CN110265010A - The recognition methods of lorry multi-person speech and system based on Baidu's voice - Google Patents
The recognition methods of lorry multi-person speech and system based on Baidu's voice Download PDFInfo
- Publication number
- CN110265010A CN110265010A CN201910488028.7A CN201910488028A CN110265010A CN 110265010 A CN110265010 A CN 110265010A CN 201910488028 A CN201910488028 A CN 201910488028A CN 110265010 A CN110265010 A CN 110265010A
- Authority
- CN
- China
- Prior art keywords
- keyword
- audio
- frequency information
- business scenario
- frequency
- 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
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Processing of the speech or voice signal to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
Abstract
The invention discloses a kind of recognition methods of lorry multi-person speech and system based on Baidu's voice, this method comprises the following steps: acquisition audio-frequency information；Identify collected audio-frequency information；Keyword in the semantic content and semantic base of the audio-frequency information that will identify that is associated pairing；The keyword of successful matching is associated with preset business scenario and is matched；The business scenario that association is matched to is pushed to user interface.The present invention handles the backstage of voice scene, pre-defines the various businesses scene of truck man, quickly can be matched to corresponding scene for truck man, avoid repetitive operation, improve travel safety；It supports more people's complexity voice scenes, noise reduction process can be carried out automatically, improve speech recognition effect；Bottom speech recognition and parsing are done using free Baidu's voice, reduce economic cost for driver.
Description
Technical field
The present invention relates to technical field of voice recognition, especially a kind of lorry multi-person speech identification side based on Baidu's voice
Method and system.
Background technique
As the corresponding city of the prosperity of the industries such as electric business, new retail trade has also welcome hair at full speed with logistic industry
Exhibition.For truck man safe driving, it is a set of meet city with lorry speech recognition system it is extremely urgent.And the core of voice system
The heart is voice technology.General voice operating software or technology can only meet basic speech recognition semantic parsing operation,
Do not meet the needs of this special population of truck man, and lorry delivery is not often a people, there are also the personnel such as carry
Together.Therefore under multi-person speech environment, the operation that can accurately identify driver is intended to, and reduces frequently multiple voice operating, increase department
Machine driving interest, it is extremely important to improve travel safety.Traditional multi-person speech processing only simply identifies lorry department
The voice of machine inputs, and cannot but process to the voice scene of input.
Summary of the invention
To solve problems of the prior art, the present invention provides a kind of lorry multi-person speech based on Baidu's voice
Recognition methods and system, speech recognition is quick, supports more people's complexity voice scenes, handles the backstage of voice scene, can
It quickly is matched to corresponding scene for truck man, avoids repetitive operation, improves travel safety.
The technical solution adopted by the present invention is that:
A kind of lorry multi-person speech recognition methods based on Baidu's voice, includes the following steps:
S1, acquisition audio-frequency information；
S2, the collected audio-frequency information of identification enter step S1 if not can recognize that audio-frequency information, if identification
Audio-frequency information out then enters step S3；
S3, the audio-frequency information that will identify that semantic content and semantic base in keyword be associated pairing, if matched
To success, then enter step S4, if pairing failure, judge the audio-frequency information whether simultaneously include environmental audio information with use
Family audio-frequency information, if it is, entering step S2；If it is not, then push re-enters audio-frequency information to user interface, into step
Rapid S1；
S4, it the keyword of successful matching is associated with preset business scenario matches；
S5, the business scenario that association is matched to is pushed to user interface.
Further, step S4 includes the following steps:
S41, judge whether the quantity of matched keyword is greater than 1, if it is, entering step S42；If it is not, then root
Corresponding business scenario is matched according to the association of preset business scenario；
The frequency that S42, each keyword of statistics occur；
S43, the frequency occurred according to keyword, the highest keyword of the frequency of occurrences is closed with preset business scenario
Lump is matched.
Further, further include following steps in step S4:
S44, judge whether the matched keyword of association is folded word, if it is, entering step S45；If it is not, then into
Step S41；
S45, the word repeated in keyword is deleted, generates new keyword；
S46, it is associated and is matched with preset business scenario according to new keyword.
A kind of lorry multi-person speech identifying system based on Baidu's voice, including audio-frequency information acquisition module, audio-frequency information
Identification module, keyword matching module, business scenario relating module and business scenario pushing module, in which:
Audio-frequency information acquisition module, for acquiring audio-frequency information；
Audio-frequency information identification module, collected audio-frequency information for identification, if not can recognize that audio-frequency information, sound
The work of frequency information acquisition module, if identifying audio-frequency information, the work of keyword matching module；
Keyword matching module is carried out for the keyword in the semantic content and semantic base of the audio-frequency information that will identify that
Association pairing, if successful matching, business scenario relating module work, if pairing failure, judges that the audio-frequency information is
It is not no while including environmental audio information and audio user information, if it is, audio-frequency information identification module works；If it is not, then
Push re-enters audio-frequency information to user interface, the work of audio-frequency information acquisition module；
Business scenario relating module is matched for the keyword of successful matching to be associated with preset business scenario；
Business scenario pushing module, the business scenario for association to be matched to are pushed to user interface.
Further, the business scenario relating module includes keyword quantity judging submodule, keyword frequency statistics
Submodule is associated with submodule with business scenario, in which:
Keyword quantity judging submodule, for judging whether the quantity of matched keyword is greater than 1, if it is, closing
The work of keyword frequency statistics submodule；If it is not, then matching corresponding business scenario according to the association of preset business scenario；
Keyword frequency statistics submodule, the frequency occurred for counting each keyword；
Business scenario be associated with submodule, the frequency for being occurred according to keyword, by the highest keyword of the frequency of occurrences with
Preset business scenario is associated matching.
Further, the business scenario relating module further includes folded word keyword judging submodule, new keywords generation
Submodule is associated with submodule with new keywords, in which:
Folded word keyword judging submodule, for judging whether the matched keyword of association is folded word, if it is, new close
Keyword generates submodule work；If it is not, then keyword quantity judging submodule works；
New keywords generate submodule and generate new keyword for deleting the word repeated in keyword；
New keywords are associated with submodule, match for being associated according to new keyword with preset business scenario.
The beneficial effects of the present invention are:
1, the backstage of voice scene is handled, quickly can be matched to corresponding scene for truck man, avoids repeating
Operation improves travel safety.
2, more people's complexity voice scenes are supported, noise reduction process can be carried out automatically, improve speech recognition effect.
3, bottom speech recognition and parsing are done using free Baidu's voice, reduces economic cost for driver.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the lorry multi-person speech recognition methods based on Baidu's voice of the embodiment of the present invention；
Fig. 2 is keyword and business in a kind of lorry multi-person speech recognition methods based on Baidu's voice of the embodiment of the present invention
The flow chart of scene matching；
Fig. 3 is new keywords and industry in a kind of lorry multi-person speech recognition methods based on Baidu's voice of the embodiment of the present invention
The flow chart of business scene matching；
Fig. 4 is a kind of schematic diagram of the lorry multi-person speech identifying system based on Baidu's voice of the embodiment of the present invention.
Appended drawing reference: 10, audio-frequency information acquisition module；20, audio-frequency information identification module；30, keyword matching module；
40, business scenario relating module；401, keyword quantity judging submodule；402, keyword frequency statistics submodule；403, industry
Business scene relating submodule；404, word keyword judging submodule is folded；405, new keywords generate submodule；406, new keywords
It is associated with submodule；50, business scenario pushing module.
Specific embodiment
The embodiment of the present invention is described in detail with reference to the accompanying drawing.
Embodiment
As shown in Figure 1-Figure 3, a kind of lorry multi-person speech recognition methods based on Baidu's voice, includes the following steps:
S1, acquisition audio-frequency information；The audio-frequency information of user is acquired by audio-frequency information acquisition module 10.
S2, the collected audio-frequency information of identification enter step S1 if not can recognize that audio-frequency information, if identification
Audio-frequency information out then enters step S3.
S3, the audio-frequency information that will identify that semantic content and semantic base in keyword be associated pairing, if matched
To success, then enter step S4, if pairing failure, judge the audio-frequency information whether simultaneously include environmental audio information with use
Family audio-frequency information, if it is, entering step S2；If it is not, then push re-enters audio-frequency information to user interface, into step
Rapid S1.
If voice recognition terminal is in noisy environment, that is, there are more people while speaking, voice terminal is to owner around
One's voice in speech is acquired and identifies, causes the semantic content identified chaotic, can not identify the true meaning of user
Figure, can not be matched with the keyword in semantic base, i.e., include the user that truck man issues in collected audio-frequency information
The environment noisy audio information that other people issue in audio-frequency information and ambient enviroment, and the voltage magnitude of audio user information
The minimum voltage amplitude that voice recognition terminal can identify is all larger than with the voltage magnitude of environment noisy audio information.Therefore, needle
After carrying out speech recognition to the audio-frequency information, the semantic content identified is likely to mismatch with the content in semantic base, can not
It is correctly responded, if it fails to match, judges whether the audio-frequency information includes environment noisy audio information and audio user
Information, if the audio-frequency information includes environment noisy audio information and audio user information, when according to acquisition audio-frequency information
The input volume of the audio-frequency information and the voltage magnitude for acquiring audio-frequency information determine the item for identifying audio-frequency information next time
Part, return step S2 start speech recognition process next time；If the audio-frequency information does not include environment noisy audio information,
It then prompts user to re-enter audio-frequency information, and return step S1, resurveys audio user information.
S4, it the keyword of successful matching is associated with preset business scenario matches；Backstage pre-defines lorry
The various businesses scene of driver, such as map, make a phone call, check or send information or open some other APP, according to language
The keyword that the semantic content that sound identifies is matched to is transmitted to backstage by AI and matches corresponding business scenario.
S5, the business scenario that association is matched to is pushed to user interface.Under normal circumstances, driver can only operate simultaneously
One scene, thus backstage be matched to only one scene after, be returned to concrete scene to user, execute the next step of the scene
Logic.If being matched to multiple keywords, keyword often is returned to by user according to the frequency that keyword occurs, or
There is folded word, such as open ground Map, or opening Map figure etc. deletes the word repeated in keyword, generates new
Keyword returns to user；It is associated and is matched with preset business scenario according to new keyword.
The backstage of voice scene is handled, the various businesses scene of truck man is pre-defined, such as map beats electricity
Talk about, check or send information or open some other APP etc., it quickly can be matched to corresponding scene for truck man, kept away
Exempt from repetitive operation, improves travel safety；It supports more people's complexity voice scenes, noise reduction process can be carried out automatically, improve voice and know
Other effect；Bottom speech recognition and parsing are done using free Baidu's voice, reduce economic cost for driver.
In one of the embodiments, as shown in Fig. 2, step S4, includes the following steps:
S41, judge whether the quantity of matched keyword is greater than 1, if it is, entering step S42；If it is not, then root
Corresponding business scenario is matched according to the association of preset business scenario；
The frequency that S42, each keyword of statistics occur；
S43, the frequency occurred according to keyword, the highest keyword of the frequency of occurrences is closed with preset business scenario
Lump is matched.
In one of the embodiments, as shown in figure 3, further including following steps in step S4:
S44, judge whether the matched keyword of association is folded word, if it is, entering step S45；If it is not, then into
Step S41；
S45, the word repeated in keyword is deleted, generates new keyword；
S46, it is associated and is matched with preset business scenario according to new keyword.
As shown in figure 4, a kind of lorry multi-person speech identifying system based on Baidu's voice, including audio-frequency information acquisition module
10, audio-frequency information identification module 20, keyword matching module 30, business scenario relating module 40 and business scenario pushing module
50, in which:
Audio-frequency information acquisition module 10, for acquiring audio-frequency information；
Audio-frequency information identification module 20, collected audio-frequency information for identification, if not can recognize that audio-frequency information,
Audio-frequency information acquisition module 10 works, if identifying audio-frequency information, keyword matching module 30 works.
Keyword matching module 30, for the keyword in the semantic content and semantic base of the audio-frequency information that will identify that into
Row association pairing, if successful matching, business scenario relating module 40 works, if pairing failure, judges the audio letter
Whether breath includes environmental audio information and audio user information simultaneously, if it is, audio-frequency information identification module 20 works；If
No, then push re-enters audio-frequency information to user interface, and audio-frequency information acquisition module 10 works；
If voice recognition terminal is in noisy environment, that is, there are more people while speaking, voice terminal is to owner around
One's voice in speech is acquired and identifies, causes the semantic content identified chaotic, can not identify the true meaning of user
Figure, can not be matched with the keyword in semantic base, i.e., include the user that truck man issues in collected audio-frequency information
The environment noisy audio information that other people issue in audio-frequency information and ambient enviroment, and the voltage magnitude of audio user information
The minimum voltage amplitude that voice recognition terminal can identify is all larger than with the voltage magnitude of environment noisy audio information.Therefore, needle
After carrying out speech recognition to the audio-frequency information, the semantic content identified is likely to mismatch with the content in semantic base, can not
It is correctly responded, if it fails to match, judges whether the audio-frequency information includes environment noisy audio information and audio user
Information, if the audio-frequency information includes environment noisy audio information and audio user information, when according to acquisition audio-frequency information
The input volume of the audio-frequency information and the voltage magnitude for acquiring audio-frequency information determine the item for identifying audio-frequency information next time
Part starts speech recognition process next time；If the audio-frequency information does not include environment noisy audio information, user's weight is prompted
New input audio information, resurveys audio user information.
A business scenario relating module 40, for the keyword of successful matching and preset business scenario to be associated
Match；Backstage pre-defines the various businesses scene of truck man, and information or opening are made a phone call, check or sent to such as map
Some other APP etc. is transmitted to backstage and is matched by AI according to the keyword that the semantic content that speech recognition comes out is matched to
Corresponding business scenario.
Business scenario pushing module 50, the business scenario for association to be matched to are pushed to user interface.In positive reason
Under condition, after driver can only operate a scene simultaneously, therefore backstage is matched to only one scene, concrete scene is returned to use
Family executes the next step logic of the scene.It, will often according to the frequency that keyword occurs if be matched to multiple keywords
The corresponding business scenario of keyword returns to user, or folded word occurs, such as opens ground Map, or open Map figure
Deng deleting the word that repeats in keyword, generates new keyword and return to user；According to new keyword and preset industry
Business scene is associated matching.
In one of the embodiments, as shown in figure 4, the business scenario relating module 40 judges including keyword quantity
Submodule 401, keyword frequency statistics submodule 402 are associated with submodule 403 with business scenario, in which:
Keyword quantity judging submodule 401, for judging whether the quantity of matched keyword is greater than 1, if it is,
Keyword frequency statistics submodule 402 works；If it is not, then matching corresponding business field according to the association of preset business scenario
Scape；
Keyword frequency statistics submodule 402, the frequency occurred for counting each keyword；
Business scenario is associated with submodule 403, the frequency for occurring according to keyword, by the highest keyword of the frequency of occurrences
It is associated and matches with preset business scenario.
In one of the embodiments, as shown in figure 4, the business scenario relating module 40 further includes that folded word keyword is sentenced
Disconnected submodule 404, new keywords generate submodule 405 and are associated with submodule 406 with new keywords, in which:
Folded word keyword judging submodule 404, for judging whether the matched keyword of association is folded word, if it is,
New keywords generate submodule 405 and work；If it is not, then keyword quantity judging submodule 401 works；
New keywords generate submodule 405 and generate new keyword for deleting the word repeated in keyword；
New keywords are associated with submodule 406, match for being associated according to new keyword with preset business scenario.
A specific embodiment of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, it can also make such as dried fruit modification and improvement, these belong to of the invention
Protection scope.
Claims (6)
1. a kind of lorry multi-person speech recognition methods based on Baidu's voice, which comprises the steps of:
S1, acquisition audio-frequency information；
S2, the collected audio-frequency information of identification enter step S1 if not can recognize that audio-frequency information, if identifying sound
Frequency information, then enter step S3；
S3, the audio-frequency information that will identify that semantic content and semantic base in keyword be associated pairing, if be paired into
Function then enters step S4, if pairing failure, judges whether the audio-frequency information includes environmental audio information and user's sound simultaneously
Frequency information, if it is, entering step S2；If it is not, then push re-enters audio-frequency information to user interface, enter step
S1；
S4, it the keyword of successful matching is associated with preset business scenario matches；
S5, the business scenario that association is matched to is pushed to user interface.
2. the lorry multi-person speech recognition methods according to claim 1 based on Baidu's voice, which is characterized in that step
S4 includes the following steps:
S41, judge whether the quantity of matched keyword is greater than 1, if it is, entering step S42；If it is not, then according to pre-
If business scenario association match corresponding business scenario；
The frequency that S42, each keyword of statistics occur；
The highest keyword of the frequency of occurrences and preset business scenario are associated by S43, the frequency occurred according to keyword
Match.
3. the lorry multi-person speech recognition methods according to claim 2 based on Baidu's voice, which is characterized in that step S4
In, further include following steps:
S44, judge whether the matched keyword of association is folded word, if it is, entering step S45；If it is not, then entering step
S41；
S45, the word repeated in keyword is deleted, generates new keyword；
S46, it is associated and is matched with preset business scenario according to new keyword.
4. a kind of lorry multi-person speech identifying system based on Baidu's voice, which is characterized in that including audio-frequency information acquisition module,
Audio-frequency information identification module, keyword matching module, business scenario relating module and business scenario pushing module, in which:
Audio-frequency information acquisition module, for acquiring audio-frequency information；
Audio-frequency information identification module, collected audio-frequency information for identification, if not can recognize that audio-frequency information, audio letter
Acquisition module work is ceased, if identifying audio-frequency information, the work of keyword matching module；
Keyword matching module is associated for the keyword in the semantic content and semantic base of the audio-frequency information that will identify that
Pairing, if successful matching, business scenario relating module work, if pairing failure, judges whether the audio-frequency information is same
When include environmental audio information and audio user information, if it is, audio-frequency information identification module works；If it is not, then push
Audio-frequency information is re-entered to user interface, the work of audio-frequency information acquisition module；
Business scenario relating module is matched for the keyword of successful matching to be associated with preset business scenario；
Business scenario pushing module, the business scenario for association to be matched to are pushed to user interface.
5. the lorry multi-person speech identifying system according to claim 4 based on Baidu's voice, which is characterized in that the industry
Business scene relating module includes that keyword quantity judging submodule, keyword frequency statistics submodule with business scenario are associated with submodule
Block, in which:
Keyword quantity judging submodule, for judging whether the quantity of matched keyword is greater than 1, if it is, keyword
The work of frequency statistics submodule；If it is not, then matching corresponding business scenario according to the association of preset business scenario；
Keyword frequency statistics submodule, the frequency occurred for counting each keyword；
Business scenario is associated with submodule, and the frequency for being occurred according to keyword by the highest keyword of the frequency of occurrences and is preset
Business scenario be associated matching.
6. the lorry multi-person speech identifying system according to claim 5 based on Baidu's voice, which is characterized in that the industry
Business scene relating module further includes folding word keyword judging submodule, new keywords generation submodule to be associated with submodule with new keywords
Block, in which:
Folded word keyword judging submodule, for judging whether the matched keyword of association is folded word, if it is, new keywords
Generate submodule work；If it is not, then keyword quantity judging submodule works；
New keywords generate submodule and generate new keyword for deleting the word repeated in keyword；
New keywords are associated with submodule, match for being associated according to new keyword with preset business scenario.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910488028.7A CN110265010A (en) | 2019-06-05 | 2019-06-05 | The recognition methods of lorry multi-person speech and system based on Baidu's voice |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910488028.7A CN110265010A (en) | 2019-06-05 | 2019-06-05 | The recognition methods of lorry multi-person speech and system based on Baidu's voice |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110265010A true CN110265010A (en) | 2019-09-20 |
Family
ID=67917022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910488028.7A Pending CN110265010A (en) | 2019-06-05 | 2019-06-05 | The recognition methods of lorry multi-person speech and system based on Baidu's voice |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110265010A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113779201A (en) * | 2021-09-16 | 2021-12-10 | 北京百度网讯科技有限公司 | Method and device for recognizing instruction and voice interaction screen |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101309327A (en) * | 2007-04-16 | 2008-11-19 | 索尼株式会社 | Sound chat system, information processing device, speech recognition and key words detectiion |
| CN105244029A (en) * | 2015-08-28 | 2016-01-13 | 科大讯飞股份有限公司 | Voice recognition post-processing method and system |
| CN106847269A (en) * | 2017-01-20 | 2017-06-13 | 浙江小尤鱼智能技术有限公司 | The sound control method and device of a kind of intelligent domestic system |
| CN107274895A (en) * | 2017-08-18 | 2017-10-20 | 京东方科技集团股份有限公司 | A kind of speech recognition apparatus and method |
| CN107949880A (en) * | 2015-09-09 | 2018-04-20 | 三菱电机株式会社 | Vehicle-mounted speech recognition equipment and mobile unit |
| CN108630202A (en) * | 2017-03-21 | 2018-10-09 | 株式会社东芝 | Speech recognition equipment, audio recognition method and speech recognition program |
| CN109120501A (en) * | 2017-06-26 | 2019-01-01 | 上海博泰悦臻网络技术服务有限公司 | Automatic scene method of servicing and system based on car-mounted terminal communication program |
| CN109145281A (en) * | 2017-06-15 | 2019-01-04 | 北京嘀嘀无限科技发展有限公司 | Audio recognition method, device and storage medium |
| CN109213856A (en) * | 2018-10-22 | 2019-01-15 | 广东小天才科技有限公司 | A kind of method for recognizing semantics and system |
| CN109243461A (en) * | 2018-09-21 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | Audio recognition method, device, equipment and storage medium |
| CN109360552A (en) * | 2018-11-19 | 2019-02-19 | 广东小天才科技有限公司 | A kind of automatic fitration wakes up the method and system of word |
| CN109473100A (en) * | 2018-11-12 | 2019-03-15 | 四川驹马科技有限公司 | Business scenario voice man-machine interaction method and its system based on speech recognition |
| CN208675495U (en) * | 2018-07-04 | 2019-03-29 | 上海博泰悦臻网络技术服务有限公司 | The playback equipment that vehicle and its multimedia automatically control |
-
2019
- 2019-06-05 CN CN201910488028.7A patent/CN110265010A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101309327A (en) * | 2007-04-16 | 2008-11-19 | 索尼株式会社 | Sound chat system, information processing device, speech recognition and key words detectiion |
| CN105244029A (en) * | 2015-08-28 | 2016-01-13 | 科大讯飞股份有限公司 | Voice recognition post-processing method and system |
| CN107949880A (en) * | 2015-09-09 | 2018-04-20 | 三菱电机株式会社 | Vehicle-mounted speech recognition equipment and mobile unit |
| CN106847269A (en) * | 2017-01-20 | 2017-06-13 | 浙江小尤鱼智能技术有限公司 | The sound control method and device of a kind of intelligent domestic system |
| CN108630202A (en) * | 2017-03-21 | 2018-10-09 | 株式会社东芝 | Speech recognition equipment, audio recognition method and speech recognition program |
| CN109145281A (en) * | 2017-06-15 | 2019-01-04 | 北京嘀嘀无限科技发展有限公司 | Audio recognition method, device and storage medium |
| CN109120501A (en) * | 2017-06-26 | 2019-01-01 | 上海博泰悦臻网络技术服务有限公司 | Automatic scene method of servicing and system based on car-mounted terminal communication program |
| CN107274895A (en) * | 2017-08-18 | 2017-10-20 | 京东方科技集团股份有限公司 | A kind of speech recognition apparatus and method |
| CN208675495U (en) * | 2018-07-04 | 2019-03-29 | 上海博泰悦臻网络技术服务有限公司 | The playback equipment that vehicle and its multimedia automatically control |
| CN109243461A (en) * | 2018-09-21 | 2019-01-18 | 百度在线网络技术（北京）有限公司 | Audio recognition method, device, equipment and storage medium |
| CN109213856A (en) * | 2018-10-22 | 2019-01-15 | 广东小天才科技有限公司 | A kind of method for recognizing semantics and system |
| CN109473100A (en) * | 2018-11-12 | 2019-03-15 | 四川驹马科技有限公司 | Business scenario voice man-machine interaction method and its system based on speech recognition |
| CN109360552A (en) * | 2018-11-19 | 2019-02-19 | 广东小天才科技有限公司 | A kind of automatic fitration wakes up the method and system of word |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113779201A (en) * | 2021-09-16 | 2021-12-10 | 北京百度网讯科技有限公司 | Method and device for recognizing instruction and voice interaction screen |
| CN113779201B (en) * | 2021-09-16 | 2023-06-30 | 北京百度网讯科技有限公司 | Method and device for identifying instruction and voice interaction screen |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111488433B (en) | Artificial intelligence interactive system suitable for bank and capable of improving field experience | |
| KR101872863B1 (en) | Business support method using a chatting bot | |
| CN107705807B (en) | Voice quality detecting method, device, equipment and storage medium based on Emotion identification | |
| CN106790004B (en) | Customer service auxiliary real-time prompt system based on artificial intelligence | |
| CN106230689B (en) | A kind of method, apparatus and server of voice messaging interaction | |
| CN106406806A (en) | A control method and device for intelligent apparatuses | |
| CN104715047B (en) | A kind of social network data collection and analysis system | |
| CN109388701A (en) | Minutes generation method, device, equipment and computer storage medium | |
| CN108416041B (en) | Voice log analysis method and system | |
| CN109922213A (en) | Data processing method, device, storage medium and terminal device when voice is seeked advice from | |
| CN108074571A (en) | Sound control method, system and the storage medium of augmented reality equipment | |
| CN111128241A (en) | Intelligent quality inspection method and system for voice call | |
| CN107644106A (en) | The internuncial method of automatic mining business, terminal device and storage medium | |
| CN112364622A (en) | Dialog text analysis method, dialog text analysis device, electronic device and storage medium | |
| CN110265010A (en) | The recognition methods of lorry multi-person speech and system based on Baidu's voice | |
| CN114786035A (en) | Compliance quality inspection and interactive question-answering system and method for live scene | |
| CN113593565B (en) | Intelligent home device management and control method and system | |
| CN113542509B (en) | Emergency processing method, device, storage medium and equipment | |
| CN109325155A (en) | A kind of novel dialogue state storage method and system | |
| CN112036820B (en) | Method, system, storage medium and equipment for processing information feedback in enterprise | |
| CN111938674A (en) | Emotion recognition control system for conversation | |
| CN114254088A (en) | Method for constructing automatic response model and automatic response method | |
| CN113704430A (en) | Intelligent auxiliary receiving method and device, electronic equipment and storage medium | |
| CN112767933A (en) | Voice interaction method, device, equipment and medium for highway maintenance management system | |
| CN111881272A (en) | Real-time early warning system and method for telephone service |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190920 |