CN106847291A - Speech recognition system and method that a kind of local and high in the clouds is combined - Google Patents
Speech recognition system and method that a kind of local and high in the clouds is combined Download PDFInfo
- Publication number
- CN106847291A CN106847291A CN201710091103.7A CN201710091103A CN106847291A CN 106847291 A CN106847291 A CN 106847291A CN 201710091103 A CN201710091103 A CN 201710091103A CN 106847291 A CN106847291 A CN 106847291A
- Authority
- CN
- China
- Prior art keywords
- local
- voice
- clouds
- speech recognition
- recognition
- 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 12
- 230000005540 biological transmission Effects 0.000 claims abstract description 6
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention relates to field of speech recognition,Especially relate to the speech recognition system that a kind of local and high in the clouds is combined,The system includes that local voice recognizes module,WIFI modules and high in the clouds speech recognition server,Local voice identification module carries out speech signal collection and recognition of speech signals obtains local voice recognition result and identification score,WIFI modules transmission of speech signals is to high in the clouds speech recognition server,High in the clouds speech recognition server is identified to voice signal and obtains online voice identification result,The online voice identification result that high in the clouds speech recognition server will be obtained is transferred to local voice and recognizes module by WIFI modules,The invention also discloses the audio recognition method that a kind of local and high in the clouds is combined,The method that the present invention is combined using local and high in the clouds,User is realized freely to talk online,And possess the characteristics of fast response time and simple control.
Description
Technical field
The present invention relates to field of speech recognition, the speech recognition system that a kind of local and high in the clouds is combined is especially related to
And method.
Background technology
Current speech recognition is widely used in each electronic product as a kind of conventional human-computer interaction technology, with
Its naturally convenient interactive mode have received liking for consumer, be increasingly becoming the main flow interactive controlling side in intelligent artifact epoch
Formula, speech recognition has two class modes at present, and a class is online free intercommunication mode, can arbitrarily be talked when user uses, by
Product facility collects user's speech content, and uploading to cloud server by equipment such as WIFI modules carries out semantic analysis reason
Solution, parses the purpose of user, then is passed to by network corresponding operational control is carried out in product facility, and this mode advantage exists
Can freely be talked in user, relatively daily life custom, but disadvantage is that network could be used；It is another kind of
The mode of speech recognition is the identification of the local voice control command word carried out by local identification module, and such mode need not make
With network, with fast response time, the advantages of control simple, but needs have been previously set voice control command word, product facility
Can just be responded after complete voice control command word need to be recognized, it is impossible to realize free intercommunication, experience sense is not high.
To solve the above problems, it is necessary to inventing one kind can realize that user freely talks online, but also with fast response time
The speech recognition system and method being combined with the simple local and high in the clouds of control.
The content of the invention
It is an object of the invention to overcome the above-mentioned deficiency in the presence of prior art, there is provided one kind can carry out online freedom
Talk and fast response time control speech recognition system and method that simply local and high in the clouds is combined.
In order to achieve the above object, the invention provides following technical scheme：
The speech recognition system that a kind of local and high in the clouds is combined, it includes：Local voice recognizes module and the local voice
The high in the clouds speech-recognition services that the WIFI modules and the WIFI modules that identification module carries out data transmission carry out data transmission
Device.
Used as preferred scheme of the invention, the local voice identification module carries out speech signal collection and recognizes institute's predicate
Message number obtains local voice recognition result and identification score, and the height of score characterizes the accurate journey of local voice recognition result
Degree, the WIFI modules transmit the voice signal to the high in the clouds speech recognition server, the high in the clouds speech-recognition services
Device is identified to the voice signal and obtains online voice identification result, and the high in the clouds speech recognition server will be obtained
The online voice identification result is transferred to the local voice and recognizes module by the WIFI modules, and the local voice is known
Other module carries out logic judgment to determine the voice identification result of final output.
Preferably, present invention definition score correspondence order of accuarcy high is high, and the score low correspondence degree of accuracy is low, if instead
Come over to define also may be used.
Present invention also offers following technical scheme：
The audio recognition method that a kind of local and high in the clouds is combined, it is comprised the following steps：
Step one local voice identification module collection voice signal simultaneously recognizes that the voice signal obtains local voice recognition result
With local voice recognition result score；
Step 2 determines whether network, if without network or network signal difference when if directly using the local voice recognize knot
Fruit simultaneously enters last step, and next step is entered if having network；
Step 3 WIFI modules send the voice signal to high in the clouds speech recognition server, the high in the clouds speech-recognition services
Device analyzes the voice signal and obtains online voice identification result；
By the WIFI modules be transferred to the online voice identification result by high in the clouds speech recognition server described in step 4
The local voice recognizes module；
Local voice identification module is compared the local voice recognition result score with the threshold value of a setting described in step 5
Compared with, the local voice recognition result is chosen if the local voice recognition result score is greater than or equal to the threshold value, if
The local voice recognition result score then chooses the online voice identification result less than the threshold value, and the threshold value is according to setting
Meter demand is set；
Step 6 exports the selection result of the step 5.
Compared with prior art, beneficial effects of the present invention：
The method that the present invention is combined using local and high in the clouds, realizes user and freely talks online, and possess response speed
The characteristics of fast and simple control.
Brief description of the drawings
Fig. 1 is frame diagram of the present invention；
Fig. 2 is flow chart of the present invention.
Specific embodiment
With reference to embodiment and specific embodiment, the present invention is described in further detail, but should not understand this
For the scope of aforementioned body of the present invention is only limitted to following embodiment, all technologies realized based on present invention belong to this
The scope of invention.
Embodiment 1
As shown in figure 1, the speech recognition system that a kind of local and high in the clouds is combined, the system include local voice recognize module,
WIFI modules and high in the clouds speech recognition server, local voice identification module carries out speech signal collection and recognition of speech signals is obtained
Local voice recognition result and score are obtained, WIFI modules transmission of speech signals to high in the clouds speech recognition server, high in the clouds voice is known
Other server is identified to voice signal and obtains online voice identification result, and high in the clouds speech recognition server will be obtained
Line voice identification result is transferred to local voice and recognizes module by WIFI modules, and WIFI modules are general modules, it is adaptable to moved
Dynamic, telecommunications and UNICOM etc., local voice identification module is using microphone collection voice signal in the present embodiment.
Embodiment 2
As shown in Fig. 2 the audio recognition method that a kind of local and high in the clouds is combined, it includes following six step：
Step one local voice identification module collection voice signal and recognition of speech signals obtain local voice recognition result and this
Ground voice identification result score, local voice identification module collection " opening machine " this voice signal in the present embodiment；
Step 2 determines whether network, if without network or network signal difference when if directly using local voice recognition result simultaneously
Last step is directly entered, next step is entered if having network；
Step 3 WIFI modules send voice signal to high in the clouds speech recognition server, high in the clouds speech recognition server analytic language
Message number obtains online voice identification result；
Online voice identification result is transferred to local voice and recognized by step 4 high in the clouds speech recognition server by WIFI modules
Module；
Step 5 local voice recognizes that with the threshold value of a setting be compared local voice recognition result score by module, if this
Ground voice identification result score then chooses local voice recognition result greater than or equal to threshold value, if local voice recognition result score
Online voice identification result is then chosen less than threshold value；
Step 6 exports the selection result of step 5, final output " opening machine " this phonetic order.
In the present embodiment, the machine in " opening machine " phonetic order can be all home electrics, such as TV, sky
Tune, computer, washing machine, micro-wave oven etc., can directly control the various electric equipments in family, when the part verbal of user surpasses
When going out to set entry scope, such as " I will go to Shanghai " etc., the local voice recognition result score of local identification module will be less than
Given threshold, the then result that the Systematic selection is returned from high in the clouds speech recognition server.
In other embodiments, the method may be directly applied to certain electrical equipment, such as be applied in voice audio amplifier,
It is that local voice recognizes entry to define the order word such as " volume is a little bigger ", " volume dot ", " next song ", if local voice is known
Other result score then illustrates that entry to be identified is included in above-mentioned local voice identification entry greater than or equal to set threshold value
In the range of, and recognize well, then using local recognition result, quick control response is carried out, if local voice identification knot
Fruit score less than set threshold value, then illustrate entry to be identified be not included in the range of above-mentioned local voice identification entry or
Person's identification certainty is not high, then selection comes from high in the clouds recognition result.
Claims (3)
1. the speech recognition system that a kind of local and high in the clouds is combined, it includes：Local voice recognizes module and the local language
The high in the clouds speech-recognition services that the WIFI modules and the WIFI modules that sound identification module carries out data transmission carry out data transmission
Device.
2. the speech recognition system that a kind of local and high in the clouds according to claim 1 is combined, it is characterised in that：Described
Ground speech recognition module carries out speech signal collection and recognizes that the voice signal obtains local voice recognition result and recognizes
Point, the WIFI modules transmit the voice signal to the high in the clouds speech recognition server, the high in the clouds speech-recognition services
Device is identified to the voice signal and obtains online voice identification result, and the high in the clouds speech recognition server will be obtained
The online voice identification result is transferred to the local voice and recognizes module by the WIFI modules.
3. the audio recognition method that a kind of local and high in the clouds is combined, it is comprised the following steps：
Step one local voice identification module collection voice signal simultaneously recognizes that the voice signal obtains local voice recognition result
With local voice recognition result score；
Step 2 determines whether network, if without network or network signal difference when if directly using the local voice recognize knot
Fruit is simultaneously directly entered last step, and next step is entered if having network；
Step 3 WIFI modules send the voice signal to high in the clouds speech recognition server, the high in the clouds speech-recognition services
Device analyzes the voice signal and obtains online voice identification result；
By the WIFI modules be transferred to the online voice identification result by high in the clouds speech recognition server described in step 4
The local voice recognizes module；
Local voice identification module is compared the local voice recognition result score with the threshold value of a setting described in step 5
Compared with, the local voice recognition result is chosen if the local voice recognition result score is greater than or equal to the threshold value, if
The local voice identification score then chooses the online voice identification result less than the threshold value；
Step 6 exports the selection result of the step 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710091103.7A CN106847291A (en) | 2017-02-20 | 2017-02-20 | Speech recognition system and method that a kind of local and high in the clouds is combined |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710091103.7A CN106847291A (en) | 2017-02-20 | 2017-02-20 | Speech recognition system and method that a kind of local and high in the clouds is combined |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106847291A true CN106847291A (en) | 2017-06-13 |
Family
ID=59128920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710091103.7A Pending CN106847291A (en) | 2017-02-20 | 2017-02-20 | Speech recognition system and method that a kind of local and high in the clouds is combined |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106847291A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146617A (en) * | 2017-06-15 | 2017-09-08 | 成都启英泰伦科技有限公司 | A kind of novel voice identification equipment and method |
| CN107909715A (en) * | 2017-09-29 | 2018-04-13 | 嘉兴川森智能科技有限公司 | Speech recognition system and method in automatic vending machine |
| CN108806682A (en) * | 2018-06-12 | 2018-11-13 | 奇瑞汽车股份有限公司 | The method and apparatus for obtaining Weather information |
| CN109920419A (en) * | 2019-03-05 | 2019-06-21 | 百度在线网络技术（北京）有限公司 | Sound control method and device, electronic equipment and computer-readable medium |
| CN110444213A (en) * | 2019-09-03 | 2019-11-12 | 上海擎测机电工程技术有限公司 | A kind of audio recognition method and system based on AR equipment |
| CN110767282A (en) * | 2019-10-30 | 2020-02-07 | 苏州思必驰信息科技有限公司 | Health record generation method and device and computer readable storage medium |
| CN110839051A (en) * | 2018-08-16 | 2020-02-25 | 科沃斯商用机器人有限公司 | Service providing method, device, robot and storage medium |
| WO2020098100A1 (en) * | 2018-11-12 | 2020-05-22 | 平安科技（深圳）有限公司 | Method and apparatus for allocating resources on basis of data analysis, and computer device |
| CN111311775A (en) * | 2020-01-20 | 2020-06-19 | 深圳供电局有限公司 | Electric robot inspection system and method |
| CN113129896A (en) * | 2019-12-30 | 2021-07-16 | 北京猎户星空科技有限公司 | Voice interaction method and device, electronic equipment and storage medium |
| WO2023241482A1 (en) * | 2022-06-13 | 2023-12-21 | 华为技术有限公司 | Man-machine dialogue method, device and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496364A (en) * | 2011-11-30 | 2012-06-13 | 苏州奇可思信息科技有限公司 | Interactive speech recognition method based on cloud network |
| CN102708865A (en) * | 2012-04-25 | 2012-10-03 | 北京车音网科技有限公司 | Method, device and system for voice recognition |
| CN103079258A (en) * | 2013-01-09 | 2013-05-01 | 广东欧珀移动通信有限公司 | Method for improving speech recognition accuracy and mobile intelligent terminal |
| CN103440867A (en) * | 2013-08-02 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for recognizing voice |
| CN103559290A (en) * | 2013-11-08 | 2014-02-05 | 安徽科大讯飞信息科技股份有限公司 | Method and system for searching POI (point of interest) |
| CN105118508A (en) * | 2015-09-14 | 2015-12-02 | 百度在线网络技术（北京）有限公司 | Voice recognition method and device |
| CN105261366A (en) * | 2015-08-31 | 2016-01-20 | 努比亚技术有限公司 | Voice identification method, voice engine and terminal |
| CN106373565A (en) * | 2016-08-24 | 2017-02-01 | 安徽咪鼠科技有限公司 | Method for automatically switching speech recognition engines |
-
2017
- 2017-02-20 CN CN201710091103.7A patent/CN106847291A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102496364A (en) * | 2011-11-30 | 2012-06-13 | 苏州奇可思信息科技有限公司 | Interactive speech recognition method based on cloud network |
| CN102708865A (en) * | 2012-04-25 | 2012-10-03 | 北京车音网科技有限公司 | Method, device and system for voice recognition |
| CN103079258A (en) * | 2013-01-09 | 2013-05-01 | 广东欧珀移动通信有限公司 | Method for improving speech recognition accuracy and mobile intelligent terminal |
| CN103440867A (en) * | 2013-08-02 | 2013-12-11 | 安徽科大讯飞信息科技股份有限公司 | Method and system for recognizing voice |
| CN103559290A (en) * | 2013-11-08 | 2014-02-05 | 安徽科大讯飞信息科技股份有限公司 | Method and system for searching POI (point of interest) |
| CN105261366A (en) * | 2015-08-31 | 2016-01-20 | 努比亚技术有限公司 | Voice identification method, voice engine and terminal |
| CN105118508A (en) * | 2015-09-14 | 2015-12-02 | 百度在线网络技术（北京）有限公司 | Voice recognition method and device |
| CN106373565A (en) * | 2016-08-24 | 2017-02-01 | 安徽咪鼠科技有限公司 | Method for automatically switching speech recognition engines |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107146617A (en) * | 2017-06-15 | 2017-09-08 | 成都启英泰伦科技有限公司 | A kind of novel voice identification equipment and method |
| CN107909715A (en) * | 2017-09-29 | 2018-04-13 | 嘉兴川森智能科技有限公司 | Speech recognition system and method in automatic vending machine |
| CN108806682A (en) * | 2018-06-12 | 2018-11-13 | 奇瑞汽车股份有限公司 | The method and apparatus for obtaining Weather information |
| CN108806682B (en) * | 2018-06-12 | 2020-12-01 | 奇瑞汽车股份有限公司 | Method and device for acquiring weather information |
| CN110839051A (en) * | 2018-08-16 | 2020-02-25 | 科沃斯商用机器人有限公司 | Service providing method, device, robot and storage medium |
| CN110839051B (en) * | 2018-08-16 | 2022-07-01 | 科沃斯商用机器人有限公司 | Service providing method, device, robot and storage medium |
| WO2020098100A1 (en) * | 2018-11-12 | 2020-05-22 | 平安科技（深圳）有限公司 | Method and apparatus for allocating resources on basis of data analysis, and computer device |
| CN109920419A (en) * | 2019-03-05 | 2019-06-21 | 百度在线网络技术（北京）有限公司 | Sound control method and device, electronic equipment and computer-readable medium |
| CN110444213A (en) * | 2019-09-03 | 2019-11-12 | 上海擎测机电工程技术有限公司 | A kind of audio recognition method and system based on AR equipment |
| CN110767282A (en) * | 2019-10-30 | 2020-02-07 | 苏州思必驰信息科技有限公司 | Health record generation method and device and computer readable storage medium |
| CN110767282B (en) * | 2019-10-30 | 2022-07-29 | 思必驰科技股份有限公司 | Health record generation method and device and computer readable storage medium |
| CN113129896A (en) * | 2019-12-30 | 2021-07-16 | 北京猎户星空科技有限公司 | Voice interaction method and device, electronic equipment and storage medium |
| CN113129896B (en) * | 2019-12-30 | 2023-12-12 | 北京猎户星空科技有限公司 | Voice interaction method and device, electronic equipment and storage medium |
| CN111311775A (en) * | 2020-01-20 | 2020-06-19 | 深圳供电局有限公司 | Electric robot inspection system and method |
| WO2023241482A1 (en) * | 2022-06-13 | 2023-12-21 | 华为技术有限公司 | Man-machine dialogue method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106847291A (en) | Speech recognition system and method that a kind of local and high in the clouds is combined | |
| CN111223497B (en) | Nearby wake-up method and device for terminal, computing equipment and storage medium | |
| CN108470034B (en) | A kind of smart machine service providing method and system | |
| CN106409283B (en) | Man-machine mixed interaction system and method based on audio | |
| CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
| CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN104123938A (en) | Voice control system, electronic device and voice control method | |
| CN103440867A (en) | Method and system for recognizing voice | |
| CN202961885U (en) | Voice-controlled toy communication device based on mobile communication terminal | |
| CN111833875B (en) | Embedded voice interaction system | |
| CN108062212A (en) | A kind of voice operating method and device based on scene | |
| CN110299152A (en) | Interactive output control method, device, electronic equipment and storage medium | |
| CN108415904B (en) | Double-channel real-time translation method | |
| CN110248021A (en) | A kind of smart machine method for controlling volume and system | |
| CN110875045A (en) | Voice recognition method, intelligent device and intelligent television | |
| CN113674742B (en) | Man-machine interaction method, device, equipment and storage medium | |
| CN107146617A (en) | A kind of novel voice identification equipment and method | |
| CN108534297A (en) | A kind of intelligent air-conditioning system and control method based on speech recognition | |
| CN103095927A (en) | Displaying and voice outputting method and system based on mobile communication terminal and glasses | |
| CN106910498A (en) | The method for improving voice control command word discrimination | |
| CN116129942A (en) | Voice interaction device and voice interaction method | |
| CN109872719A (en) | A kind of stagewise intelligent voice system and its method of speech processing | |
| CN114664303A (en) | Continuous voice instruction rapid recognition control system | |
| CN210763826U (en) | Elevator car with voice recognition device | |
| CN111933139A (en) | Off-line voice recognition method and system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170613 |