CN101739437A - Implementation method for network sound-searching unit and specific device thereof - Google Patents
Implementation method for network sound-searching unit and specific device thereof Download PDFInfo
- Publication number
- CN101739437A CN101739437A CN200910154892A CN200910154892A CN101739437A CN 101739437 A CN101739437 A CN 101739437A CN 200910154892 A CN200910154892 A CN 200910154892A CN 200910154892 A CN200910154892 A CN 200910154892A CN 101739437 A CN101739437 A CN 101739437A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- server
- audio
- text
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an implementation method for a network sound-searching unit, which comprises the steps: acquiring information from outside by a server, acquiring the information from the server, judging whether the currently acquired information is text information, converting the text information to audio information, directly playing the audio information to a user; judging whether the user needs to search for new information, acquiring a keyword input by the user, sending the keyword to the server and searching by the server according to the keyword. The network sound-searching unit comprises a network communication module for data exchange with the server, the network communication module is connected with a storage module which is connected with a speech synthesis module, and the speech synthesis module is connected with a playing module; and the network sound-searching unit further comprises an interaction module which transmits the keyword to the server via the network communication module. The implementation method has the advantages of wide information scope involved, fast information exchange speed with the server and great freeness for user to select intrigued information.
Description
Technical field
The present invention relates to a kind of implementation method and specialized equipment thereof of method for pushing and specialized equipment, particularly a kind of network sound-searching unit of the network information
Technical background
Along with the continuous development of Internet and universal day by day, the quantity of information on the internet increases with surprising rapidity.People always can feel dazzled in the face of the information of magnanimity.Though it is varied that people obtain the means of information,, still there are many colonies can not enjoy the facility that informationization brings such as internet, newspapers and periodicals, TV programme or the like.Especially some the socially disadvantageds, such as: blind person or look weak person and can't obtain information by visual pathway, need be by reading to shield software; The elderly can operating computer etc. novel information terminal device; Also has other various low-income groups expensive terminal device of cannot afford.
Chinese patent has been announced a kind of internet radio No. 02260990.3, comprise a housing, be provided with a circuit board in this housing, the circuit that is distributed on this circuit board is connected with a microprocessor, microprocessor is connected with following each element: this internet radio is connected on the network, and can download the data module of the station website of each network radio station, in order to store the network address of each network radio station, and the digital audio of downloading from each network radio station, the digital audio conversion that internet radio automatic network radio station can be accepted is the message of simulating audio and handles module, the power supply unit of required electric power when the running of this internet radio to be provided shows the display interface of network address of the website that is connected and the function key of input network address.During work, download the station website of each network radio station by data module automatic network, and each station website is stored in the data storage medium, when using internet radio next time, as long as access the station website that is stored in data storage medium in advance, can be connected to this network radio station, listen to the broadcast program that play in this radio station.
There is following shortcoming in this internet radio: 1, can only listen to the program that network radio station is play, the information faces of dabbling is narrow and small.What 2, transmit between the webserver and the internet radio is audio-frequency information, and occupation space is big, and transmission speed is slow.3, the user can only listen to the program that play in the radio station passively, can't oneself select information of interest, and interactivity is poor.
Summary of the invention
For the information faces of dabbling that overcomes prior art narrow and small, information takes up room greatly, transmission speed is slow, shortcoming with user's interactivity difference, it is big to the invention provides a kind of information faces of dabbling, and information transmission speed is fast between server, and the user can oneself select the implementation method and the specialized equipment thereof of the network sound-searching unit that information of interest listens to.
A kind of implementation method of network sound-searching unit may further comprise the steps:
1, from network, obtains information resources by server, or text or audio-frequency information are input to server by administrator hand, server is pressed its described classification (as news category, blog class, e-book class, music class, storytelling class with all information ...), described theme is (as physical culture, military affairs, amusement ...) identify respectively;
2, server is listened to interest according to the user and is initiatively given network sound-searching unit with information push, and network sound-searching unit receives and identifies described classification of current information and theme;
3, judge that the current information of obtaining is text message or audio frequency,, again this audio-frequency information is played to the user if text message then earlier is converted to audio-frequency information with text message; If audio-frequency information is then play-overed to the user;
4, judge whether the user needs to search for not the fresh information that pushes, if, then obtain the keyword of its information of interest of representative of user's input, this keyword is sent to server, is retrieved according to keyword by server, execution in step 2 again.
Further, in the step 4, the mode that the user imports keyword is text input and phonetic entry, if the keyword of user's input is a text message, then directly this text is sent to server; If the keyword of user's input is an audio-frequency information, then earlier this audio-frequency information is converted to text message, text message is sent to server.
Further, in the step 4, the step that audio-frequency information is converted to text message comprises:
1) sets up the text speech model corresponding with audio frequency;
(1.1) newsletter archive on the periodic analysis network extracts the hot news speech of current point in time and forms the focus dictionary;
(1.2) the lowest weightings threshold value of focus speech is set, As time goes on adjusts the weight of all focus speech in the focus dictionary, the deletion weight is lower than the focus speech of described lowest weightings threshold value;
(1.3) use the voice corpus that each focus speech is carried out voice training, obtain each focus speech characteristic of correspondence vector model, preserve focus speech and characteristic of correspondence vector model thereof as speech model.
2) obtain the eigenvector model of the audio frequency of user input, the audio frequency and the speech model of user's input are compared, identify the text corresponding with audio user.
Further, judge whether the user will switch the current information of listening to, if, then obtain the information that user's selection is listened to, judge that this selecteed information is audio-frequency information or text message, if audio-frequency information is then play-overed to the user; If text message is an audio-frequency information with text information translation earlier then, play to the user again;
Further, text marking, this message length of classification under the information of listening to the user and theme, this information and the time span of listening to this information are listened to interest as the user, and recording user is listened to interest and sent it to server.
A kind of network sound-searching unit, comprise with can from network, obtain information resources or by administrator hand input and with all information classifications not, the server of subject identification carries out exchanges data, identification from the affiliated classification of the text message of server, the network communication module of theme, described network communication module is connected with the memory module of can be sub-category, dividing theme to store from the text message of server; Described memory module is connected with a phonetic synthesis module that text message can be converted to audio-frequency information, and described phonetic synthesis module is connected with the playing module that the audio frequency that it can be changed is broadcast to the user;
Described network sound-searching unit also comprises the keyword that allows the user to import to represent its interest so that the interactive module of the interested fresh information of search subscriber, and described interactive module transfers to keyword server, retrieved according to keyword by server by described network communication module.
Further, described interactive module comprises the text that can obtain user input or the input block of audio frequency keyword, the audio frequency keyword is converted to the voice recognition unit of text, and described interactive module transfers to server by described network communication module with text key word.
Further, the resolution unit that comprises the pairing target signature vector model of audio frequency of resolving user's input in the described voice recognition unit, make up the voice unit of the text speech model corresponding with audio frequency, with with the comparison of target signature vector model and speech model, to identify the recognition unit with the pairing text of audio user, described recognition unit is connected with server by described network communication module.
Further, described voice unit comprises the hot news speech that extracts in the network, the dictionary unit that makes up the focus dictionary, adjust the weight information of the focus speech in the dictionary and delete the administrative unit that weight is lower than the focus speech of setting threshold according to passage of time, use the voice corpus that each focus speech is carried out voice training to obtain each focus speech characteristic of correspondence vector model, to emerge the training unit of speech model.
Further, described input block comprises handwriting screen input, keyboard input and audio frequency input.
Further, described network sound-searching unit comprises also and the current information of listening to can be switched to the navigation module that the user wants the information listened to that described navigation module is connected with described memory module.
Further, described network sound-searching unit also comprises text marking, this message length of classification under the information of can recording user listening to and theme, this information and listens to the feedback module of the time span of this information that described feedback module is sent to server by described network communication module with temporal summation.
Technical conceive of the present invention is: the information resources that will obtain from the internet or the information resources theme storage of being imported by administrator hand in sub-category minute, and the speech synthesis technique of inciting somebody to action text message utilization maturation wherein plays to the user with voice mode, the information that the user listens to is not limited to site radio, can expand to all resource types on the internet, the information of dabbling is wide, and network sound-searching unit and server not only can carry out exchanges data by audio form, can also textual form carry out exchanges data (except that audio resource), with can only carry out comparing of exchanges data by audio form, transmission speed of the present invention is faster, the storage space that takies is little, is convenient to management.
Server obtains, analysis user is listened to interest, and is open by No. the 200810121950.4th, Chinese patent to the method for network sound-searching unit pushed information.
Simultaneously,, the user is submerged in the magnanimity information of internet for being unlikely to, can be as searching for relevant information on computers, and network sound-searching unit also provides good interactive interface for the user.The user not only can select the content that will listen to, can also pass through literal or phonetic entry keyword, obtains relevant information from server.Network sound-searching unit integrating speech sound recognition technology is converted into keyword with the speech data of input.Afterwards, network sound-searching unit sends to server with keyword by network, and server is recommended relevant information resources according to user interest model, and it is sent it back network sound-searching unit.
Network sound-searching unit combines media platforms such as internet and newpapers and periodicals with traditional radio, can active give him with the information push that voice mode will meet user's request, and ordinary populace is benefited, and also can make all kinds of disadvantaged group obtain the welfare of imformation age.
Network sound-searching unit can be based on this method developing operation at all kinds of intelligent terminals software of (as supporting mobile phone, PDA, the IPTV etc. of networking); Also can be separately occur with the form of intelligent terminal; Can also be integrated with traditional radio, replace traditional radio, search the sound machine as on automobile, using new-type network.
It is wide that the present invention has the information of dabbling, and speed of information exchange is fast between server, and the user can freely select the advantage of information of interest.
Description of drawings
Fig. 1 is a main flow chart of the present invention
Fig. 2 is the process flow diagram of text for audio conversion
Fig. 3 is user's operation chart
Fig. 4 is a structural drawing of the present invention
Embodiment
Embodiment one
With reference to Fig. 1,2,3
A kind of implementation method of network sound-searching unit may further comprise the steps:
1, from network, obtains information resources by server, or text or audio-frequency information are input to server by administrator hand, server is pressed its described classification (as news category, blog class, e-book class, music class, storytelling class with all information ...), described theme is (as physical culture, military affairs, amusement ...) identify respectively;
2, specifying information clauses and subclauses under each theme of listening to the user and the time of listening to are listened to interest as the user, server is listened to interest according to the user and is initiatively given network sound-searching unit with information push, and network sound-searching unit receives and identifies described classification of current information and theme;
3, judge that the current information of obtaining is text message or audio frequency,, again this audio-frequency information is played to the user if text message then earlier is converted to audio-frequency information with text message; If audio-frequency information is then play-overed to the user;
4, judge whether the user needs to search for not the fresh information that pushes, if, then obtain the keyword of its information of interest of representative of user's input, this keyword is sent to server, is retrieved according to keyword by server, execution in step 2 again.
In the step 4, the mode that the user imports keyword is text input and phonetic entry, if the keyword of user's input is a text message, then directly this text is sent to server; If the keyword of user's input is an audio-frequency information, then earlier this audio-frequency information is converted to text message, text message is sent to server.
In the step 4, the step that audio-frequency information is converted to text message comprises:
1) sets up the text speech model corresponding with audio frequency;
(1.1) newsletter archive on the periodic analysis network extracts the hot news speech of current point in time and forms the focus dictionary;
(1.2) the lowest weightings threshold value of focus speech is set, As time goes on adjusts the weight of all focus speech in the focus dictionary, the deletion weight is lower than the focus speech of described lowest weightings threshold value;
(1.3) use the voice corpus that each focus speech is carried out voice training, obtain each focus speech characteristic of correspondence vector model, preserve focus speech and characteristic of correspondence vector model thereof as speech model.
2) obtain the eigenvector model of the audio frequency of user input, the audio frequency and the speech model of user's input are compared, identify the text corresponding with audio user.
Judge whether the user will switch the current information of listening to, if, then obtain the information that user's selection is listened to, judge that this selecteed information is audio-frequency information or text message, if audio-frequency information is then play-overed to the user; If text message is an audio-frequency information with text information translation earlier then, play to the user again;
Recording user is listened to interest and is sent to server.
Technical conceive of the present invention is: the information resources that will obtain from the internet or the information resources theme storage of being imported by administrator hand in sub-category minute, and the speech synthesis technique of inciting somebody to action text message utilization maturation wherein plays to the user with voice mode, the information that the user listens to is not limited to site radio, can expand to all resource types on the internet, the information of dabbling is wide, and network sound-searching unit and server not only can carry out exchanges data by audio form, can also textual form carry out exchanges data (except that audio resource), with can only carry out comparing of exchanges data by audio form, transmission speed of the present invention is faster, the storage space that takies is little, is convenient to management.
Simultaneously,, the user is submerged in the magnanimity information of internet for being unlikely to, can be as searching for relevant information on computers, and network sound-searching unit also provides good interactive interface for the user.The user not only can select the content that will listen to, can also pass through literal or phonetic entry keyword, obtains relevant information from server.Network sound-searching unit integrating speech sound recognition technology is converted into keyword with the speech data of input.Afterwards, network sound-searching unit sends to server with keyword by network, and server is recommended relevant information resources according to user interest model, and it is sent it back network sound-searching unit.
Network sound-searching unit combines media platforms such as internet and newpapers and periodicals with traditional radio, can active give him with the information push that voice mode will meet user's request, and ordinary populace is benefited, and also can make all kinds of disadvantaged group obtain the welfare of imformation age.
Network sound-searching unit can be based on this method developing operation at all kinds of intelligent terminals software of (as supporting mobile phone, PDA, the IPTV etc. of networking); Also can be separately occur with the form of intelligent terminal; Can also be integrated with traditional radio, replace traditional radio, search the sound machine as on automobile, using new-type network.
Embodiment two
With reference to Fig. 1-4
A kind of network sound-searching unit, comprise with can from network, obtain information resources or by administrator hand input and with all information classifications not, the server of subject identification carries out exchanges data, identification from the affiliated classification of the text message of server, the network communication module of theme, described network communication module is connected with the memory module of can be sub-category, dividing theme to store from the text message of server; Described memory module is connected with a phonetic synthesis module that text message can be converted to audio-frequency information, and described phonetic synthesis module is connected with the playing module that the audio frequency that it can be changed is broadcast to the user;
Described network sound-searching unit also comprises the keyword that allows the user to import to represent its interest so that the interactive module of the interested fresh information of search subscriber, and described interactive module transfers to keyword server, retrieved according to keyword by server by described network communication module.
Described interactive module comprises the text that can obtain user input or the input block of audio frequency keyword, and the audio frequency keyword is converted to the voice recognition unit of text, and described interactive module transfers to server with text key word.
The resolution unit that comprises the pairing target signature vector model of audio frequency of resolving user's input in the described voice recognition unit, make up the voice unit of the text speech model corresponding with audio frequency, with with the comparison of target signature vector model and speech model, to identify the recognition unit with the pairing text of audio user, described recognition unit is connected with server by described network communication module.
Described voice unit comprises the hot news speech that extracts in the network, the dictionary unit that makes up the focus dictionary, adjust the weight information of the focus speech in the dictionary and delete the administrative unit that weight is lower than the focus speech of setting threshold according to passage of time, use the voice corpus that each focus speech is carried out voice training to obtain each focus speech characteristic of correspondence vector model, to emerge the training unit of speech model.
Described input block comprises handwriting screen input, keyboard input and audio frequency input.
Described network sound-searching unit comprises also and the current information of listening to can be switched to the navigation module that the user wants the information listened to that described navigation module is connected with described memory module.
Described network sound-searching unit also comprises the specifying information clauses and subclauses under each theme of can recording user listening to and the feedback module of time of listening to, and described feedback module is sent to server by described network communication module with temporal summation.
The described content of this instructions embodiment only is enumerating the way of realization of inventive concept; protection scope of the present invention should not be regarded as only limiting to the concrete form that embodiment states, protection scope of the present invention also reach in those skilled in the art conceive according to the present invention the equivalent technologies means that can expect.
Claims (10)
1. the implementation method of a network sound-searching unit may further comprise the steps:
1), from network, obtains information resources by server, or text or audio-frequency information are input to server by administrator hand, server is pressed its described classification (as news category, blog class, e-book class, music class, storytelling class with all information ...), described theme is (as physical culture, military affairs, amusement ...) identify respectively;
2), server listens to interest according to the user and initiatively gives network sound-searching unit with information push, network sound-searching unit receives and identifies described classification of current information and theme;
3), judge that the current information of obtaining is text message or audio frequency, if text message then earlier is converted to audio-frequency information with text message, again this audio-frequency information is played to the user; If audio-frequency information is then play-overed to the user;
4), judge whether the user needs to search for not the fresh information that pushes, if, then obtain the keyword of its information of interest of representative of user's input, this keyword is sent to server, is retrieved according to keyword by server, execution in step 2 again.
2. the implementation method of a kind of network sound-searching unit as claimed in claim 1, it is characterized in that: in the step 4, the mode that the user imports keyword is text input and phonetic entry, if the keyword of user's input is a text message, then directly this text is sent to server; If the keyword of user's input is an audio-frequency information, then earlier this audio-frequency information is converted to text message, text message is sent to server.
3. the implementation method of a kind of network sound-searching unit as claimed in claim 2, it is characterized in that: in the step 4, the step that audio-frequency information is converted to text message comprises:
1) sets up the text speech model corresponding with audio frequency;
(1.1) newsletter archive on the periodic analysis network extracts the hot news speech of current point in time and forms the focus dictionary;
(1.2) the lowest weightings threshold value of focus speech is set, As time goes on adjusts the weight of all focus speech in the focus dictionary, the deletion weight is lower than the focus speech of described lowest weightings threshold value;
(1.3) use the voice corpus that each focus speech is carried out voice training, obtain each focus speech characteristic of correspondence vector model, preserve focus speech and characteristic of correspondence vector model thereof as speech model.
2) obtain the eigenvector model of the audio frequency of user input, the audio frequency and the speech model of user's input are compared, identify the text corresponding with audio user.
4. as the implementation method of one of claim 1-3 described a kind of network sound-searching unit, it is characterized in that: judge whether the user will switch the current information of listening to, if then obtain the information that user's selection is listened to, with text information translation is audio-frequency information, plays to the user again.
5. the implementation method of a kind of network sound-searching unit as claimed in claim 4, it is characterized in that: classification and theme, text marking, this message length of this information and the time of listening under the information of listening to the user are listened to interest as the user, and recording user is listened to interest and sent it to server.
6. use the network sound-searching unit of the implementation method of a kind of network sound-searching unit as claimed in claim 1, it is characterized in that: comprise with can from network, obtain information resources or by administrator hand input and with all information classifications not, the server of subject identification carries out exchanges data, identification from the affiliated classification of the text message of server, the network communication module of theme, described network communication module is connected with the memory module of can be sub-category, dividing theme to store from the text message of server; Described memory module is connected with a phonetic synthesis module that text message can be converted to audio-frequency information, and described phonetic synthesis module is connected with the playing module that the audio frequency that it can be changed is broadcast to the user;
Described network sound-searching unit also comprises the keyword that allows the user to import to represent its interest so that the interactive module of the interested fresh information of search subscriber, and described interactive module transfers to keyword server, retrieved according to keyword by server by described network communication module.
7. network sound-searching unit as claimed in claim 6 is characterized in that: described input block comprises handwriting screen input, keyboard input and audio frequency input;
Described interactive module comprises the text that can obtain user input or the input block of audio frequency keyword, the audio frequency keyword is converted to the voice recognition unit of text, and described interactive module transfers to server by described network communication module with text key word.
The resolution unit that comprises the pairing target signature vector model of audio frequency of resolving user's input in the described voice recognition unit, make up the voice unit of the text speech model corresponding with audio frequency, with with the comparison of target signature vector model and speech model, to identify the recognition unit with the pairing text of audio user, described recognition unit is connected with server by described network communication module.
8. network sound-searching unit as claimed in claim 7, it is characterized in that: described voice unit comprises the hot news speech that extracts in the network, the dictionary unit that makes up the focus dictionary, adjust the weight information of the focus speech in the dictionary and delete the administrative unit that weight is lower than the focus speech of setting threshold according to passage of time, use the voice corpus that each focus speech is carried out voice training to obtain each focus speech characteristic of correspondence vector model, to emerge the training unit of speech model.
9. as the described network sound-searching unit of one of claim 6-8, it is characterized in that: described network sound-searching unit also comprises can obtain the navigation module that the user selects the information listen to.
10. network sound-searching unit as claimed in claim 9, it is characterized in that: described network sound-searching unit also comprises text marking, this message length of classification under the information of can recording user listening to and theme, this information and the feedback module of time of listening to, and described feedback module is sent to server by described network communication module with temporal summation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910154892A CN101739437A (en) | 2009-11-26 | 2009-11-26 | Implementation method for network sound-searching unit and specific device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910154892A CN101739437A (en) | 2009-11-26 | 2009-11-26 | Implementation method for network sound-searching unit and specific device thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101739437A true CN101739437A (en) | 2010-06-16 |
Family
ID=42462927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910154892A Pending CN101739437A (en) | 2009-11-26 | 2009-11-26 | Implementation method for network sound-searching unit and specific device thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101739437A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930297A (en) * | 2010-07-23 | 2010-12-29 | 百度在线网络技术（北京）有限公司 | Method, device and system for user to perform text input in network interaction |
| CN102592595A (en) * | 2012-03-19 | 2012-07-18 | 安徽科大讯飞信息科技股份有限公司 | Voice recognition method and system |
| CN102739697A (en) * | 2011-04-01 | 2012-10-17 | 深圳市赛格导航科技股份有限公司 | Method for broadcasting information on navigator and apparatus thereof |
| CN103677722A (en) * | 2012-09-03 | 2014-03-26 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN104103268A (en) * | 2013-04-03 | 2014-10-15 | ***通信集团安徽有限公司 | Corpus processing method, device and voice synthesis system |
| CN106098056A (en) * | 2016-06-14 | 2016-11-09 | 腾讯科技（深圳）有限公司 | Processing method, NEWS SERVER and the system of a kind of voice news |
| CN106341722A (en) * | 2016-09-21 | 2017-01-18 | 努比亚技术有限公司 | Video editing method and device |
| CN108551482A (en) * | 2018-04-16 | 2018-09-18 | 深圳壹账通智能科技有限公司 | A kind of method for pushing of speech message, device and computer readable storage medium |
| CN108710707A (en) * | 2018-05-30 | 2018-10-26 | 武汉轻工大学 | Show method, apparatus, terminal device and the system of disadvantaged group's user information |
| CN109392309A (en) * | 2017-06-13 | 2019-02-26 | 谷歌有限责任公司 | Establish the network session based on audio with non-registered resource |
| CN111104088A (en) * | 2018-10-25 | 2020-05-05 | 阿里巴巴集团控股有限公司 | Method and system for broadcasting information through voice equipment |
| CN112396536A (en) * | 2019-08-12 | 2021-02-23 | 北京国双科技有限公司 | Method and device for realizing intelligent service |
-
2009
- 2009-11-26 CN CN200910154892A patent/CN101739437A/en active Pending
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101930297B (en) * | 2010-07-23 | 2013-09-04 | 百度在线网络技术（北京）有限公司 | Method, device and system for user to perform text input in network interaction |
| CN101930297A (en) * | 2010-07-23 | 2010-12-29 | 百度在线网络技术（北京）有限公司 | Method, device and system for user to perform text input in network interaction |
| CN102739697A (en) * | 2011-04-01 | 2012-10-17 | 深圳市赛格导航科技股份有限公司 | Method for broadcasting information on navigator and apparatus thereof |
| CN102739697B (en) * | 2011-04-01 | 2015-06-17 | 深圳市赛格导航科技股份有限公司 | Method for broadcasting information on navigator and apparatus thereof |
| CN102592595A (en) * | 2012-03-19 | 2012-07-18 | 安徽科大讯飞信息科技股份有限公司 | Voice recognition method and system |
| CN102592595B (en) * | 2012-03-19 | 2013-05-29 | 安徽科大讯飞信息科技股份有限公司 | Voice recognition method and system |
| CN103677722A (en) * | 2012-09-03 | 2014-03-26 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN104103268B (en) * | 2013-04-03 | 2017-03-29 | ***通信集团安徽有限公司 | A kind of language material library processing method, device and speech synthesis system |
| CN104103268A (en) * | 2013-04-03 | 2014-10-15 | ***通信集团安徽有限公司 | Corpus processing method, device and voice synthesis system |
| CN106098056A (en) * | 2016-06-14 | 2016-11-09 | 腾讯科技（深圳）有限公司 | Processing method, NEWS SERVER and the system of a kind of voice news |
| CN106341722A (en) * | 2016-09-21 | 2017-01-18 | 努比亚技术有限公司 | Video editing method and device |
| CN109392309A (en) * | 2017-06-13 | 2019-02-26 | 谷歌有限责任公司 | Establish the network session based on audio with non-registered resource |
| CN109392309B (en) * | 2017-06-13 | 2022-02-22 | 谷歌有限责任公司 | Establishing audio-based web sessions with unregistered resources |
| US11475900B2 (en) | 2017-06-13 | 2022-10-18 | Google Llc | Establishment of audio-based network sessions with non-registered resources |
| CN108551482A (en) * | 2018-04-16 | 2018-09-18 | 深圳壹账通智能科技有限公司 | A kind of method for pushing of speech message, device and computer readable storage medium |
| CN108710707A (en) * | 2018-05-30 | 2018-10-26 | 武汉轻工大学 | Show method, apparatus, terminal device and the system of disadvantaged group's user information |
| CN111104088A (en) * | 2018-10-25 | 2020-05-05 | 阿里巴巴集团控股有限公司 | Method and system for broadcasting information through voice equipment |
| CN111104088B (en) * | 2018-10-25 | 2023-10-03 | 阿里巴巴集团控股有限公司 | Method and system for broadcasting information through voice equipment |
| CN112396536A (en) * | 2019-08-12 | 2021-02-23 | 北京国双科技有限公司 | Method and device for realizing intelligent service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101739437A (en) | Implementation method for network sound-searching unit and specific device thereof | |
| JP6982602B2 (en) | Resource push method for smart devices, smart devices and computer readable storage media | |
| US9824150B2 (en) | Systems and methods for providing information discovery and retrieval | |
| CN102117614B (en) | Personalized text-to-speech synthesis and personalized speech feature extraction | |
| US9218414B2 (en) | System, method, and user interface for a search engine based on multi-document summarization | |
| CN105335455A (en) | Text reading method and apparatus | |
| CN107844586A (en) | News recommends method and apparatus | |
| CN106570100A (en) | Information search method and device | |
| CN106059904B (en) | Method and system for scoring live broadcast songs based on instant messaging software | |
| CN107864410B (en) | Multimedia data processing method and device, electronic equipment and storage medium | |
| CN102196207A (en) | Method, device and system for controlling television by using voice | |
| CN110164415A (en) | A kind of recommended method based on speech recognition, device and medium | |
| CN108763579A (en) | Search for content recommendation method, device, terminal device and storage medium | |
| CN101566995A (en) | Method and system for integral release of internet information | |
| WO2019047850A1 (en) | Identifier displaying method and device, request responding method and device | |
| CN110460514A (en) | Message method, device, storage medium and the equipment of instant messaging tools | |
| CN101465068A (en) | Method for the determination of supplementary content in an electronic device | |
| CN107645685A (en) | Information processing method, device, terminal device and storage medium | |
| CN109144285A (en) | A kind of input method and device | |
| CN104038774B (en) | Generate the method and device of ring signal file | |
| CN106911959A (en) | A kind of voice drawing reading and system based on intelligent television | |
| CN103593356A (en) | Method and system for information searching on basis of multimedia information fingerprint technology and application | |
| CN104581396A (en) | Processing method and device for promotion information | |
| CN107193922B (en) | A kind of method and device of information processing | |
| CN109948155B (en) | Multi-intention selection method and device and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20100616 |