is different from the second embodiment described above in that it updates the broadcasting station database.
  • FIG. 10 is a schematic diagram illustrating an example of functions of the television device 30 according to the third embodiment.
  • symbol is attached
  • television device 30 according to Embodiment 3 has, for example, the function of TV device 20 according to Embodiment 2 and a function of updating broadcasting station database 37 stored in storage unit 36 .
  • the broadcasting station database 37 of the storage unit 36 is configured to store one or more appellations of the broadcasting station associated with each broadcasting station name in addition to information on the official name of the broadcasting station.
  • the title information of "Channel 1" has been stored in the item "NHK General Television” of the broadcasting station database 37
  • the title of "Channel 5" has been stored in the item "te re bi Asahi”. information.
  • the voice processing unit 32 of the television device 30 also refers to the address information stored in the broadcast station database 37 when searching the broadcast station database 37 for a broadcast station name matching the character string information received from the voice recognition server 50 . Except for this, the operation of the processing P11 to P27 of the television device 30 is the same as the operation shown in FIG. 6 of the second embodiment described above.
  • the audio processing unit 32 finds a broadcasting station name that matches the broadcasting station name included in the replacement reading result of the replacement reading server 60 in the broadcasting station database 37, and sets the broadcasting station as a broadcasting station to be selected.
  • the character string information converted into a character string by the voice recognition server 50 is added to the broadcast station database 37 in association with the broadcast station name of the broadcast station to be selected.
  • the part related to the broadcasting station name of the sound signal of "te re a sa ni si te" based on the user's utterance is converted into a character string of "te re toward", which is determined by the television device 30.
  • the communication unit 25 receives it.
  • the sound processing unit 32 finds a broadcasting station name matching "te re bi Asahi” in which the character string "te re Asahi” has been replaced and read from the broadcasting station database 37, and selects te re bi Asahi as a channel selection object.
  • the voice processing unit 32 adds character string information including the character string "te re asa” as the title of "te re bi Asahi” in the broadcasting station database 37 (processing P28).
  • the item of "te re bi Asahi” is found to contain the character string information converted by the voice recognition server 50 and contains "te re towards”.
  • Matching appellation does not need to perform a replacement reading request to the replacement reading server 60, and te re bi Asahi is selected as the channel selection object.
  • FIG. 11 is a flowchart showing an example of the procedure of the channel selection process including the update process of the broadcasting station database 37 in the television device 30 according to the third embodiment.
  • steps S301 to S310 is the same as the processing of steps S201 to S210 shown in FIG. 7 of Embodiment 2 described above.
  • step S301 to S310 When the audio processing unit 32 of the television device 30 finds a broadcasting station name that matches the broadcasting station name included in the replacement reading result received from the replacement reading server 60 from the broadcasting station database 37 (steps S301 to S310), The character string information received from the voice recognition server 50 (step S303) is associated with the broadcasting station name matching the replacement read result and added to the broadcasting station database 37 (step S311).
  • Step S312 the processing when the character string information or the broadcasting station name matching the broadcasting station name included in the replacement read result is found in the broadcasting station database 37 (step S312), and the processing when it is not found (Step S313 ) is the same as the processing of steps S211 and S212 shown in FIG. 7 of Embodiment 2 described above.
  • the audio processing unit 32 sets The character string information is added to the broadcast station database 37 in association with the broadcast station name matching the broadcast station name information based on the character string information.
  • the broadcasting station database 37 can be appropriately expanded, and the retrieval accuracy of the audio processing unit 32 can be improved.
  • the number of accesses to the replacement reading server 60 can be further reduced, the workload of the television device 30 and the replacement reading server 60 can be reduced, and the time until a broadcasting station is selected can be shortened.
  • a television device 30a according to a modified example of Embodiment 3 will be described with reference to FIGS. 12 and 13 . Except for the timing of the channel selection process, the television device 30 a according to the modified example differs from the third embodiment described above in that it updates the broadcasting station database.
  • FIG. 12 is a schematic diagram illustrating an example of functions of a television device 30 a according to a modification of the third embodiment.
  • symbol is attached
  • the television apparatus 30a of the modified example also has the function of updating the broadcast station stored in the storage unit 36a based on the address information acquired from the replacement reading server 60. Function of the database 37a. That is, the television device 30a performs update processing of the broadcast station database 37a in addition to the operations of the processing P11 to P28 shown in FIG. 10 of the third embodiment described above.
  • the audio processing unit 32a of the television device 30a notifies the communication unit 35a that no audio signal from the user is currently being received at a predetermined timing when the channel selection process has not been performed (process P31).
  • a predetermined timing for example, there is a timing when the television device 30a is turned on.
  • the communication unit 35a acquires, from the replacement reading dictionary 64 stored in the storage unit 63 of the replacement reading server 60, the information of the replacement reading target character string associated with the broadcasting station name, that is, the address information of the corresponding broadcasting station (process P32) .
  • the communication unit 35a passes the title information acquired from the replacement reading server 60 to the voice processing unit 32a (process P33).
  • the audio processing unit 32a registers them in the broadcast station database 37a in association with the corresponding broadcast station name (process P34).
  • the television device 30a performs channel selection processing autonomously without accessing the alternative reading server 60 for a predetermined period.
  • the broadcasting station database 37a of the storage unit 36a is appropriately updated to the latest state at a predetermined timing, even if the user utters the appellation of a predetermined broadcasting station, the appellation uttered can be found from the broadcasting station database 37a. There is no need to access the replacement read server 60 .
  • the period during which the television device 30a independently performs the channel selection process without accessing the replacement reading server after updating the broadcasting station database 37a once can be appropriately set based on the frequency of expansion of the replacement reading server 60 . It is also possible to set the timing itself for updating the broadcast station database 37 a according to the expansion frequency of the replacement reading server 60 .
  • FIG. 13 is a flowchart showing an example of a procedure for updating the broadcasting station database 37a of the television device 30a according to the modification of the third embodiment.
  • the audio processing unit 32a of the television device 30a determines whether or not it is a predetermined timing such as the timing of starting the television device 30a (step S321 ).
  • the audio processing unit 32a waits until a predetermined timing is reached (step S321: NO).
  • step S321: YES the communication unit 35a acquires title information from the replacement reading dictionary 64 of the replacement reading server 60 (step S322).
  • the voice processing unit 32a searches the broadcast station database 37a for matching title information (step S323).
  • the audio processing unit 32a determines whether or not there is matching title information in the broadcast station database 37a based on the search result of the broadcast station database 37a (step S324).
  • step S324: No the voice processing section 32a associates its appellation information with the corresponding broadcast station name and adds it to the broadcast station database 37a (step S325). (Step S324: Yes), without adding the title information, it is determined whether the title information is the last title information acquired from the replacement reading server 60 (step S326).
  • step S326: No If it is not the last title information (step S326: No), the voice processing unit 32a repeats the process starting from step S323, and sequentially adds unregistered title information to the broadcasting station database 37a. When it is the last address information (step S326: YES), the audio processing unit 32a ends the processing.
  • the communication unit 35a acquires the title information from the replacement reading server 60 at a predetermined timing when no audio signal is received, and the voice processing unit 32a combines the title information acquired by the communication unit 35a with the corresponding broadcasting station name It is added to the broadcasting station database 37a in association.
  • the broadcast station database 37 can be expanded in advance before the next channel selection process. Therefore, in the subsequent channel selection processing, the search accuracy of the audio processing unit 32a can be further improved. In addition, in the subsequent channel selection process, the number of accesses to the replacement reading server 60 can be further reduced, the workload of the television device 30a and the replacement reading server 60 can be further reduced, and the time until the broadcast station is selected can be further shortened. .
  • the television apparatuses 30 and 30a of the above-mentioned third embodiment and the modified examples perform the same channel selection process as the television apparatus 20 of the second embodiment except that they have the update function of the broadcasting station databases 37 and 37a.
  • the television device performing the channel selection process of Embodiment 1 or the channel selection process of the modified example of Embodiment 2 may have the updating function of the broadcasting station database of the television devices 30 and 30a of Embodiment 3 or its modified example.
  • the channel selection system 1 and the like include the voice recognition server 50 and the replacement reading server 60 .
  • the voice recognition server and the replacement reading server may also be configured integrally. That is, the channel selection system may further include a server having a voice recognition function and a replacement reading function.
  • programs for realizing the various functions described above in the television device 10 and the like are provided as computer program products in an installable form or in an executable form. That is, the above-mentioned programs are provided in a state of being included in a computer program product having a non-volatile computer-readable storage medium such as CD-ROM, flexible disk (FD), CD-R, and DVD.
  • a non-volatile computer-readable storage medium such as CD-ROM, flexible disk (FD), CD-R, and DVD.
  • the above-mentioned program may be stored in a computer connected to a network such as the Internet, and may be provided or distributed via the network.
  • the above-mentioned programs may also be provided in a state preinstalled in a ROM or the like.
  • the CPU of the television device 10 or the like By installing such a program in the television device 10 or the like, the CPU of the television device 10 or the like reads the program from the ROM, and develops the above-described respective functional configurations on the RAM.
  • the above-described program may be provided as a web application stored in a cloud server or the like, and in this case, the program can be executed without being installed in the television device 10 or the like.
  • the receiving device is the television device 10, 20, 20a, 30, 30a, but the configuration of the embodiment is not limited thereto.
  • the receiving device may also be a personal computer, a smart phone, a tablet computer, a mobile phone, or other equipment equipped with a broadcast signal receiving function, a broadcasting function, and a voice recognition service function.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Signal Processing (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

本申请涉及的接收装置及选台***提高广播台的选台精度。接收装置基于语音切换广播台，具备：接收部，其接收所述用户发声的声音作为声音信号；存储部，其存储有包含广播台名的信息在内的数据库；处理部，其从数据库中检索与所述声音信号对应的广播台名；以及通信部，其向替换读取服务器发送基于所述声音信号的字符串信息，并且从替换读取服务器接收字符串信息的替换读取结果，其中，所述替换读取服务器保持替换读取词典，所述广播台名的称呼即称呼信息和与称呼对应的广播台名相关联地保存于所述替换读取词典。

Description

接收装置及选台***
相关申请的交叉引用
本申请要求在2021年9月27日提交日本专利局、申请号为2021-156859、发明名称为“接收装置及选台***”的日本专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明的实施方式涉及接收装置及选台***。
背景技术
存在基于用户的发声而切换播送的广播台的接收装置。接收装置对用户发声的与广播台名对应的广播台进行选台。
在先技术文献
专利文献
专利文献1：日本特开2003-223183号公报
专利文献2：日本特开2004-260544号公报
专利文献3：日本特开2007-010884号公报
发明内容
然而，有时广播台存在与正式的广播台名不同的各种称呼。在用户发声这些称呼的情况下，接收装置无法识别该称呼而导致选台失败。
本申请要解决的课题是提供一种能够提高广播台的选台精度的接收装置及选台***。
实施方式的接收装置基于用户的发声而切换播送的广播台，具备：接收部，其接收所述用户发声的声音作为声音信号；存储部，其存储有包含广播台名的信息在内的数据库；处理部，其从所述数据库中检索与所述声音信号对应的广播台名；以及通信部，其向替换读取服务器发送基于所述声音信号的字符串信息，并从所述替换读取服务器接收所述字符串信息的替换读取结果，所述替换读取服务器存有替换读取词典，所述广播台名的称呼即称呼信息和与所述称呼对应的广播台名相关联地保存于所述替换读取词典。
附图说明
图1是表示实施方式1的选台***的结构的一例的图；
图2是表示实施方式1的电视装置的硬件结构的一例的图；
图3是表示实施方式1的电视装置的功能结构的一例的图；
图4是说明实施方式1的电视装置具有的功能的一例的模式图；
图5是表示实施方式1的电视装置的选台处理的顺序的一例的流程图；
图6是说明实施方式2的电视装置具有的功能的一例的模式图；
图7是表示实施方式2的电视装置的选台处理的顺序的一例的流程图；
图8是说明实施方式2的变形例的电视装置具有的功能的一例的模式；
图9是表示实施方式2的变形例的电视装置的选台处理的顺序的一例的流程图；
图10是说明实施方式3的电视装置具有的功能的一例的模式图；
图11是表示实施方式3的电视装置的包含广播台数据库的更新处理在内的选台处理的顺序的一例的流程图；
图12是说明实施方式3的变形例的电视装置具有的功能的一例的模式图；
图13是表示实施方式3的变形例的电视装置的广播台数据库的更新处理的顺序的一例的流程图。
附图标记说明
1…选台***，10、20、20a、30、30a…电视装置，11…接收部，12、22、22a、32、32a…声音处理部，13…显示控制部，14…设备控制部，15、25、25a、35a…通信部，16…存储部，17…广播台数据库，40…网络，50…声音识别服务器，60…替换读取服务器，64…替换读取词典。
具体实施方式
[实施方式1]
下面，参照附图详细地说明实施方式1。
(选台***的结构)
图1是表示实施方式1的选台***1的结构的一例的图。如图1所示，选台***1具备电视装置10、声音识别服务器50、以及替换读取服务器60，例如向电视装置10的用户提供声音识别服务。根据声音识别服务，用户能够通过例如声音等进行电视装置10播送的广播台的选台的操作。
电视装置10、声音识别服务器50、以及替换读取服务器60例如经由互联网等网络40，通过无线或有线相互连接。
作为接收装置的电视装置10能够接收例如来自广播台的广播信号并接收各种节目。此外，电视装置10具有声音识别功能，若检测到用户发出的广播台名或广播台的称呼等，则进行基于声音识别服务的广播台的切换。
电视装置10的声音识别功能专门用于检测用户的发声。在声音识别服务开始后，电视装置10利用例如声音识别服务器50的声音识别功能以及替换读取服务器60的替换读取功能，将声音识别服务提供给用户。
这时，电视装置10将检测到的声音信号发送给声音识别服务器50，并且接收由声音识别服务器50进行的声音识别结果的、声音信号被转换为与其对应的字符串的字符串信息。
此外，电视装置10将从声音识别服务器50接收到的字符串信息发送给替换读取服务器60，并且接收由替换读取服务器60进行的替换读取结果的、字符串信息被替换读取为与其对应的广播台名的信息。
声音识别服务器50和替换读取服务器60构成为例如置于云端上的云服务器等。声音识别服务器50和替换读取服务器60中的至少一个还能够构成为具备CPU(Central Processing Unit，中央处理器)、ROM(Read Only Memory，只读存储器)、以及RAM(Random Access Memory，随机存取存储器)等物理结构的一个以上的计算机。
通过构成云服务器或计算机的CPU执行例如存储于ROM等中的程序，从而实现声音识别服务器50的声音识别功能和替换读取服务器60的替换读取功能。
作为用于实现声音识别功能的功能部，声音识别服务器50具备声音识别部51、通信部52、以及存储部53。
声音识别部51通过使用了例如自然语言处理等的解析，识别从电视装置10经由通信部52接收到的用户发声的声音信号。此时，声音识别部51参照存储部53的声音词典54。声音识别部51将识别出的声音信号转换为与其对应的字符串信息。
通信部52进行与电视装置10之间的通信。例如，通信部52从电视装置10接收用户的声音信号。此外，通信部52将字符串信息发送给电视装置10。
存储部53存储声音识别服务器50实现上述功能的过程中所需的各种参数及信息等。作为一例，存储部53具备声音词典54，该声音词典54存储有用于解析来自用户的声音信号的声音数据。
声音词典54具有的声音数据具有例如来自用户的声音信号中可包含的音素以及特征等关于各种要素的信息，声音识别部51比较该声音数据和来自用户的声音信号而作为用于识别声音的指标。
可包含在来自用户的声音信号中的音素以及特征等可依据已有的广播台的名称中所包含的字符串。由此，当用户的发声为例如“e nie ei ti kie”时，能够容易地转换成“NHK”的正确的字符串。此外，当用户的发声为“hu ji te re bi”时，不是转换为“富士te re bi”等，而是转换为“hu ji te re bi”的正确字符串。
保存在声音词典54中的声音数据可以存在多个。例如，多个声音数据中可以包含男性用、女性用、以及儿童用等基于性别和年龄的各种声音数据。
存储部53构成为例如大容量存储装置。由此，存储部53能够保存例如上述的具有庞大的声音数据的声音词典54，并且声音识别服务器50能够进行高精度的声音识别。
如此，通过使声音识别服务相关的功能的主要部分搭载于处理能力高的声音识别服务器50上，从而提高来自用户的声音信号的识别精度和识别速度，并且能够提供内容更完整的声音识别服务。
在电视装置10检测到的用户的发声内容为广播台的称呼的情况下，替换读取服务器60将其替换读取为正式的广播台名。作为用于实现这种替换读取功能的功能部，替换读取服务器60具备替换读取处理部61、通信部62、以及存储部63。
替换读取处理部61解析从电视装置10经由通信部62接收到的字符串信息并替换读取为正式的广播台名。此时，替换读取处理部61参照存储部63的替换读取词典64。
通信部62进行与电视装置10的通信。例如，通信部62从电视装置10接收用户的声音信号转换为字符串的字符串信息。此外，通信部62将与字符串信息对应的广播台名发送给电视装置10。
存储部63存储替换读取服务器60实现上述功能所需的各种参数以及信息等。作为一例，存储部63具备替换读取词典64，该替换读取词典64存储有用于解析字符串信息的数据。替换读取词典64中存储有例如与各个广播台的各种称呼相关的信息。
(电视装置的硬件结构)
图2是表示实施方式1的电视装置10的硬件结构的一例的图。
如图2所示，电视装置10具备天线101、输入端子102a～102c、调谐器103、解调器104、解复用器105、A/D(模拟/数字)转换器106、选择器107、信号处理部108、扬声器109、显示面板110、操作部111、受光部112、IP通信部113、CPU 114、内存(memory) 115、存储器(storage)116、麦克风117、以及音频(audio)I/F(接口)118。
天线101接收数字广播的广播信号，并将接收的广播信号经由输入端子102a提供给调谐器103。
调谐器103在由天线101提供的广播信号中对期望的频道的广播信号进行选台，并将选台的广播信号提供给解调器104。
解调器104解调由调谐器103提供的广播信号，并将解调的广播信号提供给解复用器105。
解复用器105分离由解调器104提供的广播信号并生成图像信号和声音信号，并将生成的图像信号和声音信号提供给选择器107。
选择器107从由解复用器105、A/D转换器106、以及输入端子102c提供的多个信号中选择一个，并将选择的一个信号提供给信号处理部108。
信号处理部108对由选择器107提供的图像信号实施规定的信号处理，并将处理后的图像信号提供给显示面板110。此外，信号处理部108对由选择器107提供的声音信号实施规定的信号处理，并将处理后的声音信号提供给扬声器109。
扬声器109基于由信号处理部108提供的声音信号而输出声音或各种语音。此外，扬声器109基于CPU 114的控制，变更输出的声音或各种语音的音量。
作为显示部的显示面板110，基于由信号处理部108提供的图像信号或CPU 114的控制，显示静态图像及动态图像等视像、其它图像、以及文字信息等。
输入端子102b接收从外部输入的图像信号及声音信号等模拟信号。此外，输入端子102c接收从外部输入的图像信号以及声音信号等数字信号。例如，输入端子102c能够从搭载了驱动装置的录像机(Recorder)等输入数字信号，该驱动装置驱动BD(Blu-ray Disc)(注册商标)等录像播放用的存储介质而进行录像及播放。
A/D转换器106将数字信号提供给选择器107，该数字信号是通过对由输入端子102b提供的模拟信号实施A/D转换而生成的信号。
操作部111接收用户的操作输入。
受光部112从遥控器119接收红外线。
IP通信部113是用于进行经由网络40的IP(互联网协议)通信的通信接口。
作为控制部的CPU 114控制电视装置10整体。
内存115是保存CPU 114执行的各种计算机程序的ROM、以及向CPU 114提供工作分区(area)的RAM等。例如，ROM中存储有用于电视装置10检测用户的声音的声音识别程序、以及用于提供声音识别服务的应用程序等。
存储器116是HDD(Hard Disk Drive，硬盘驱动器)或SSD(Solid State Drive，固态硬盘)等。存储器116例如将由选择器107选择出的信号作为录像数据进行存储。
作为声音输入部的麦克风117获取用户发声的声音，并发送给音频I/F 118。
音响I/F 118将麦克风117获取的声音转换为模拟/数字信号，作为声音信号发送给CPU 114。
(电视装置的功能结构)
接着，使用图3说明实施方式1的电视装置10的功能结构例。图3是表示实施方式1的电视装置10的功能结构的一例的图。
在电视装置10中，通过上述的CPU114执行存储于例如ROM等的程序，从而能够 实现电视装置10的声音识别功能等。在电视装置10中执行的程序成为包含以下叙述的各个功能部在内的模块儿结构。
如图3所示，作为实现电视装置10的功能的功能部，电视装置10具备接收部11、声音处理部12、显示控制部13、设备控制部14、通信部15、以及存储部16。
接收部11从用户接收各种输入。例如，接收部11将输入到麦克风117的用户的声音经由音响I/F118作为声音信号而接收。此外，例如，接收部11从操作部111或遥控器119接收通过操作输入进行的各种指示。
作为处理部的声音处理部12进行与接收部11接收到的用户的声音相关的处理。例如，声音处理部12将接收部11接收到的声音信号经由通信部15发送给声音识别服务器50。此外，声音处理部12基于经由通信部15从替换读取服务器60接收到的替换读取结果，从保存在存储部16中的广播台数据库17中，检索与声音信号对应的广播台名。此外，在广播台数据库17中存在与声音信号对应的广播台名的情况下，声音处理部12将该广播台作为切换目标的广播台进行选台。
显示控制部13控制显示在显示面板110上的各种显示。例如，当接收部11获取到使用了遥控器119的用户的操作时，显示控制部13将其操作对应的操作画面显示于显示面板110。此外，当通过检测用户发声的声音来开始声音识别服务时，显示控制部13将响应于声音的消息或图标等显示于显示面板110。这些消息或图标等是例如显示被选台的广播台的内容等。
设备控制部14控制电视装置10的各部。例如，设备控制部14在提供声音识别服务的过程中，基于用户的声音所包含的命令，控制电视装置10的各部，从而将电视装置10播送的广播台切换为被选台的广播台。
通信部15控制经由网络40与外部设备的通信。例如，通信部15在提供声音识别服务时，对声音识别服务器50以及替换读取服务器60与电视装置10的通信进行控制。此外，通信部15接收广播信号中包含的与广播台相关的信息，获取在电视装置10设置的地区内可接收的广播台的广播台名，随时保存于存储部16的广播台数据库17。
存储部16存储实现电视装置10的如上所述功能所需的各种参数及信息等。作为一例，存储部16具备广播台数据库17，所述广播台数据库17存储有正式的广播台名的信息，所述正式的广播台名的信息是用于基于来自用户的声音信号对广播台进行选台的信息。如上所述，广播台数据库17的广播台名的信息通过通信部15随时更新。
(电视装置的功能例)
接着，使用图4详细地说明实施方式1的电视装置10的功能。图4是说明实施方式1的电视装置10具有的功能的一例的模式图。
如图4所示，例如，设想用户为了选台朝日电视台而发声“te re a sa ni si te”。接收部11将用户发声的声音作为声音信号而接收(处理P11)，传递给声音处理部12(处理P12)。声音处理部12将其声音信号进一步传递给通信部15(处理P13)。
通信部15将被传递的声音信号发送给声音识别服务器50，接收声音信号转换为字符串的字符串信息(处理P14)。此时，在声音识别服务器50中，声音识别部51解析从电视装置10接收的声音信号并转换为字符串，作为声音识别结果而生成字符串信息。
在图4的例中，声音识别部51从电视装置10接收的“te re a sa ni si te”的声音信号中，作为相当于广播台名的部分而提取“te re a sa”，将其转换为“te re朝”的字符串。
通信部15将从声音识别服务器50接收的字符串信息发送给替换读取服务器60，接收字符串信息被替换读取的广播台名的信息(处理P15)。这时，在替换读取服务器60中，替换处理部61解析从电视装置10接收的字符串信息并替换读取为正式的广播台名，作为替换读取结果而生成广播台名的信息。
在解析字符串信息时，替换读取处理部61参照保存于存储部63的替换读取词典64。广播台的各种称呼即称呼信息与对应的广播台名相关联地保存在替换读取词典64中。在替换读取词典64中，对于一个广播台可以关联一个称呼信息，或者在一个广播台具有多个称呼的情况下，对于一个广播台可以关联多个称呼信息。
作为成为替换读取目标的广播台名，例如可以覆盖全国的广播台。由此，不管电视装置10设置于任何区域，也都能够对应来自电视装置10的替换读取请求。作为广播台的称呼，可以有广播台的俗称、略称、别名、旧称等。
例如，就NHK E te re而言，能够有如E te re等略称、教育te re bi等别名。因此，替换读取词典64中，作为成为替换读取对象的称呼的“E te re”、“教育te re bi”等字符串的信息与正式的广播台名即“NHK E te re”关联地保存。
在图4的例中，替换读取处理部61在替换读取词典64中检索与从电视装置10接收到的“te re朝”的字符串信息匹配的替换读取对象字符串。在替换读取词典64中，“te re朝”的字符串与例如“5频道”等字符串一起与“te re bi朝日”关联。替换读取处理部61生成将“te re朝”替换读取为“te re bi朝日”的广播台名的信息。
另外，当用户的声音信息为从一开始就包含广播台的正式名称的“te re bi a sa hi ni si te”的情况下，替换读取词典64的替换读取对象字符串中也可能不包含与从电视装置10接收到的字符串信息匹配的字符串。这时，替换读取服务器60将没有符合的广播台名这样的替换读取结果发送给电视装置10。
通信部15将从替换读取服务器60接收的替换读取结果传递给声音处理部12(处理P16)。当替换读取结果中包含有广播台的称呼被替换读取的广播台名的情况下，声音处理部12在存储部16的广播台数据库17中检索与替换读取结果匹配的广播台名(处理P17)。
广播台数据库中存储有“NHK综合电视”、“NHK E te re”、“日本te re bi”、“te re bi朝日”等各个广播台的正式名称的信息。
在图4的例中，声音处理部12从广播台数据库17中选择与替换读取结果中包含的“te re bi朝日”匹配的te re bi朝日。电视装置10的设备控制部14控制电视装置10的各部，将电视装置10播送的广播台切换为te re bi朝日。
另外，如替换读取服务器60的替换读取词典64中没有符合的广播台名，在替换读取结果中未包含广播台名时，声音处理部12在广播台数据库17中检索与从声音识别服务器50接收到的字符串信息匹配的广播台名。声音处理部12在存在匹配的广播台名时选择该广播台名，设备控制部14将电视装置10播送的广播台转换为选择的广播台。
用户发声了该区域内无法接收的广播台名的情况等，在广播台数据库17中没有与来自替换读取服务器60的广播台名的信息、或来自声音识别服务器50的字符串信息中的任一个匹配的广播台名的情况下，表示广播台选择失败，不进行广播台的切换。显示控制部13在显示面板110上显示选台失败。
(电视装置的选台处理)
接着，使用图5说明实施方式1的电视装置10的选台处理的例子。图5是表示实施 方式1的电视装置10的选台处理的顺序的一例的流程图。
如图5所示，接收部11将用户发声的声音作为声音信号接收(步骤S101)。通信部15将接收部11接收的声音信号发送给声音识别服务器50(步骤S102)。在声音识别服务器50中，声音识别部51解析声音信号，并生成被识别的声音信号转换为字符串的字符串信息。
电视装置10的通信部15从声音识别服务器50接收与声音信号对应的字符串信息作为声音识别结果(步骤S103)。通信部15将接收的字符串信息发送给替换读取服务器60(步骤S104)。
在替换读取服务器60中，替换读取处理部61参照替换读取词典64而检索与字符串信息对应的广播台名。当有对应的广播台名时，替换读取处理部61生成包含该广播台名在内的广播台名的信息作为替换读取结果。当没有对应的广播台名时，替换读取处理部61生成没有符合的广播台名的信息作为替换读取结果。
电视装置10的通信部15从替换读取服务器60接收替换读取结果(步骤S105)。声音处理部12根据替换读取结果而检索广播台数据库17(步骤S106)。
当替换读取结果中包含广播台名时，声音处理部12从广播台数据库17中检索与替换读取结果匹配的广播台名。当替换读取结果中未包含广播台名时，声音处理部12从广播台数据库17中检索与从声音识别服务器50接收的字符串信息匹配的广播台名。
声音处理部12根据广播台数据库17的检索结果而判定是否存在与替换读取结果或字符串信息匹配的广播台名(步骤S107)。若存在匹配的广播台名(步骤S107：是)，则设备控制部14进行向该广播台的切换(步骤S108)。若不存在匹配的广播台名(步骤S107：否)，则显示控制部13将无法进行广播台的切换的情况显示于显示面板110(步骤S109)。
由此，结束实施方式1的电视装置10的选台处理。
(比较例)
近年来，开发了能够通过声音识别服务来进行选台的电视装置等。在这种电视装置中，若用户发声包含广播台名的声音，则相应的广播台被选台。
然而，广播台除了正式的广播台名以外有时具有各种称呼，当用户发声广播台的称呼时，有时无法通过电视装置进行识别而选台失败。此外，通过声音识别服务器50，转换为与广播台的正式名称不同的表述的情况下，电视装置也不能进行识别。
例如，以前的“富士电视”改名为“hu ji电视”那样，在广播台的表述突然变更了的情况下等，通过声音识别服务器50，依据旧称而转换为字符串。由于电视装置的广播台数据库随时更新为最新的数据，因此在上述的情况下电视装置也无法识别依据旧称而转换的字符串，导致选台失败。
在比较例的电视装置中，为了提高选台的精度，例如预先在广播台数据库中还登记了广播台的各种称呼。然而，对于任一个广播台，为了应对产生了衍生别名的情况或改名的情况等，需要更新或重新安装电视装置的软件。
根据实施方式1的电视装置10，向存有包含广播台名的称呼信息在内的替换读取词典64的替换读取服务器60发送基于声音信号的字符串信息，从替换读取服务器60接收字符串信息的替换读取结果。
由此，能够提高电视装置10进行的广播台的选台精度。无需在电视装置10的广播台数据库17中保存称呼信息，或者为了追加称呼信息而重新安装电视装置10的软件。
[实施方式2]
下面，参照附图详细说明实施方式2。实施方式2的电视装置中，向替换读取服务器60发送字符串信息的时机(timing)与上述的实施方式1不同。
(电视装置的功能例)
图6是说明实施方式2的电视装置20具有的功能的一例的模式图。另外，以下说明中对与实施方式1相同的结构标记相同的符号并省略该说明。
如图6所示，在实施方式2的电视装置20中，若接收到用户的声音信号，则在通信部25与声音识别服务器50之间进行声音信号与其转换为字符串的字符串信息的交换(处理P11～P14)。
通信部25将从声音识别服务器50接收的字符串信息传递给声音处理部22(处理P21)。声音处理部22在存储部16的广播台数据库17中检索与字符串信息匹配的广播台名(处理P22)。
当有匹配的广播台名时，声音处理部22选择该广播台，电视装置20的设备控制部14(参照图3)控制电视装置20的各部，将电视装置20播送的广播台切换为选择的广播台。
在图6的例中，声音处理部22无法从广播台数据库17中找到与从声音识别服务器50接收的“te re朝”的字符串信息匹配的广播台名。
通信部25从声音处理部22接收广播台数据库17中没有与字符串信息匹配的广播台名的信息(处理P23)。之后的处理与上述的实施方式1的电视装置10的情况相同。
即，通信部25将从声音识别服务器50接收的字符串信息发送给替换读取服务器60，从替换读取服务器60接收替换读取结果(处理P25)。声音处理部22在替换读取结果中包含广播台名的情况下，从广播台数据库17中选择匹配的广播台名(处理P26、P27)，设备控制部14将电视装置20播送的广播台切换为选择的广播台。
当广播台数据库17中没有匹配的广播台名时，或者最初替换读取结果中未包含广播台名时，广播台的选择失败，显示控制部13(参照图3)将选台的失败显示于电视装置20的显示面板110。
(电视装置的选台处理)
接着，使用图7说明实施方式2的电视装置20的选台处理的例子。图7是表示实施方式2的电视装置20的选台处理的顺序的一例的流程图。
如图7所示，步骤S201～S203的处理与上述的实施方式1的图5表示的步骤S101～S103的处理相同。即，将用户的声音信号发送给声音识别服务器50并接收转换为字符串的字符串信息(步骤S201～S203)。
声音处理部22在广播台数据库17中检索与字符串信息匹配的广播台名(步骤S204)。此外，声音处理部22根据广播台数据库17的检索结果，判定是否存在与字符串信息匹配的广播台名(步骤S205)。若存在匹配的广播台名(步骤S205：是)，则设备控制部14进行向该广播台的切换(步骤S211)。
若不存在匹配的广播台名(步骤S205：否)，则通信部25将从声音识别服务器50接收的字符串信息发送给替换读取服务器60(步骤S206)，从替换读取服务器60接收替换读取结果(步骤S207)。
声音处理部22判定通信部25接收的替换读取结果中是否包含广播台名(步骤S208)。 当未包含广播台名时(步骤S208：否)，显示控制部13将无法进行广播台的切换的情况显示于显示面板110(步骤S212)。
替换读取结果中包含广播台名时(步骤S208：是)，声音处理部22在广播台数据库17中检索与替换读取结果中包含的广播台名匹配的广播台名(步骤S209)。
声音处理部22根据广播台数据库17的检索结果，判定是否存在匹配的广播台名(步骤S210)。当存在匹配的广播台名时(步骤S210：是)，设备控制部14进行向该广播台的切换(步骤S211)。
当不存在匹配的广播台名时(步骤S210：否)，显示控制部13将无法进行广播台的切换的情况显示于显示面板110(步骤S212)。
由此，实施方式2的电视装置20的选台处理结束。
(概括)
根据实施方式2的电视装置20，在广播台数据库17中没有与从声音识别服务器50接收的字符串信息匹配的广播台名的情况下，通信部25将字符串信息发送给替换读取服务器60。如此，通信部25等待基于字符串信息的声音处理部22的检索结果后，根据需要进行向替换读取服务器60请求的替换读取请求。
由此，能够减少向替换读取服务器60的访问次数，并且能够减少电视装置20以及替换读取服务器60的工作负荷。此外，通过减少对替换读取服务器60的访问次数，从而能够与替换读取服务器60中的检索时间对应地使选择广播台为止的处理时间加快。
(变形例)
接着，使用图8以及图9说明实施方式2的变形例的电视装置20a。变形例的电视装置20a向替换读取服务器60发送字符串信息的时机与上述实施方式2不同。
图8是说明实施方式2的变形例的电视装置20a具有的功能的一例的模式图。另外，在以下说明中，对与实施方式2相同的结构标记相同的符号并省略说明。
如图8所示，在变形例的电视装置20a中，当接收用户的声音信号时，在通信部25a与声音识别服务器50之间进行声音信号与其转换为字符串的字符串信息的交换(处理P11～P14)。
通信部25a将从声音识别服务器50接收的字符串信息传递给声音处理部22a(处理P21)。声音处理部22a在存储部16的广播台数据库17中检索与字符串信息匹配的广播台名(处理P22a)。
通信部25a无需等待声音处理部22a进行的广播台数据库17的检索结果，而是与声音处理部22a的检索处理并行地，将从声音识别服务器50接收的字符串信息发送给替换读取服务器60，开始与替换读取服务器60的交换(处理P25a)。
相比于基于字符串信息的声音处理部22a的广播台数据库17的检索，通过通信部25a向替换读取服务器60的访问、以及在替换读取服务器60中的读取处理过程更需要时间。因此，能够认为在通信部25a接收来自替换读取服务器60的替换读取结果之前得出声音处理部22a的检索结果。
通信部25正在进行与替换读取服务器60的交换过程中，得出广播台数据库17中存在与字符串信息匹配的广播台名的结果的情况下，通信部25取消替换读取服务器60中的字符串信息的替换读取。
通信部25正在进行与替换读取服务器60的交换过程中，得出广播台数据库17中没 有与字符串信息匹配的广播台名的结果的情况下，通信部25无需取消替换读取服务器60中的字符串信息的替换读取而等待接收替换读取结果。
之后的处理与上述实施方式2的电视装置20的情况相同。即，若通信部25a接收到替换读取结果，则声音处理部22a在替换读取结果中包含广播台名的情况下，从广播台数据库17中选择匹配的广播台名(处理P26、P27)，设备控制部14将电视装置20a播送的广播台切换为选择的广播台。
当广播台数据库17中没有匹配的广播台名的情况下，或者最初替换读取结果中没有包含广播台名的情况下，广播台的选择失败，显示控制部13将选台失败显示于电视装置20的显示面板110。
图9是表示实施方式2的变形例的电视装置20a的选台处理的顺序的一例的流程图。
如图9所示，步骤S201～S204的处理与上述实施方式2的图7表示的步骤S201～S204的处理相同。即，将用户的声音信号发送给声音识别服务器50并接收转换为字符串的字符串信息，开始基于字符串信息的广播台数据库17的检索(步骤S201～S204)。
与声音处理部22a进行的广播台数据库17的检索并行地，通信部25a将从声音识别服务器50接收的字符串信息发送给替换读取服务器60(步骤S204a)。
声音处理部22a根据基于字符串信息的广播台数据库17的检索结果，判定是否存在与字符串信息匹配的广播台名(步骤S205)。当存在匹配的广播台名时(步骤S205：是)，通信部25a取消访问替换读取服务器60(步骤S207a)，设备控制部14进行向该广播台的切换(步骤S211)。
当不存在与字符串信息匹配的广播台名的情况下(步骤S205：否)，之后的处理与上述的实施方式2的图7的步骤S207开始的处理相同。
即，通信部25a等待替换读取服务器60的替换读取处理结束后接收替换读取结果，若替换读取结果包含广播台名，则声音处理部22a执行基于替换读取结果的广播台数据库17的检索，若存在匹配的广播台名，则设备控制部14进行向该广播台的切换(步骤S207～S211)。
若不存在匹配的广播台名，则显示控制部13将无法进行广播台的切换显示于显示面板110(步骤S208、S212)。
由此，变形例的电视装置20a的选台处理结束。
根据变形例的电视装置20a，与从声音识别服务器50接收的字符串信息匹配的广播台名的检索并行地，通信部25a将字符串信息发送给替换读取服务器60。由此，能够同时进行声音处理部22a的检索处理、和替换读取服务器60的检索处理，能够进一步加快选择广播台为止的处理时间。
根据变形例的电视装置20a，当广播台数据库17中存在与字符串信息匹配的广播台名的情况下，通信部25a取消替换读取服务器60中的字符串信息的替换读取。由此，能够进一步减轻替换读取服务器60的工作负荷，或者更进一步加快直到选择广播台为止的处理时间。
[实施方式3]
下面，参照附图详细说明实施方式3。实施方式3的电视装置在进行广播台数据库的更新方面与上述的实施方式2不同。
(电视装置的功能例)
图10是说明实施方式3的电视装置30具有的功能的一例的模式图。另外，在以下说明中，对与实施方式1、2相同的结构标记相同的符号并省略说明。
如图10所示，实施方式3的电视装置30除了具有例如实施方式2的电视装置20的功能，还具有更新保存在存储部36中的广播台数据库37的功能。
存储部36的广播台数据库37构成为，除了保存广播台的正式名称的信息，还可以保存与每个广播台名相关联的广播台的一个或多个称呼信息。在图10的例子中，例如广播台数据库37的“NHK综合电视”的项目中已经存储有“1频道”的称呼信息，“te re bi朝日”的项目中已经存储有“5频道”的称呼信息。
电视装置30的声音处理部32在广播台数据库37中检索与从声音识别服务器50接收的字符串信息匹配的广播台名时，还参照保存在广播台数据库37中的称呼信息。除此以外，电视装置30的处理P11～P27的动作与上述的实施方式2的图6表示的动作相同。
声音处理部32在广播台数据库37中找到与包含在替换读取服务器60的替换读取结果中的广播台名匹配的广播台名，并将该广播台作为选台对象的广播台的情况下，基于来自用户的声音信号，将由声音识别服务器50转换为字符串的字符串信息与成为选台对象的广播台的广播台名关联地追加到广播台数据库37中。
在图10的例子中，基于用户的发声的“te re a sa ni si te”的声音信号的广播台名相关的部分转换为“te re朝”的字符串，该字符串由电视装置30的通信部25接收。
该时刻，“te re朝”的称呼信息未登记在广播台数据库37中。声音处理部32从广播台数据库37找到与“te re朝”的字符串被替换读取过的“te re bi朝日”匹配的广播台名，将te re bi朝日作为选台对象进行选择。
这时，声音处理部32追加包含“te re朝”的字符串在内的字符串信息作为广播台数据库37的“te re bi朝日”的称呼(处理P28)。由此，此后，当用户发声“te re a sa ni si te”等时，“te re bi朝日”的项目中找到与由声音识别服务器50转换的包含“te re朝”在内的字符串信息匹配的称呼，无需进行向替换读取服务器60的替换读取请求，te re bi朝日被选择为选台对象。
(电视装置的选台处理)
接着，使用图11说明实施方式3的电视装置30的选台处理的例。图11是表示实施方式3的电视装置30的包含广播台数据库37的更新处理在内的选台处理的顺序的一例的流程图。
如图11所示，步骤S301～S310的处理与上述的实施方式2的图7表示的步骤S201～S210的处理相同。
电视装置30的声音处理部32在从广播台数据库37找到与包含在从替换读取服务器60接收的替换读取结果中的广播台名匹配的广播台名的情况下(步骤S301～S310)，将从声音识别服务器50接收的字符串信息(步骤S303)、和与替换读取结果匹配的广播台名关联并追加到广播台数据库37中(步骤S311)。
之后的、字符串信息或与替换读取结果中包含的广播台名匹配的广播台名在广播台数据库37中被发现的情况下的处理(步骤S312)、以及未被发现的情况下的处理(步骤S313)，分别与上述的实施方式2的图7表示的步骤S211、S212的处理相同。
由此，实施方式3的电视装置30的选台处理结束。
(概括)
根据实施方式3的电视装置30，声音处理部32在广播台数据库37中存在与基于用户的发声的字符串信息被替换读取过的广播台名的信息匹配的广播台名的情况下，将字符串信息、和与基于该字符串信息的广播台名的信息匹配的广播台名关联地追加到广播台数据库37中。
由此，能够适当扩充广播台数据库37，提高声音处理部32的检索精度。此外，能够进一步减少对替换读取服务器60的访问次数，能够减少电视装置30和替换读取服务器60的工作负荷，并且能够缩短直到广播台被选台为止的时间。
(变形例)
接着，使用图12和图13说明实施方式3的变形例的电视装置30a。除了选台处理的时机以外，变形例的电视装置30a与上述的实施方式3的不同点在于，进行广播台数据库的更新。
图12是说明实施方式3的变形例的电视装置30a具有的功能的一例的模式图。另外，在以下说明中，对与实施方式3相同的结构标记相同的符号并省略其说明。
如图12所示，变形例的电视装置30a例如除了实施方式3的电视装置30的功能之外，还具有基于从替换读取服务器60获取的称呼信息来更新保存在存储部36a中的广播台数据库37a的功能。即，电视装置30a除了上述的实施方式3的图10所示的处理P11～P28的动作，还进行广播台数据库37a的更新处理。
电视装置30a的声音处理部32a在未进行选台处理的规定的时机，向通信部35a通知当前未接收到来自用户的声音信号(处理P31)。作为这种规定的时机，例如有电视装置30a被启动的时机。
通信部35a从保存在替换读取服务器60的存储部63的替换读取词典64获取与广播台名相关联的替换读取对象字符串的信息、即对应的广播台的称呼信息(处理P32)。通信部35a将从替换读取服务器60获取的称呼信息传递给声音处理部32a(处理P33)。
当传递的称呼信息中存在未登记到广播台数据库37a的称呼信息时，声音处理部32a将它们与对应的广播台名相关联地一起登记到广播台数据库37a中(处理P34)。
在图12的例子中，从替换读取服务器60获取的多个称呼信息中，日本te re bi的称呼即“4频道”、以及te re bi朝日的称呼即“te re朝”未登记。声音处理部32a分别将“4频道”保存到“日本te re bi”的项目中，将“te re朝”保存到“te re bi朝日”的项目。
另外，从替换读取服务器60获取的称呼信息被追加到广播台数据库37a后，电视装置30a自主地进行选台处理而无需在规定期间访问替换读取服务器60。
即，由于存储部36a的广播台数据库37a在规定的时机适当地更新为最新状态，因此即使在用户发声了规定的广播台的称呼的情况下，也能够从广播台数据库37a中找到发声的称呼而无需访问替换读取服务器60。
另一方面，当广播台数据库37a中未找到由用户发声的称呼等时，都不需要访问替换读取服务器60，就能够得出没有符合的广播台这样的不能选台的判定。
关于电视装置30a在更新一次广播台数据库37a后无需访问替换读取服务器而自主地进行选台处理的期间，能够基于进行替换读取服务器60的扩充的频率而适当设定。还能够将更新广播台数据库37a的时机本身与替换读取服务器60的扩充频率相应地设定。
图13是表示实施方式3的变形例的电视装置30a的广播台数据库37a的更新处理的顺序的一例的流程图。
如图13所示，电视装置30a的声音处理部32a判定是否为电视装置30a启动的时机等规定的时机(步骤S321)。声音处理部32a等待直至成为规定的时机(步骤S321：否)。
当成为规定时机时(步骤S321：是)，通信部35a从替换读取服务器60的替换读取词典64获取称呼信息(步骤S322)。
对于从替换读取服务器60获取的多个称呼信息中的一个，声音处理部32a从广播台数据库37a中检索与此匹配的称呼信息(步骤S323)。声音处理部32a基于广播台数据库37a的检索结果判定广播台数据库37a中是否存在匹配的称呼信息(步骤S324)。
当不存在匹配的称呼信息时(步骤S324：否)，声音处理部32a将其呼称信息与对应的广播台名相关联地追加到广播台数据库37a(步骤S325)，当存在匹配的称呼信息时(步骤S324：是)，无需追加该称呼信息，判定该称呼信息是否为从替换读取服务器60获取的最后的称呼信息(步骤S326)。
当不是最后的称呼信息时(步骤S326：否)，声音处理部32a重复步骤S323开始的处理，依次将未登记的称呼信息追加到广播台数据库37a。当是最后的称呼信息时(步骤S326：是)，声音处理部32a结束处理。
以上，变形例的电视装置30a的更新处理结束。
根据变形例的电视装置30a，通信部35a在未接收到声音信号的规定的时机，从替换读取服务器60获取称呼信息，声音处理部32a将通信部35a获取的称呼信息与对应的广播台名相关联地追加到广播台数据库37a。
由此，能够在下一次选台处理前预先扩充广播台数据库37。因此，在以后的选台处理中，能够进一步提高声音处理部32a的检索精度。此外，在以后的选台处理中，能够进一步减少对替换读取服务器60的访问次数，进一步减轻电视装置30a和替换读取服务器60的工作负荷，并且能够进一步缩短直至广播台被选台的时间。
另外，上述的实施方式3以及变形例的电视装置30、30a除了具有广播台数据库37、37a的更新功能以外，进行与实施方式2的电视装置20相同的选台处理。但也可以是，进行实施方式1的选台处理或者实施方式2的变形例的选台处理的电视装置具有实施方式3或其变形例的电视装置30、30a的广播台数据库的更新功能。
此外，在上述的实施方式1～3以及变形例中，选台***1等具备声音识别服务器50和替换读取服务器60。但是，声音识别服务器和替换读取服务器也可以一体构成。即，选台***还可以具备服务器，该服务器具有声音识别功能和替换读取功能。
此外，电视装置10等中实现上述各种功能的程序作为可安装形式或可执行形式的计算机程序产品而提供。即，上述程序以包含在具有CD-ROM、柔性磁盘(FD)、CD-R、DVD等非易失性的计算机可读存储介质的计算机程序产品中的状态来提供。
此外，上述程序也可以存储于连接到互联网等网络上的计算机中，并通过网络提供或发布。上述程序还可以以预先安装在ROM等中的状态下提供。
通过将这种程序安装在电视装置10等，从而电视装置10等的CPU从ROM读取程序，并且在RAM上展开上述的各个功能结构。
然而，上述程序可以作为存储在云服务器等中的网络应用被提供，在该情况下，程序无需安装在电视装置10等中就可以被执行。
此外，虽然在上述的实施方式1～3以及变形例中，接收装置为电视装置10、20、20a、30、30a，但实施方式的结构并不限定于此。例如，接收装置还可以为具备了广播信号的接 收功能及播送功能、以及声音识别服务功能的个人电脑、智能手机、平板电脑、移动电话等其它设备。
虽然对本发明的实施方式进行了说明，但该实施方式是作为例子提出的方式，并不限定发明的范围。该新的实施方式可以以其它各种形态实施，在不脱离发明的主旨的范围内可以进行各种省略、替换、变更。这些实施方式、其变形包含在发明的范围、主旨中，并且包含在与权利要求书记载的发明等同的范围内。

Claims (10)

  1. 一种用于基于语音切换广播台的接收装置，其中，
    所述接收装置具备：
    接收部，其接收所述用户发声的声音作为声音信号；
    存储部，其存储有包含广播台名的信息在内的数据库；
    处理部，其从所述数据库中检索与所述声音信号对应的广播台名；以及
    通信部，其向替换读取服务器发送基于所述声音信号的字符串信息，并且从所述替换读取服务器接收所述字符串信息的替换读取结果，其中，所述替换读取服务器存有替换读取词典，所述广播台名的称呼即称呼信息、和与所述称呼对应的广播台名相关联地被保存于所述替换读取词典。
  2. 根据权利要求1所述的接收装置，其中，
    所述处理部在所述替换读取结果中包含有所述字符串信息被替换读取的广播台名的信息的情况下，从所述数据库中检索与基于所述字符串信息的所述广播台名的信息匹配的广播台名。
  3. 根据权利要求2所述的接收装置，其中，
    所述处理部在所述替换读取结果中未包含所述字符串信息被替换读取的广播台名的信息的情况下，检索与所述字符串信息匹配的广播台名。
  4. 根据权利要求1所述的接收装置，其中，
    所述处理部在所述数据库中检索与所述字符串信息匹配的广播台名，
    在所述数据库中不存在与所述字符串信息匹配的广播台名的情况下，且在所述替换读取结果中包含有所述字符串信息被替换读取的广播台名的信息的情况下，在所述数据库中检索与基于所述字符串信息的所述广播台名的信息匹配的广播台名。
  5. 根据权利要求4所述的接收装置，其中，
    所述通信部在所述数据库中不存在与所述字符串信息匹配的广播台名的情况下，将所述字符串信息发送给所述替换读取服务器。
  6. 根据权利要求4或5所述的接收装置，其中，
    所述数据库构成为，能够将所述广播台名的称呼即称呼信息、和与所述称呼对应的广播台名相关联地保存，
    所述处理部在所述数据库中存在与基于所述字符串信息的所述广播台名的信息匹配的广播台名的情况下，将所述字符串信息、和与所述广播台名的信息匹配的所述广播台名相关联地追加到所述数据库。
  7. 根据权利要求4或6所述的接收装置，其中，
    与所述字符串信息匹配的广播台名的检索并行地，所述通信部将所述字符串信息发送给所述替换读取服务器，
    在所述数据库中存在与所述字符串信息匹配的广播台名的情况下，所述通信部取消所述替换读取服务器中的所述字符串信息的替换读取。
  8. 根据权利要求1至7中任一项所述的接收装置，其中，
    所述数据库构成为，能够将所述广播台名的称呼即称呼信息、和与所述称呼对应的广播台名相关联地保存，
    所述通信部在未接收到所述声音信号的规定的时机，从所述替换读取服务器获取所述称呼信息，
    所述处理部将所述通信部获取到的所述称呼信息与对应的广播台名相关联地追加到所述数据库。
  9. 根据权利要求1至8中任一项所述的接收装置，其中，
    所述接收装置还具备设备控制部，该设备控制部切换所述接收装置播送的广播台，
    所述设备控制部在所述数据库中存在与所述声音信号对应的广播台名的情况下，将所述接收装置播送的广播台切换为具有与所述声音信号对应的所述广播台名的广播台。
  10. 一种选台***，其中，
    所述选台***具备：
    接收装置，其基于用户的发声而切换播送的广播台；以及
    替换读取服务器，其存有替换读取词典，所述替换读取词典将广播台名的称呼即称呼信息和与所述称呼对应的广播台名相关联地保存，
    所述接收装置具备：
    接收部，其接收所述用户发声的声音作为声音信号，
    存储部，其存储有数据库，该数据库包含设置有所述接收装置的地区内可接收的广播台的广播台名的信息，
    处理部，其从所述数据库中检索与所述声音信号对应的广播台名，
    通信部，其向所述替换读取服务器发送基于所述声音信号的字符串信息，并从所述替换读取服务器接收所述字符串信息的替换读取结果。
PCT/CN2022/101496 2021-09-27 2022-06-27 接收装置及选台*** WO2023045459A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202280007590.3A CN116547975A (zh) 2021-09-27 2022-06-27 接收装置及选台***

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-156859 2021-09-27
JP2021156859A JP7241142B1 (ja) 2021-09-27 2021-09-27 受信装置および選局システム

Publications (1)

Publication Number Publication Date
WO2023045459A1 true WO2023045459A1 (zh) 2023-03-30

Family

ID=85570556

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/101496 WO2023045459A1 (zh) 2021-09-27 2022-06-27 接收装置及选台***

Country Status (3)

Country Link
JP (1) JP7241142B1 (zh)
CN (1) CN116547975A (zh)
WO (1) WO2023045459A1 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1416112A (zh) * 2001-11-02 2003-05-07 松下电器产业株式会社 利用语音识别的选台装置及其控制方法
JP2003223183A (ja) * 2001-11-02 2003-08-08 Matsushita Electric Ind Co Ltd 音声認識による選局装置及びその制御方法
JP2004260544A (ja) * 2003-02-26 2004-09-16 Matsushita Electric Ind Co Ltd 音声認識機能を有する番組情報表示装置
CN101516005A (zh) * 2008-02-23 2009-08-26 华为技术有限公司 一种语音识别频道选择***、方法及频道转换装置
JP2009301498A (ja) * 2008-06-17 2009-12-24 Yahoo Japan Corp クエリ置換検索サーバ、検索方法及びプログラム
CN101902587A (zh) * 2009-06-01 2010-12-01 沈阳同方多媒体科技有限公司 一种通过语音对电视机进行控制的***
CN102075797A (zh) * 2010-12-29 2011-05-25 深圳市同洲电子股份有限公司 一种语音浏览频道或节目的方法及数字电视接收终端
CN103607609A (zh) * 2013-11-27 2014-02-26 Tcl集团股份有限公司 一种电视机频道的语音切换方法和装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007178927A (ja) 2005-12-28 2007-07-12 Canon Inc 情報検索装置および方法
JP4816409B2 (ja) 2006-01-10 2011-11-16 日産自動車株式会社 認識辞書システムおよびその更新方法
JP6908461B2 (ja) 2016-11-02 2021-07-28 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ 情報処理方法及びプログラム
JP7091234B2 (ja) 2018-12-17 2022-06-27 アルパイン株式会社 放送受信器の音声入力システム
JP7202938B2 (ja) 2019-03-20 2023-01-12 Ｔｖｓ Ｒｅｇｚａ株式会社 番組名検索支援装置、及び、番組名検索支援方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1416112A (zh) * 2001-11-02 2003-05-07 松下电器产业株式会社 利用语音识别的选台装置及其控制方法
JP2003223183A (ja) * 2001-11-02 2003-08-08 Matsushita Electric Ind Co Ltd 音声認識による選局装置及びその制御方法
JP2004260544A (ja) * 2003-02-26 2004-09-16 Matsushita Electric Ind Co Ltd 音声認識機能を有する番組情報表示装置
CN101516005A (zh) * 2008-02-23 2009-08-26 华为技术有限公司 一种语音识别频道选择***、方法及频道转换装置
JP2009301498A (ja) * 2008-06-17 2009-12-24 Yahoo Japan Corp クエリ置換検索サーバ、検索方法及びプログラム
CN101902587A (zh) * 2009-06-01 2010-12-01 沈阳同方多媒体科技有限公司 一种通过语音对电视机进行控制的***
CN102075797A (zh) * 2010-12-29 2011-05-25 深圳市同洲电子股份有限公司 一种语音浏览频道或节目的方法及数字电视接收终端
CN103607609A (zh) * 2013-11-27 2014-02-26 Tcl集团股份有限公司 一种电视机频道的语音切换方法和装置

Also Published As

Publication number Publication date
CN116547975A (zh) 2023-08-04
JP7241142B1 (ja) 2023-03-16
JP2023047760A (ja) 2023-04-06

Similar Documents

Publication Publication Date Title
JP6603754B2 (ja) 情報処理装置
JP6375521B2 (ja) 音声検索装置、音声検索方法、および表示装置
JP6244560B2 (ja) 音声認識処理装置、音声認識処理方法、および表示装置
EP3023982B1 (en) Image display apparatus, method for driving the same, and computer readable recording medium
CN103517094B (zh) 服务器和控制该服务器的方法
US20140123185A1 (en) Broadcast receiving apparatus, server and control methods thereof
CN103546787A (zh) 校正语音识别错误的方法和应用该方法的广播接收设备
CN103916687A (zh) 显示装置和控制显示装置的方法
CN103916704A (zh) 对话型接口设备及其控制方法
JP5296598B2 (ja) 音声情報抽出装置
EP2846554A1 (en) A method, an electronic device, and a computer program
KR20160057085A (ko) 디스플레이 장치 및 그 제어 방법
KR20150080684A (ko) 음성 신호에 따라 컨텐츠 정보를 검색하여 제공하는 디스플레이 장치, 서버 장치 및 이들을 포함하는 음성 입력 시스템과, 그 방법들
CN109792502B (zh) 信息处理设备、信息处理方法、存储介质和信息处理***
JP4601306B2 (ja) 情報検索装置、情報検索方法、およびプログラム
JP2004295102A5 (zh)
US10832669B2 (en) Electronic device and method for updating channel map thereof
US11538458B2 (en) Electronic apparatus and method for controlling voice recognition thereof
WO2023045459A1 (zh) 接收装置及选台***
JP4654438B2 (ja) 教育用コンテンツ生成装置
KR20190117913A (ko) 디스플레이 장치
JP7202938B2 (ja) 番組名検索支援装置、及び、番組名検索支援方法
JP7058052B2 (ja) コンピュータシステム、画面共有方法及びプログラム
JP7009338B2 (ja) 情報処理装置、情報処理システム、および映像装置
JP7229906B2 (ja) コマンド制御装置、制御方法および制御プログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22871520

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202280007590.3

Country of ref document: CN

NENP Non-entry into the national phase

Ref country code: DE