CN102968987A - Speech recognition method and system - Google Patents
Speech recognition method and system Download PDFInfo
- Publication number
- CN102968987A CN102968987A CN2012104695180A CN201210469518A CN102968987A CN 102968987 A CN102968987 A CN 102968987A CN 2012104695180 A CN2012104695180 A CN 2012104695180A CN 201210469518 A CN201210469518 A CN 201210469518A CN 102968987 A CN102968987 A CN 102968987A
- Authority
- CN
- China
- Prior art keywords
- voice
- type
- speech
- recognition
- recognition result
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 239000013598 vector Substances 0.000 claims description 30
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a speech recognition method which comprises the following steps of: receiving speech information and a recognition result type transmitted from a client; looking for a speech classification lexicon corresponding to the recognition result type from more than one preset speech classification lexicons, thus obtaining the recognition result from the found speech classification lexicon according to the speech information; and feeding back recognition results which are sequenced according to similarities from high to low to the client. The invention further provides a speech recognition system. According to the technical scheme provided by the invention, the speech recognition rate of application with the speech recognition function is improved.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the field of Internet application, in particular to a voice recognition method and a voice recognition system.
[ background of the invention ]
The voice recognition technology is one of the ten-year-round important scientific and technological development technologies in the field of information technology, and is mainly applied to voice dialing, voice navigation, indoor equipment control, voice search, dictation data entry and the like. Because the voice recognition process is intelligent, the situations of homophones and different characters can occur, so that a plurality of recognition results can occur, and when a plurality of recognition results exist, the sequencing of the recognition results is particularly important.
At present, a plurality of recognition results are sorted mainly according to the sequence from high to low of the matching rate of the input voice information and the voice model in the voice model library, for example, in hundred-degree search, the same sequence of recognition results can be obtained no matter which search classification the input voice information is in; in the recognition results provided to the user according to the current sorting method, the results sorted in the top are not the optimal results, and the user needs to further interact with the search server to manually screen or re-input the voice information for searching, so that the voice recognition rate of the search server is low, and the load of the search server is increased when the user repeatedly inputs the voice information.
[ summary of the invention ]
The invention provides a voice recognition method and a voice recognition system, which can improve the voice recognition rate of an application with a voice recognition function.
The specific technical scheme of the invention is as follows:
according to a preferred embodiment of the present invention, a speech recognition method includes:
receiving voice information and a recognition result type sent by a client;
finding a voice classification word bank corresponding to the type of the recognition result from more than one preset voice classification word bank, and acquiring the recognition result from the found voice classification word bank according to the voice information;
and returning the recognition results with the similarity ranked from high to low to the client.
In the above method, the method for finding the speech classification lexicon corresponding to the recognition result type comprises:
according to the type of the recognition result, finding a voice classification word bank corresponding to the type of the recognition result in a corresponding relation table of the locally preset result type and the voice classification word bank;
or finding out a similar result type corresponding to the recognition result type according to a preset type association table, and taking the voice classification word bank corresponding to the similar result type as the voice classification word bank corresponding to the recognition result type.
In the method, the speech classification word stock stores the corresponding relation of phrases or characters, type information and speech characteristic vectors; and the type information represents the type of the phrase or the word in the speech classification word stock.
In the above method, the method for updating the speech classification lexicon comprises: and performing semantic analysis on keywords input by a user, and adding the keywords to a corresponding speech classification word bank according to an analysis result.
In the above method, the obtaining the recognition result from the found speech classification lexicon according to the speech information specifically includes:
and extracting a voice characteristic vector from the voice information, comparing the similarity of the extracted voice characteristic vector with the voice characteristic vector in the found voice classification word stock, and taking a word group or a word corresponding to the voice characteristic vector with the similarity ranking at the top as a recognition result.
A speech recognition system comprising: a receiving unit, an identifying unit and a sending unit; wherein,
the receiving unit is used for receiving the voice information and the type of the recognition result sent by the client;
the recognition unit is used for finding the voice classification word bank corresponding to the type of the recognition result from more than one preset voice classification word bank and acquiring the recognition result from the found voice classification word bank according to the voice information;
and the sending unit is used for returning the recognition results with the similarity sorted from high to low to the client.
In the above system, the step of finding the speech classification lexicon corresponding to the recognition result type by the recognition unit specifically includes:
according to the type of the recognition result, finding a voice classification word bank corresponding to the type of the recognition result in a corresponding relation table of the locally preset result type and the voice classification word bank;
or finding out a similar result type corresponding to the recognition result type according to a preset type association table, and taking the voice classification word bank corresponding to the similar result type as the voice classification word bank corresponding to the recognition result type.
In the system, the speech classification word stock stores the corresponding relation of phrases or characters, type information and speech characteristic vectors; and the type information represents the type of the phrase or the word in the speech classification word stock.
In the above system, the updating the speech classification lexicon specifically includes: and performing semantic analysis on keywords input by a user, and adding the keywords to a corresponding speech classification word bank according to an analysis result.
In the above system, the acquiring, by the recognition unit, the recognition result from the found speech classification lexicon according to the speech information specifically includes:
and extracting a voice characteristic vector from the voice information, comparing the similarity of the extracted voice characteristic vector with the voice characteristic vector in the found voice classification word stock, and taking a word group or a word corresponding to the voice characteristic vector with the similarity ranking at the top as a recognition result.
According to the technical scheme, the invention has the following beneficial effects:
the recognition result type represents the requirement of the user on the recognition result, the current voice recognition mode is optimized according to the user requirement, the most-front result in the recognition results provided for the user is ensured to be the optimal result, the frequent interaction between the user and the server is reduced, and the voice recognition rate of the server is improved.
[ description of the drawings ]
FIG. 1 is a flow chart diagram of a preferred embodiment of the present invention for implementing a speech recognition method;
fig. 2 is a schematic structural diagram of a preferred embodiment of the present invention for implementing a speech recognition system.
[ detailed description ] embodiments
The basic idea of the invention is: receiving voice information and a recognition result type sent by a client; finding a voice classification word bank corresponding to the type of the recognition result from more than one preset voice classification word bank, and acquiring the recognition result from the found voice classification word bank according to the voice information; and returning the recognition results with the similarity ranked from high to low to the client.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
The present invention provides a speech recognition method, fig. 1 is a schematic flow chart of a preferred embodiment of implementing the speech recognition method of the present invention, as shown in fig. 1, the preferred embodiment includes the following steps:
Specifically, the client receives voice information input by a user in an application with a voice recognition function and a recognition result type selected by the user, and sends the voice information and the recognition result type to the server through a voice recognition request; the server is a server corresponding to an application with a voice recognition function, the recognition result type is a subtype with the minimum range under the current application, and the recognition result type can be understood as the result type of the voice recognition result currently required by the user.
For example, if the current application with speech recognition function is a hundred degree search, the types of search included under the hundred degree search are: the method comprises the following steps that web pages, videos, music, maps, news, pictures, libraries, encyclopedias, posts, knowledge and the like are displayed, and in the hundred-degree search, a user can select any search type as a current search type according to requirements; if the current application with the voice recognition function is an ordering application, the menu types included under the ordering application are as follows: cold dish, hot dish, staple food, wine, etc.
And 102, the server finds a voice classification word bank corresponding to the type of the recognition result in more than one preset voice classification word bank.
Specifically, after receiving a voice recognition request from a client, a server first finds a voice classification lexicon corresponding to a recognition result type in a corresponding relation table of a locally preset result type and the voice classification lexicon according to the recognition result type carried in the voice recognition request; if the speech classification word bank corresponding to the recognition result type is not found, judging whether the recognition result type has a corresponding similar result type according to a preset type association table, if so, searching the corresponding speech classification word bank in the corresponding relation between the result type and the speech classification word bank according to the similar result type, and taking the found speech classification word bank as the speech classification word bank corresponding to the recognition result type; if the corresponding similar result type does not exist, searching a default voice model library, and searching the default voice model library to obtain a recognition result belongs to the prior art, which is not described herein again; here, the correspondence table between the result type and the speech classification lexicon and the type association table may be preset in the server by the user, wherein the similar result types in the type association table are all set according to the speech classification lexicon, and the type of the speech information in the speech classification lexicon is used as the similar result type, so that the corresponding speech classification lexicon can be found as long as the recognition result type has the similar result type.
For example, if the application with the voice recognition function used by the user is a search application, the recognition result type is the scenery spot type, but there is no voice classification thesaurus corresponding to the scenery spot type, the similar result type of the scenery spot type is determined to be the map type according to the type association table, and then the voice classification thesaurus of the map type is found as the voice classification thesaurus of the scenery spot type.
The voice classification word stock is preset in the server by a user and is used for storing corresponding relations of phrases or characters, type information and voice characteristic vectors; the type information is used for representing the type of the phrase or the character in the speech classification word stock, for example, for a search application with a speech recognition function, a Liuyang is a place name and belongs to a map type, and a Duoyang belongs to a focus phrase and belongs to a webpage type; in the preferred embodiment, there may be more than one speech classification word stock, each speech classification word stock includes only one type of phrase or word; the speech classification word bank can be updated manually or automatically by a server at regular time; for example, the server may perform semantic analysis according to a keyword input by the user, and classify the keyword into a corresponding speech classification word bank according to an analysis result, so as to enrich phrases or words in the speech classification word bank.
And 103, matching the found speech classification word bank by the server according to the speech information input by the user to obtain a recognition result.
Specifically, the server extracts voice feature vectors from voice information input by a user, compares the extracted voice feature vectors with similarity of each voice feature vector in a found voice classification word stock in sequence, and takes phrases or characters corresponding to the voice feature vectors with the similarity ranked at the top as recognition results; specifically, several extracted recognition results can be configured according to requirements; and sequencing more than one obtained recognition result from high to low according to the similarity to obtain a recognition result sequence.
And 104, the server returns the recognition results with the similarity ranked from high to low to the client.
Specifically, the server sorts the recognition results obtained from the speech classification lexicon in the order of high similarity to low similarity to obtain a recognition result sequence, and returns the recognition result sequence to the client.
The client displays the received identification results, wherein the client can display the first identification result in the identification result sequence as a default identification result to the user, or display all the identification results in a sequence from high to low according to the similarity, and the user selects from all the identification results.
To implement the above method, the present invention further provides a speech recognition system, which can be installed in a server of an application with speech recognition function, fig. 2 is a schematic structural diagram of a preferred embodiment of implementing the speech recognition system according to the present invention, as shown in fig. 2, the system includes: a receiving unit 20, a recognition unit 21, and a transmitting unit 22; wherein,
a receiving unit 20, configured to receive the voice information and the type of the recognition result sent by the client;
the recognition unit 21 is configured to find a speech classification lexicon corresponding to the type of the recognition result from more than one preset speech classification lexicon, and obtain a recognition result from the found speech classification lexicon according to the speech information;
and the sending unit 22 is configured to return the recognition results with the similarity ranked from high to low to the client.
The step of finding the speech classification lexicon corresponding to the recognition result type by the recognition unit 21 specifically includes: according to the type of the recognition result, finding a voice classification word bank corresponding to the recognition result in a corresponding relation table of the locally preset result type and the voice classification word bank; or finding out a similar result type corresponding to the recognition result type according to a preset type association table, and taking the voice classification word bank corresponding to the similar result type as the voice classification word bank corresponding to the recognition result type.
The speech classification word stock stores corresponding relations of phrases or characters, type information and speech characteristic vectors; and the type information represents the type of the phrase or the word in the speech classification word stock. The updating the speech classification word bank specifically comprises: and performing semantic analysis on keywords input by a user, and adding the keywords to a corresponding speech classification word bank according to an analysis result.
The obtaining, by the recognition unit 21, a recognition result from the found speech classification lexicon according to the speech information specifically includes: and extracting a voice characteristic vector from the voice information, comparing the similarity of the extracted voice characteristic vector with the voice characteristic vector in the found voice classification word stock, and taking a word group or a word corresponding to the voice characteristic vector with the similarity ranking at the top as a recognition result.
In the above technical solution, the range of the recognition result is preferentially determined according to the type of the recognition result selected by the user, and the recognition result matched with the input voice information is searched in the determined range, for example, for a search application, the voice input by the user is liuyang, if the type of the recognition result is a map type, the first recognition result in the row of the recognition results returned by the server is a liuyang, and if the type of the recognition result is a web page type, the first recognition result in the recognition results returned by the server is a juyan; therefore, in the preferred embodiment of the present invention, the recognition result type can represent the user's requirement for the recognition result, so that the current speech recognition mode is optimized based on the user requirement, and it is ensured that the top-ranked result in the recognition results provided to the user is the optimal result, thereby reducing frequent interaction between the user and the server, improving the speech recognition rate of the server, and bringing about good user experience.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of speech recognition, the method comprising:
receiving voice information and a recognition result type sent by a client;
finding a voice classification word bank corresponding to the type of the recognition result from more than one preset voice classification word bank, and acquiring the recognition result from the found voice classification word bank according to the voice information;
and returning the recognition results with the similarity ranked from high to low to the client.
2. The method of claim 1, wherein the method for finding the phonetic classification lexicon corresponding to the recognition result type comprises:
according to the type of the recognition result, finding a voice classification word bank corresponding to the type of the recognition result in a corresponding relation table of the locally preset result type and the voice classification word bank;
or finding out a similar result type corresponding to the recognition result type according to a preset type association table, and taking the voice classification word bank corresponding to the similar result type as the voice classification word bank corresponding to the recognition result type.
3. The method of claim 1,
the speech classification word stock stores corresponding relations of phrases or characters, type information and speech characteristic vectors; and the type information represents the type of the phrase or the word in the speech classification word stock.
4. The method of claim 3, wherein the step of updating the phonetic classification lexicon comprises: and performing semantic analysis on keywords input by a user, and adding the keywords to a corresponding speech classification word bank according to an analysis result.
5. The method of claim 1, wherein the obtaining recognition results from the found speech classification lexicon according to the speech information specifically comprises:
and extracting a voice characteristic vector from the voice information, comparing the similarity of the extracted voice characteristic vector with the voice characteristic vector in the found voice classification word stock, and taking a word group or a word corresponding to the voice characteristic vector with the similarity ranking at the top as a recognition result.
6. A speech recognition system, comprising: a receiving unit, an identifying unit and a sending unit; wherein,
the receiving unit is used for receiving the voice information and the type of the recognition result sent by the client;
the recognition unit is used for finding the voice classification word bank corresponding to the type of the recognition result from more than one preset voice classification word bank and acquiring the recognition result from the found voice classification word bank according to the voice information;
and the sending unit is used for returning the recognition results with the similarity sorted from high to low to the client.
7. The system according to claim 6, wherein the finding, by the recognition unit, the speech classification lexicon corresponding to the recognition result type specifically comprises:
according to the type of the recognition result, finding a voice classification word bank corresponding to the type of the recognition result in a corresponding relation table of the locally preset result type and the voice classification word bank;
or finding out a similar result type corresponding to the recognition result type according to a preset type association table, and taking the voice classification word bank corresponding to the similar result type as the voice classification word bank corresponding to the recognition result type.
8. The system of claim 6,
the speech classification word stock stores corresponding relations of phrases or characters, type information and speech characteristic vectors; and the type information represents the type of the phrase or the word in the speech classification word stock.
9. The system of claim 8, wherein updating the phonetic classification lexicon specifically comprises: and performing semantic analysis on keywords input by a user, and adding the keywords to a corresponding speech classification word bank according to an analysis result.
10. The system of claim 6, wherein the obtaining, by the recognition unit, the recognition result from the found speech classification lexicon according to the speech information specifically comprises:
and extracting a voice characteristic vector from the voice information, comparing the similarity of the extracted voice characteristic vector with the voice characteristic vector in the found voice classification word stock, and taking a word group or a word corresponding to the voice characteristic vector with the similarity ranking at the top as a recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104695180A CN102968987A (en) | 2012-11-19 | 2012-11-19 | Speech recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104695180A CN102968987A (en) | 2012-11-19 | 2012-11-19 | Speech recognition method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102968987A true CN102968987A (en) | 2013-03-13 |
Family
ID=47799094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012104695180A Pending CN102968987A (en) | 2012-11-19 | 2012-11-19 | Speech recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102968987A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103237136A (en) * | 2013-05-10 | 2013-08-07 | 上海华勤通讯技术有限公司 | Mobile terminal and searching method of subject headings of mobile terminal |
| CN103634321A (en) * | 2013-12-04 | 2014-03-12 | 百度在线网络技术（北京）有限公司 | Voice recognition result display method and device |
| CN103811000A (en) * | 2014-02-24 | 2014-05-21 | 中国移动（深圳）有限公司 | Voice recognition system and voice recognition method |
| CN104731918A (en) * | 2015-03-25 | 2015-06-24 | 百度在线网络技术（北京）有限公司 | Voice search method and device |
| CN104808808A (en) * | 2015-03-23 | 2015-07-29 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN105244024A (en) * | 2015-09-02 | 2016-01-13 | 百度在线网络技术（北京）有限公司 | Voice recognition method and device |
| CN105469789A (en) * | 2014-08-15 | 2016-04-06 | 中兴通讯股份有限公司 | Voice information processing method and voice information processing terminal |
| CN106205613A (en) * | 2016-07-22 | 2016-12-07 | 深圳智眸科技有限公司 | A kind of navigation audio recognition method and system |
| CN107170446A (en) * | 2017-05-19 | 2017-09-15 | 深圳市优必选科技有限公司 | Semantic processing server and method for semantic processing |
| CN107193829A (en) * | 2016-03-14 | 2017-09-22 | 百度在线网络技术（北京）有限公司 | Application program recommends method and apparatus |
| CN107678309A (en) * | 2017-09-01 | 2018-02-09 | 科大讯飞股份有限公司 | Control sentence pattern generation and application control method and device and storage medium |
| WO2018205704A1 (en) * | 2017-05-10 | 2018-11-15 | 平安科技（深圳）有限公司 | Electronic device, intelligent voice navigation method and computer readable storage medium |
| CN109359295A (en) * | 2018-09-18 | 2019-02-19 | 深圳壹账通智能科技有限公司 | Semantic analytic method, device, computer equipment and the storage medium of natural language |
| CN109509473A (en) * | 2019-01-28 | 2019-03-22 | 维沃移动通信有限公司 | Sound control method and terminal device |
| CN110517660A (en) * | 2019-08-22 | 2019-11-29 | 珠海格力电器股份有限公司 | Noise reduction method and device based on embedded Linux real-time kernel |
| CN111583909A (en) * | 2020-05-18 | 2020-08-25 | 科大讯飞股份有限公司 | Voice recognition method, device, equipment and storage medium |
| CN111899763A (en) * | 2020-07-18 | 2020-11-06 | 浙江长护信息技术有限公司 | Nursing identification and evaluation method based on audio analysis |
| CN112257415A (en) * | 2020-09-29 | 2021-01-22 | 当趣网络科技(杭州)有限公司 | Method, system, electronic device and storage medium for searching word bank by voice |
| CN114999204A (en) * | 2022-07-29 | 2022-09-02 | 北京百度网讯科技有限公司 | Navigation information processing method, device, equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020021841A1 (en) * | 2000-08-17 | 2002-02-21 | Hiroto Yoshii | Information processing method and apparatus |
| CN1604078A (en) * | 2004-08-02 | 2005-04-06 | 魏新成 | Search operation method based on single-purpose search key |
| US20080033720A1 (en) * | 2006-08-04 | 2008-02-07 | Pankaj Kankar | A method and system for speech classification |
| CN101398834A (en) * | 2007-09-29 | 2009-04-01 | 北京搜狗科技发展有限公司 | Processing method and device for input information and input method system |
| CN101404035A (en) * | 2008-11-21 | 2009-04-08 | 北京得意音通技术有限责任公司 | Information search method based on text or voice |
| CN101431573A (en) * | 2007-11-08 | 2009-05-13 | 上海赢思软件技术有限公司 | Method and equipment for implementing automatic customer service through human-machine interaction technology |
| CN101437039A (en) * | 2007-11-15 | 2009-05-20 | 华为技术有限公司 | Mobile searching method, system and equipment |
| CN101510423A (en) * | 2009-03-31 | 2009-08-19 | 李伟 | Pronunciation detection method and apparatus |
| CN102005070A (en) * | 2010-11-17 | 2011-04-06 | 广东中大讯通信息有限公司 | Voice identification gate control system |
| CN102591932A (en) * | 2011-12-23 | 2012-07-18 | 优视科技有限公司 | Voice search method, voice search system, mobile terminal and transfer server |
| CN102708859A (en) * | 2012-06-20 | 2012-10-03 | 太仓博天网络科技有限公司 | Real-time music voice identification system |
-
2012
- 2012-11-19 CN CN2012104695180A patent/CN102968987A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020021841A1 (en) * | 2000-08-17 | 2002-02-21 | Hiroto Yoshii | Information processing method and apparatus |
| CN1604078A (en) * | 2004-08-02 | 2005-04-06 | 魏新成 | Search operation method based on single-purpose search key |
| US20080033720A1 (en) * | 2006-08-04 | 2008-02-07 | Pankaj Kankar | A method and system for speech classification |
| CN101398834A (en) * | 2007-09-29 | 2009-04-01 | 北京搜狗科技发展有限公司 | Processing method and device for input information and input method system |
| CN101431573A (en) * | 2007-11-08 | 2009-05-13 | 上海赢思软件技术有限公司 | Method and equipment for implementing automatic customer service through human-machine interaction technology |
| CN101437039A (en) * | 2007-11-15 | 2009-05-20 | 华为技术有限公司 | Mobile searching method, system and equipment |
| CN101404035A (en) * | 2008-11-21 | 2009-04-08 | 北京得意音通技术有限责任公司 | Information search method based on text or voice |
| CN101510423A (en) * | 2009-03-31 | 2009-08-19 | 李伟 | Pronunciation detection method and apparatus |
| CN102005070A (en) * | 2010-11-17 | 2011-04-06 | 广东中大讯通信息有限公司 | Voice identification gate control system |
| CN102591932A (en) * | 2011-12-23 | 2012-07-18 | 优视科技有限公司 | Voice search method, voice search system, mobile terminal and transfer server |
| CN102708859A (en) * | 2012-06-20 | 2012-10-03 | 太仓博天网络科技有限公司 | Real-time music voice identification system |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103237136B (en) * | 2013-05-10 | 2016-01-20 | 上海华勤通讯技术有限公司 | The search method of mobile terminal and descriptor thereof |
| CN103237136A (en) * | 2013-05-10 | 2013-08-07 | 上海华勤通讯技术有限公司 | Mobile terminal and searching method of subject headings of mobile terminal |
| CN103634321B (en) * | 2013-12-04 | 2017-01-18 | 百度在线网络技术（北京）有限公司 | Voice recognition result display method and device |
| CN103634321A (en) * | 2013-12-04 | 2014-03-12 | 百度在线网络技术（北京）有限公司 | Voice recognition result display method and device |
| CN103811000A (en) * | 2014-02-24 | 2014-05-21 | 中国移动（深圳）有限公司 | Voice recognition system and voice recognition method |
| CN105469789A (en) * | 2014-08-15 | 2016-04-06 | 中兴通讯股份有限公司 | Voice information processing method and voice information processing terminal |
| CN104808808A (en) * | 2015-03-23 | 2015-07-29 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN104731918A (en) * | 2015-03-25 | 2015-06-24 | 百度在线网络技术（北京）有限公司 | Voice search method and device |
| CN105244024A (en) * | 2015-09-02 | 2016-01-13 | 百度在线网络技术（北京）有限公司 | Voice recognition method and device |
| CN105244024B (en) * | 2015-09-02 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | A kind of audio recognition method and device |
| CN107193829A (en) * | 2016-03-14 | 2017-09-22 | 百度在线网络技术（北京）有限公司 | Application program recommends method and apparatus |
| CN106205613A (en) * | 2016-07-22 | 2016-12-07 | 深圳智眸科技有限公司 | A kind of navigation audio recognition method and system |
| CN106205613B (en) * | 2016-07-22 | 2019-09-06 | 广州市迈图信息科技有限公司 | A kind of navigation audio recognition method and system |
| WO2018205704A1 (en) * | 2017-05-10 | 2018-11-15 | 平安科技（深圳）有限公司 | Electronic device, intelligent voice navigation method and computer readable storage medium |
| CN107170446A (en) * | 2017-05-19 | 2017-09-15 | 深圳市优必选科技有限公司 | Semantic processing server and method for semantic processing |
| CN107678309A (en) * | 2017-09-01 | 2018-02-09 | 科大讯飞股份有限公司 | Control sentence pattern generation and application control method and device and storage medium |
| CN109359295A (en) * | 2018-09-18 | 2019-02-19 | 深圳壹账通智能科技有限公司 | Semantic analytic method, device, computer equipment and the storage medium of natural language |
| WO2020057023A1 (en) * | 2018-09-18 | 2020-03-26 | 深圳壹账通智能科技有限公司 | Natural-language semantic parsing method, apparatus, computer device, and storage medium |
| CN109509473A (en) * | 2019-01-28 | 2019-03-22 | 维沃移动通信有限公司 | Sound control method and terminal device |
| CN110517660A (en) * | 2019-08-22 | 2019-11-29 | 珠海格力电器股份有限公司 | Noise reduction method and device based on embedded Linux real-time kernel |
| CN111583909A (en) * | 2020-05-18 | 2020-08-25 | 科大讯飞股份有限公司 | Voice recognition method, device, equipment and storage medium |
| CN111583909B (en) * | 2020-05-18 | 2024-04-12 | 科大讯飞股份有限公司 | Voice recognition method, device, equipment and storage medium |
| CN111899763A (en) * | 2020-07-18 | 2020-11-06 | 浙江长护信息技术有限公司 | Nursing identification and evaluation method based on audio analysis |
| CN112257415A (en) * | 2020-09-29 | 2021-01-22 | 当趣网络科技(杭州)有限公司 | Method, system, electronic device and storage medium for searching word bank by voice |
| CN114999204A (en) * | 2022-07-29 | 2022-09-02 | 北京百度网讯科技有限公司 | Navigation information processing method, device, equipment and storage medium |
| CN114999204B (en) * | 2022-07-29 | 2022-11-08 | 北京百度网讯科技有限公司 | Navigation information processing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102968987A (en) | Speech recognition method and system | |
| CN109918673B (en) | Semantic arbitration method and device, electronic equipment and computer-readable storage medium | |
| CN108829893B (en) | Method and device for determining video label, storage medium and terminal equipment | |
| CN109408622B (en) | Statement processing method, device, equipment and storage medium | |
| CN107291783B (en) | Semantic matching method and intelligent equipment | |
| US10431214B2 (en) | System and method of determining a domain and/or an action related to a natural language input | |
| US8126897B2 (en) | Unified inverted index for video passage retrieval | |
| US9330661B2 (en) | Accuracy improvement of spoken queries transcription using co-occurrence information | |
| CN111309877A (en) | Intelligent question-answering method and system based on knowledge graph | |
| US20040163035A1 (en) | Method for automatic and semi-automatic classification and clustering of non-deterministic texts | |
| US8572087B1 (en) | Content identification | |
| US11829433B2 (en) | Contextual deep bookmarking | |
| CN106708929B (en) | Video program searching method and device | |
| CN111522909B (en) | Voice interaction method and server | |
| CN108038099B (en) | Low-frequency keyword identification method based on word clustering | |
| CN113806588B (en) | Method and device for searching video | |
| CN111160007B (en) | Search method and device based on BERT language model, computer equipment and storage medium | |
| CN114021577A (en) | Content tag generation method and device, electronic equipment and storage medium | |
| CN111291168A (en) | Book retrieval method and device and readable storage medium | |
| CN117909560A (en) | Search method, training device, training equipment, training medium and training program product | |
| CN113779364A (en) | Searching method based on label extraction and related equipment thereof | |
| CN114742062B (en) | Text keyword extraction processing method and system | |
| US11748405B2 (en) | Method and apparatus for presenting search results | |
| CN113553851A (en) | Keyword determination method and device, storage medium and computing equipment | |
| JPH11272709A (en) | File retrieval system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130313 |
|
| RJ01 | Rejection of invention patent application after publication |