CN103117058A - Multi-voice engine switch system and method based on intelligent television platform - Google Patents
Multi-voice engine switch system and method based on intelligent television platform Download PDFInfo
- Publication number
- CN103117058A CN103117058A CN201210558320XA CN201210558320A CN103117058A CN 103117058 A CN103117058 A CN 103117058A CN 201210558320X A CN201210558320X A CN 201210558320XA CN 201210558320 A CN201210558320 A CN 201210558320A CN 103117058 A CN103117058 A CN 103117058A
- Authority
- CN
- China
- Prior art keywords
- speech
- module
- speech engine
- engine
- voice
- 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.)
- Granted
Links
Images
Abstract
The invention relates to intelligent television software platforms and discloses a multi-voice engine switch method based on an intelligent television platform. The purposes that a voice engine with highest identifying efficiency at present can be automatically searched and switching is carried out are achieved, and voice interactive experience of a user can be improved. The method includes that when the user operates a voice application program and uses a voice identifying function, a voice engine selection module obtains collected voice data through a voice application interface, then the voice data are transmitted to each voice engine module, response time of returning of an identifying result by each voice engine module is recorded and compared, and a voice engine module with the shortest response time is selected and switching is carried out. In addition, the invention further discloses a corresponding switch system which is suitable for achieving a quick voice identifying function in an intelligent television.
Description
Technical field
The present invention relates to the intelligent television software platform, specifically, relate to a kind of more voice engine switched system and method based on the intelligent television platform.
Background technology
Along with television terminal is intelligent, the development of networking, the retrievable content of intelligent television has obtained abundant greatly, and function is more diversification also, and controlling of TV becomes more frequent and complicated thereupon.User's operating process has been simplified in the application of speech recognition technology on intelligent television greatly, and the user experiences and is greatly improved.Because speech recognition need to take huge system resource, intelligent television generally all connects cloud server by network at present and realizes speech identifying function;
Be used for realizing that the speech recognition engine of speech identifying function is comprised of speech detection module, characteristic extracting module and identification search module in server; Wherein, the function of speech detection module be carry out voice signal detection and with processing, TV is sent to this module with the primary voice data that collects, and voice signal data need to convert the data layout (such as 8K, 16bit) of standard in the speech detection module; Simultaneously, utilize efficient signal detection algorithm, judge the starting point and ending point of voice; Characteristic extracting module is received the audio data stream after detection, therefrom extracts the eigenvector stream that obtains voice signal.Phonetic feature is to utilize Digital Signal Processing, extracts the information of reacting its essential attribute most from voice signal.In this module, need to carry out the processing such as pre-emphasis, minute frame, windowing, product and conversion, Cepstrum Transform, difference to voice signal, finally obtain the eigenvector of tens of dimensions left and right; Acoustic model storehouse, dictionary/dictionary in the unknown phonic signal character that will receive of identification search module and engine and identify syntactic information and mate obtains the word sequence of suitable unknown phonetic feature.This process can be briefly described as follows: by retrieval dictionary/dictionary, sentence can be resolved into the sequence of phoneme by word sequence.The sequence of this phoneme combines with acoustic model, just obtains more reflecting the acoustic model unit sequence information of its essential attribute.Then, the information of the eigenvector of raw tone and all possible sentence candidate's acoustic model unit sequence is mated mutually, calculate its matching probability, select the acoustic model unit sequence with maximum a posteriori probability.By this unit sequence, can obtain with it corresponding word sequence, the word sequence of Here it is engine exports to TV.
And owing to there being a plurality of speech recognition engines in server, if the some stationary engines of single use carry out speech recognition, be unfavorable for the lifting of intelligent television audio identification efficiency, cause the user speech interactive experience bad; Therefore, how to search the speech recognition engine of current full blast and to switch be problem demanding prompt solution during interactive voice is used between a plurality of speech recognition engines.
Summary of the invention
Technical matters to be solved by this invention is: propose a kind of more voice engine switched system and method based on the intelligent television platform, realize automatically searching the highest speech engine of current recognition efficiency and switching, the interactive voice that promotes the user is experienced.
The scheme that the present invention solves the problems of the technologies described above employing is: the more voice engine switched system based on the intelligent television platform comprises: speech engine is selected module and at least two speech engine modules; All speech engine modules are encapsulated by unified speech engine interface, and connect speech engine selection module by the speech engine interface; Described speech engine selects module to be connected with speech application by the voice application interface.
Further, described speech engine module is used for obtaining from the speech engine interface speech data that speech engine selects module to transmit, and speech data is identified, and then selects module to return to recognition result to speech engine; Described speech engine selects module to be used for when speech application uses speech identifying function, obtain the speech data that collects by the voice application interface, speech data is sent to each speech engine module by the speech engine interface, and receive the recognition result that all speech engine modules are returned, recording each speech engine module returns to the response time of recognition result and compares, select the shortest speech engine module of response time to switch, make speech application can call the highest speech engine module of recognition efficiency.
Further, described selection the shortest speech engine module of response time is switched and referred to: speech engine selects module to be connected to the shortest speech engine module of response time by the speech engine interface, disconnects simultaneously and being connected of other speech engine module.
In addition, the invention allows for a kind of corresponding more voice engine switching method based on the intelligent television platform, comprising:
A. when the user moved speech application use speech identifying function, speech engine selected module to obtain the speech data that collects by the voice application interface;
B. speech engine selects module that speech data is sent to each speech engine module by the speech engine interface;
C. each speech engine module is identified speech data, then selects module to return to recognition result to speech engine;
D. speech engine selects each speech engine module of module records return to the response time of recognition result and compare, and selects the shortest speech engine module of response time to switch.
Further, in steps d, described selection the shortest speech engine module of response time is switched and referred to: speech engine selects module to be connected to the shortest speech engine module of response time by the speech engine interface, disconnects simultaneously and being connected of other speech engine module.
The invention has the beneficial effects as follows: compare by the response time (being recognition speed) of each speech engine module being returned to recognition result, select the shortest speech engine module of response time to switch, make speech application can call the highest speech engine module of recognition efficiency and carry out speech recognition, thereby promoted the whole recognition efficiency of speech recognition; And, because the connection carrier (voice application interface) between speech application and speech engine selection module remains unchanged, when the speech engine module switches, speech application need not to pay close attention to specifically which speech engine module switches, thereby has guaranteed stability and the continuity of speech recognition.
Description of drawings
Fig. 1 is that in the present invention, the more voice engine switched system based on the intelligent television platform is realized framework map;
Fig. 2 is the process flow diagram based on the more voice engine switching method of intelligent television platform in the present invention.
Embodiment
of the present inventionly realize that principle is: due to the performance difference of each speech engine module in system, these modules to the processing of speech data with regard to faster or slower, therefore, we can select module that the response time of each speech engine resume module speech data is recorded and compares by a speech engine is set, thereby it is the shortest to find out the processing time, respond the fastest speech engine module, then the connection that switches to this speech engine module gets final product, and the introducing that speech engine is selected module does not change all the time due to the application interface between itself and speech application, therefore, stability problem that simultaneously can also resolution system.
Referring to Fig. 1, the more voice engine switched system based on the intelligent television platform in the present invention comprises speech engine selection module and a plurality of speech engine module; All speech engine modules are encapsulated by unified speech engine interface, and connect speech engine selection module by the speech engine interface; Described speech engine selects module to be connected with speech application by the voice application interface.
Wherein, described speech engine module is used for obtaining from the speech engine interface speech data that speech engine selects module to transmit, and speech data is identified, and then selects module to return to recognition result to speech engine; Described speech engine selects module to be used for when speech application uses speech identifying function, obtain the speech data that collects by the voice application interface, speech data is sent to each speech engine module by the speech engine interface, and receive the recognition result that all speech engine modules are returned, recording each speech engine module returns to the response time of recognition result and compares, select the shortest speech engine module of response time to switch, make speech application can call the highest speech engine module of recognition efficiency.
Fig. 2 has provided the corresponding flow process of changing method, and it comprises following performing step:
A. when the user moved speech application use speech identifying function, speech engine selected module to obtain the speech data that collects by the voice application interface; The voice capture device that this speech data derives from intelligent television collects to get sound source signal;
B. speech engine selects module that speech data is sent to each speech engine module by the speech engine interface; Owing to having adopted unified speech engine interface to encapsulate, each speech engine module can be received same speech data simultaneously;
C. each speech engine module is identified speech data, then selects module to return to recognition result to speech engine;
D. speech engine selects each speech engine module of module records return to the response time of recognition result and compare, select the shortest speech engine module of response time to switch: speech engine selects module to be connected to the shortest speech engine module of response time by the speech engine interface, and disconnection simultaneously is connected with other speech engine module.After this, speech application can be realized speech recognition fast by calling the shortest speech engine module of this response time, and the interactive voice that promotes the user is experienced.
Claims (5)
1. based on the more voice engine switched system of intelligent television platform, it is characterized in that, comprising: speech engine is selected module and at least two speech engine modules; All speech engine modules are encapsulated by unified speech engine interface, and connect speech engine selection module by the speech engine interface; Described speech engine selects module to be connected with speech application by the voice application interface.
2. the more voice engine switched system based on the intelligent television platform as claimed in claim 1, it is characterized in that, described speech engine module is used for obtaining from the speech engine interface speech data that speech engine selects module to transmit, and speech data is identified, then select module to return to recognition result to speech engine; Described speech engine selects module to be used for when speech application uses speech identifying function, obtain the speech data that collects by the voice application interface, speech data is sent to each speech engine module by the speech engine interface, and receive the recognition result that all speech engine modules are returned, recording each speech engine module returns to the response time of recognition result and compares, select the shortest speech engine module of response time to switch, make speech application can call the highest speech engine module of recognition efficiency.
3. the more voice engine switched system based on the intelligent television platform as claimed in claim 2, it is characterized in that, described selection the shortest speech engine module of response time is switched and referred to: speech engine selects module to be connected to the shortest speech engine module of response time by the speech engine interface, disconnects simultaneously and being connected of other speech engine module.
4. based on the more voice engine switching method of intelligent television platform, it is characterized in that, comprising:
A. when the user moved speech application use speech identifying function, speech engine selected module to obtain the speech data that collects by the voice application interface;
B. speech engine selects module that speech data is sent to each speech engine module by the speech engine interface;
C. each speech engine module is identified speech data, then selects module to return to recognition result to speech engine;
D. speech engine selects each speech engine module of module records return to the response time of recognition result and compare, and selects the shortest speech engine module of response time to switch.
5. the more voice engine switching method based on the intelligent television platform as claimed in claim 4, it is characterized in that, in steps d, described selection the shortest speech engine module of response time is switched and referred to: speech engine selects module to be connected to the shortest speech engine module of response time by the speech engine interface, disconnects simultaneously and being connected of other speech engine module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210558320.XA CN103117058B (en) | 2012-12-20 | 2012-12-20 | Based on Multi-voice engine switch system and the method for intelligent television platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210558320.XA CN103117058B (en) | 2012-12-20 | 2012-12-20 | Based on Multi-voice engine switch system and the method for intelligent television platform |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103117058A true CN103117058A (en) | 2013-05-22 |
CN103117058B CN103117058B (en) | 2015-12-09 |
Family
ID=48415416
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210558320.XA Active CN103117058B (en) | 2012-12-20 | 2012-12-20 | Based on Multi-voice engine switch system and the method for intelligent television platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103117058B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103336687A (en) * | 2013-06-17 | 2013-10-02 | 深圳市金立通信设备有限公司 | Application interface switching method and terminal |
CN103714814A (en) * | 2013-12-11 | 2014-04-09 | 四川长虹电器股份有限公司 | Voice introducing method of voice recognition engine |
CN104795069A (en) * | 2014-01-21 | 2015-07-22 | 腾讯科技(深圳)有限公司 | Speech recognition method and server |
CN105609102A (en) * | 2014-11-21 | 2016-05-25 | 中兴通讯股份有限公司 | Method and device for voice engine parameter configuration |
WO2017128775A1 (en) * | 2016-01-28 | 2017-08-03 | 中兴通讯股份有限公司 | Voice control system, voice processing method and terminal device |
CN107526512A (en) * | 2017-08-31 | 2017-12-29 | 联想(北京)有限公司 | Switching method and system for electronic equipment |
CN107657031A (en) * | 2017-09-28 | 2018-02-02 | 四川长虹电器股份有限公司 | Method based on android system management intelligent sound box voice technical ability |
CN109036427A (en) * | 2018-09-25 | 2018-12-18 | 苏宁智能终端有限公司 | A kind of method and system of dynamic configuration speech-recognition services |
CN109410926A (en) * | 2018-11-27 | 2019-03-01 | 恒大法拉第未来智能汽车(广东)有限公司 | Voice method for recognizing semantics and system |
CN109493862A (en) * | 2018-12-24 | 2019-03-19 | 深圳Tcl新技术有限公司 | Terminal, the determination method of voice server and computer readable storage medium |
CN109949816A (en) * | 2019-02-14 | 2019-06-28 | 安徽云之迹信息技术有限公司 | Robot voice processing method and processing device, cloud server |
CN109947651A (en) * | 2019-03-21 | 2019-06-28 | 上海智臻智能网络科技股份有限公司 | Artificial intelligence engine optimization method and device |
CN110708365A (en) * | 2019-09-23 | 2020-01-17 | 杭州迪普科技股份有限公司 | Data receiver selection method and device |
CN111179934A (en) * | 2018-11-12 | 2020-05-19 | 奇酷互联网络科技(深圳)有限公司 | Method of selecting a speech engine, mobile terminal and computer-readable storage medium |
CN113450785A (en) * | 2020-03-09 | 2021-09-28 | 上海擎感智能科技有限公司 | Implementation method, system, medium and cloud server for vehicle-mounted voice processing |
CN113593535A (en) * | 2021-06-30 | 2021-11-02 | 青岛海尔科技有限公司 | Voice data processing method and device, storage medium and electronic device |
CN114446279A (en) * | 2022-02-18 | 2022-05-06 | 青岛海尔科技有限公司 | Voice recognition method, voice recognition device, storage medium and electronic equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000250591A (en) * | 1999-02-25 | 2000-09-14 | Matsushita Electric Ind Co Ltd | Automatic retrieval system for television program |
CN1323435A (en) * | 1998-10-02 | 2001-11-21 | 国际商业机器公司 | System and method for providing network coordinated conversational services |
CN1429019A (en) * | 2001-12-18 | 2003-07-09 | 松下电器产业株式会社 | TV set with sound discrimination function and its control method |
CN1633679A (en) * | 2001-12-29 | 2005-06-29 | 摩托罗拉公司 | Method and apparatus for multi-level distributed speech recognition |
CN1723487A (en) * | 2002-12-13 | 2006-01-18 | 摩托罗拉公司 | Method and apparatus for selective speech recognition |
-
2012
- 2012-12-20 CN CN201210558320.XA patent/CN103117058B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1323435A (en) * | 1998-10-02 | 2001-11-21 | 国际商业机器公司 | System and method for providing network coordinated conversational services |
JP2000250591A (en) * | 1999-02-25 | 2000-09-14 | Matsushita Electric Ind Co Ltd | Automatic retrieval system for television program |
CN1429019A (en) * | 2001-12-18 | 2003-07-09 | 松下电器产业株式会社 | TV set with sound discrimination function and its control method |
CN1633679A (en) * | 2001-12-29 | 2005-06-29 | 摩托罗拉公司 | Method and apparatus for multi-level distributed speech recognition |
CN1723487A (en) * | 2002-12-13 | 2006-01-18 | 摩托罗拉公司 | Method and apparatus for selective speech recognition |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103336687A (en) * | 2013-06-17 | 2013-10-02 | 深圳市金立通信设备有限公司 | Application interface switching method and terminal |
CN103336687B (en) * | 2013-06-17 | 2016-09-14 | 深圳市金立通信设备有限公司 | The changing method of a kind of application interface and terminal |
CN103714814A (en) * | 2013-12-11 | 2014-04-09 | 四川长虹电器股份有限公司 | Voice introducing method of voice recognition engine |
CN104795069A (en) * | 2014-01-21 | 2015-07-22 | 腾讯科技(深圳)有限公司 | Speech recognition method and server |
CN105609102A (en) * | 2014-11-21 | 2016-05-25 | 中兴通讯股份有限公司 | Method and device for voice engine parameter configuration |
WO2017128775A1 (en) * | 2016-01-28 | 2017-08-03 | 中兴通讯股份有限公司 | Voice control system, voice processing method and terminal device |
CN107018228A (en) * | 2016-01-28 | 2017-08-04 | 中兴通讯股份有限公司 | A kind of speech control system, method of speech processing and terminal device |
CN107526512A (en) * | 2017-08-31 | 2017-12-29 | 联想(北京)有限公司 | Switching method and system for electronic equipment |
CN107657031A (en) * | 2017-09-28 | 2018-02-02 | 四川长虹电器股份有限公司 | Method based on android system management intelligent sound box voice technical ability |
CN109036427A (en) * | 2018-09-25 | 2018-12-18 | 苏宁智能终端有限公司 | A kind of method and system of dynamic configuration speech-recognition services |
CN111179934A (en) * | 2018-11-12 | 2020-05-19 | 奇酷互联网络科技(深圳)有限公司 | Method of selecting a speech engine, mobile terminal and computer-readable storage medium |
CN109410926A (en) * | 2018-11-27 | 2019-03-01 | 恒大法拉第未来智能汽车(广东)有限公司 | Voice method for recognizing semantics and system |
CN109493862A (en) * | 2018-12-24 | 2019-03-19 | 深圳Tcl新技术有限公司 | Terminal, the determination method of voice server and computer readable storage medium |
CN109493862B (en) * | 2018-12-24 | 2021-11-09 | 深圳Tcl新技术有限公司 | Terminal, voice server determination method, and computer-readable storage medium |
CN109949816A (en) * | 2019-02-14 | 2019-06-28 | 安徽云之迹信息技术有限公司 | Robot voice processing method and processing device, cloud server |
CN109947651A (en) * | 2019-03-21 | 2019-06-28 | 上海智臻智能网络科技股份有限公司 | Artificial intelligence engine optimization method and device |
CN109947651B (en) * | 2019-03-21 | 2022-08-02 | 上海智臻智能网络科技股份有限公司 | Artificial intelligence engine optimization method and device |
CN110708365A (en) * | 2019-09-23 | 2020-01-17 | 杭州迪普科技股份有限公司 | Data receiver selection method and device |
CN113450785A (en) * | 2020-03-09 | 2021-09-28 | 上海擎感智能科技有限公司 | Implementation method, system, medium and cloud server for vehicle-mounted voice processing |
CN113450785B (en) * | 2020-03-09 | 2023-12-19 | 上海擎感智能科技有限公司 | Implementation method, system, medium and cloud server for vehicle-mounted voice processing |
CN113593535A (en) * | 2021-06-30 | 2021-11-02 | 青岛海尔科技有限公司 | Voice data processing method and device, storage medium and electronic device |
CN114446279A (en) * | 2022-02-18 | 2022-05-06 | 青岛海尔科技有限公司 | Voice recognition method, voice recognition device, storage medium and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN103117058B (en) | 2015-12-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103117058B (en) | Based on Multi-voice engine switch system and the method for intelligent television platform | |
CN103093755B (en) | Based on terminal and mutual network household electric appliance control method and the system of internet voice | |
EP3734596A1 (en) | Server for determining target device based on speech input of user and controlling target device, and operation method of the server | |
CN109522083B (en) | Page intelligent response interaction system and method | |
CN102196207B (en) | Method, device and system for controlling television by using voice | |
CN104867492A (en) | Intelligent interaction system and method | |
US11457061B2 (en) | Creating a cinematic storytelling experience using network-addressable devices | |
CN102855872A (en) | Method and system for controlling household appliance on basis of voice interaction between terminal and internet | |
CN101576901B (en) | Method for generating search request and mobile communication equipment | |
JP6783339B2 (en) | Methods and devices for processing audio | |
CN107018228B (en) | Voice control system, voice processing method and terminal equipment | |
CN102831892A (en) | Toy control method and system based on internet voice interaction | |
CN103730115A (en) | Method and device for detecting keywords in voice | |
CN106792048B (en) | Method and device for recognizing voice command of smart television user | |
CN103208285A (en) | Household electrical appliance control method and system based on voice interaction of mobile communication terminals | |
CN113889113A (en) | Sentence dividing method and device, storage medium and electronic equipment | |
CN101833977A (en) | Court trial video real-time indexing method triggered by specific voice | |
CN101833982A (en) | Special sound-triggered court trial audio file real-time indexing method | |
CN116566760B (en) | Smart home equipment control method and device, storage medium and electronic equipment | |
EP3059731A1 (en) | Method and apparatus for automatically sending multimedia file, mobile terminal, and storage medium | |
CN111833857A (en) | Voice processing method and device and distributed system | |
CN112700770A (en) | Voice control method, sound box device, computing device and storage medium | |
CN101588415A (en) | Voice service method and voice service system | |
KR20220056836A (en) | Method and apparatus for determining voice response rate, electronic device, computer readable storage medium and computer program | |
CN113936655A (en) | Voice broadcast processing method and device, computer equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |