CN107342075A - A kind of Voice command performs the System and method for of APS system commands - Google Patents
A kind of Voice command performs the System and method for of APS system commands Download PDFInfo
- Publication number
- CN107342075A CN107342075A CN201610578075.7A CN201610578075A CN107342075A CN 107342075 A CN107342075 A CN 107342075A CN 201610578075 A CN201610578075 A CN 201610578075A CN 107342075 A CN107342075 A CN 107342075A
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- program
- text information
- speech
- 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 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 2
- 230000009897 systematic effect Effects 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 description 13
- 238000011017 operating method Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 240000005373 Panax quinquefolius Species 0.000 description 1
- 241000282376 Panthera tigris Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000003860 storage 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
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- 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
- G10L15/08—Speech classification or search
-
- 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
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/003—Changing voice quality, e.g. pitch or formants
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)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Document Processing Apparatus (AREA)
Abstract
A kind of Voice command performs the System and method for of APS system commands, voice input module（1）Receive speech data, sound identification module（2）Speech data will be received and be converted into speech text information；Voice match module（3）Speech text information after conversion is matched with keywords database, can judgement match completely；Voice correction module（4）By voice match module（3）The speech text information for judging to match completely is corrected the speech text information that is converted into and can match completely；Keyword and programmatic binding module（5）Speech text information after matching is bound；Programmed logic arranges link block（6）Carry out logic arrangement linker；Program execution module（7）Receive the program information after arrangement connection and complete the execution of work shown in program；Present invention reduces the working strength of operating personnel, improves operating experience, also saves use cost for user so that APS systematic differences are more convenient.
Description
Technical field
The present invention relates to speech control system industry field, what particularly a kind of Voice command performed APS system commands is
System and method.
Background technology
Since the mobile interchange epoch are entered, it has not been that people study to input access information by legacy equipments such as keyboards
Emphasis, how identifying processing voice, how to be received more and more attention for software application.Speech controlled toy, voice control
Auto navigation processed, Voice command household electrical appliances etc., the application of phonetic order is more and more, more and more extensive.Various voice control technologies
Continued to bring out with device, it is generally the case that speech control process is divided into substantially：Voice collecting, speech recognition, voice command production
The parts such as raw, audio controls transmission, control action execution, wherein most critical and difficulty is exactly speech recognition.
Current manufacturing industry is for APS（High-level plan and scheduling）Application it is manual still in legacy equipments such as keyboards
Input phase.It is numerous using legacy equipment advantage, but its inferior position can not be ignored.APS systems are a huge systems, its work(
Can be various and comprehensive.Had defective vision for some, unskilled, the not nimble people of hand, the particularly boss of enterprise operated to software,
Age is bigger but will see projected conditions using the software daily, still seems that some are inconvenient using the software, Ta Menxu
The time more than ordinary person is spent to find the function button of oneself needs, and difficult utilization mouse etc. completes command operation.It is right
In several hours or a couple of days uninterruptedly using the software people for, the frequent operation of this mode, complexity, working strength compared with
Greatly, operating experience is bad, and for some operations, also needs to depend particularly on the accumulation of experience, so as to directly or indirectly
Add the use cost of user.
The content of the invention
For drawbacks described above, it is an object of the invention to provide a kind of Voice command perform the systems of APS system commands with
Method, call default keywords database in APS systems to carry out speech text information matches by voice match module, then pass through language
Sound correction module calls default keywords database in APS systems to enter correction to unmatched speech text information, improves voice
The accuracy rate of instruction.
The technical scheme is that be accomplished by the following way：What a kind of Voice command performed APS system commands is
System, it is characterised in that：The Voice command perform APS system commands system include voice input module, sound identification module,
Voice match module, voice correction module, keyword and programmatic binding module, programmed logic arrangement link block, program perform
Module, the sound identification module are connected with voice input module, for the speech data for receiving the voice input module
It is converted into speech text information；Voice match module is connected with sound identification module, for will conversion after speech text information with
Keywords database is matched, and can judgement match completely；Voice correction module is connected with voice match module, for by institute's predicate
The speech text that the speech text information that the judgement of sound matching module can not match completely matches with keywords database is converted into can be complete
The speech text information of matching；Keyword is connected with programmatic binding module with voice correction module, for by the voice after matching
Text message, and bound by keyword with corresponding program；Programmed logic arrangement link block is tied up with keyword and program
Cover half block connects, for receiving the program information bound and according to certain logic arrangement linker；Program performs mould
Block is connected with programmed logic arrangement link block, for receiving the program information after arrangement connects and completing what is worked shown in program
Perform.
Keywords database is preset with the APS systems, voice association text library is provided with keywords database, is store in storehouse big
The word relevant with APS system operating program operational orders, word, the sentence of amount.
The voice match module 3, voice correction module 4 are connected with default keywords database in APS systems.
A kind of method that Voice command performs APS system commands, it is characterised in that：Including following operating procedure：
1）Obtain, the phonetic order for obtaining issue carries out phonetic entry acquisition speech data；
2）Conversion, obtain speech data and carry out speech recognition acquisition speech text information；
3）Matching, obtain speech text information and carry out Keywords matching with keywords database, judge whether to match completely；
4）Correction, if Incomplete matching, speech text information is subjected to voice correction according to voice association text library；
5）Binding, speech text information are bound according to keyword with corresponding program；
6）Logic arrangement, obtain the program information after binding and according to certain logic arrangement linker；
7）Perform, obtain the program information after arrangement and complete the execution of work shown in program；
The operating procedure 4）In bearing calibration comprise the following steps：
4.1）, speech text information to be corrected；
4.2）, word for word correct, the speech text information after matching is word for word corrected according to voice association text library；
4.3）, by word correct, by the speech text information after matching according to voice association text library carry out by word correct；
4.4）, sentence by sentence correct, the speech text information after matching is corrected sentence by sentence according to voice association text library；
4.5）, all the match is successful.
The operating procedure 5）Binding method comprise the following steps：
5.1）, receive completely matching after speech text information, language is found out with corresponding program relation according to default keyword
The program ordered described in sound text is simultaneously bound；
5.2）, confirm binding, above-mentioned speech text information performs inquiry during being bound according to keyword with corresponding program
Ask choosing then with affirmation mode, under the pattern, when keyword and a kind of programmatic binding, can prompt whether to confirm to perform；Work as key
When word is bound with multiple programs, it may appear that select then function, be just made whether to confirm to perform after carrying out option single choice or double choosings.
A kind of Voice command provided by the invention performs the System and method for of APS system commands so that the manipulation spirit of APS systems
It is living convenient, the working strength of operating personnel is reduced, operating experience is improved, also saves use cost for user so that APS
Systematic difference would be much more convenient fast.And by voice correction module, the speech text information after speech recognition is carried out
Secondary identification, improve the accuracy rate of phonetic order.
Brief description of the drawings
Fig. 1 is the structured flowchart for the system that a kind of Voice command provided by the invention performs APS system commands.
Fig. 2 is the method and step flow chart that a kind of Voice command performs APS system commands.
Fig. 3 is the step flow chart of voice bearing calibration in Fig. 2.
In figure：1 be voice input module, 2 be sound identification module, 3 be voice match module, 4 be voice correction module,
5 be keyword with programmatic binding module, 6 it is programmed logic arrangement link block, 7 is program execution module.
Embodiment
It is more obvious understandable to enable the invention to, the present invention is made with reference to the accompanying drawings and detailed description further
Detailed description.
Known by Fig. 1, be a kind of structured flowchart for the system that Voice command performs APS system commands；The Voice command is held
The system of row APS system commands includes voice input module 1, sound identification module 2, voice match module 3, voice correction module
4th, keyword and programmatic binding module 5, programmed logic arrangement link block 6, program execution module 7, the sound identification module 2
It is connected with voice input module 1, the speech data for the voice input module 1 to be received is converted into speech text information；
Voice match module 3 is connected with sound identification module 2, for speech text information after conversion to be matched with keywords database,
Can judgement match completely；Voice correction module 4 is connected with voice match module 3, for the voice match module 3 to be judged
The speech text that the speech text information that can not be matched completely matches with keywords database is converted into the speech text that can be matched completely
Information；Keyword is connected with programmatic binding module 5 with voice correction module 4, for by the speech text information after matching, and is led to
Keyword is crossed to be bound with corresponding program；Programmed logic arrangement link block 6 is connected with keyword with programmatic binding module 5,
For receiving the program information bound and according to certain logic arrangement linker；Program execution module 7 is patrolled with program
Collect arrangement link block 6 to connect, simultaneously the execution to be worked shown in program is completed for receiving the program information after arrangement connects；It is described
Be preset with keywords database in APS systems, voice association text library be provided with keywords database, store in storehouse largely with APS systems
The relevant word of system operation sequence operational order, word, sentence；It is pre- in the voice match module, voice correction module 4 and APS systems
If keywords database connection, keywords database can be called.
Embodiment one
Known by Fig. 2, the method that the Voice command performs APS system commands includes following operating procedure：（Voice need not be carried out
Correction）
1）, obtain issue phonetic order carry out phonetic entry obtain speech data；
2）, obtain speech data carry out speech recognition obtain speech text information；
3）, obtain speech text information and keywords database progress Keywords matching, judge whether to match completely；
4）, matching completely, speech text bound according to keyword with corresponding program；
4.1）, receive completely matching after speech text information, language is found out with corresponding program relation according to default keyword
The program ordered described in sound text is simultaneously bound；
4.2）, confirm binding, above-mentioned speech text information performs inquiry during being bound according to keyword with corresponding program
Ask choosing then with affirmation mode, under the pattern, when keyword and a kind of programmatic binding, can prompt whether to confirm to perform；Work as key
When word is bound with multiple programs, it may appear that select then function, be just made whether to confirm to perform after carrying out option single choice or double choosings.
5）, obtain binding after program information and according to certain logic arrangement linker；
5.1）, obtain binding after program information；
5.2）If, only exist a program execution command, optimization is corrected to the program；If a plurality of program be present performs life
Order, then be associated judgement to program.Successively associated when existing between program（I.e. a certain program is the prerequisite bar of another program
Part, or another program are the prerequisites of a certain program）When, it is ranked up according to precedence relationship, and the program to ranking the first
It is corrected optimization；When successively association is not present between program, priority alignment is carried out according to the sequencing of acquisition, and to every
One program is corrected optimization.
Above-mentioned steps 5.1）It is middle obtain binding after program information and according to the school in certain logic arrangement linker
Positive optimization functional steps include：
5.1.1）, sequencing performed according to default program, determining program whether there is prerequisite program；
5.1.2）, when the program that transmits performs prerequisite be present（I.e. program must can just be held after the completion of prerequisite program
OK）When, the addition of prerequisite program is arranged in before the program transmitted automatically；
6）, obtain the program information after arrangement and complete the execution of work shown in program.
Embodiment two：
Known by Fig. 2, the method that the Voice command performs APS system commands includes following operating procedure：（Need to carry out voice school
Just）
1）, obtain issue phonetic order carry out phonetic entry obtain speech data；
2）, obtain speech data carry out speech recognition obtain speech text information；
3）, obtain speech text information and keywords database progress Keywords matching, judge whether to match completely；
4）, Incomplete matching, by speech text information according to voice association text library text carry out voice correction；Because voice is known
Other function can not absolutely correctly convert speech into text, always occur during conversion some unisonances or
The text of nearly sound, for this problem, we apply voice correction, to solve the problems, such as voice conversion.Voice conversion can percentage
Hundred convert speech into text, but the text converted is not necessarily the speech text of our original ideas, may
It is the text of unisonance or nearly sound.The problem of same, can also occur for the phonetic order that equally we send, and produce several unisonances
Or nearly sound text, rather than the instruction needed for us.Voice correction just necessarily allows system to produce just by the method for correction
True instruction.Caused incorrect text is not arbitrary after speech recognition, and the phonetic order always sent with user has certain
A little associations.For example " opening manufacturing plan sheet " phonetic order is possibly converted to " open sound production greatly and post words table ", " Da Kai, which abounds with, to be intensified
The text of mark " etc..Text caused by these voice systems we be referred to as " voice association text ".The quantity of " voice association text "
A lot, it is but regular, it is unisonance or nearly sound text.These unisonances or nearly sound text be with phonetic order in number of words
It is more, the quantity mistake of word is only just produced under extremely individual other particular case.On the other hand, we have done one for each instruction
Group " voice association text ", text caused by phonetic order conversion is entirely in this " voice association text " group.To some voices
Instruction may cause word quantity different " voice association text ", all these numbers of words different " voice association text "
It is placed on entirely in one group " voice association text " corresponding to this instruction." the voice association text " of all instructions is organized storage by we
Form " voice association text " storehouse.The text that all phonetic orders sent are converted into all can be looked in " voice association text " storehouse
Arrive, and match mutually corresponding instruct.Correct phonetic order has been produced for us by the matching of " voice association text ".
Which solves the problem of inaccurate and wrong in voice conversion process；
5）, speech text bound according to keyword with corresponding program；
6）, obtain binding after program information and according to certain logic arrangement linker；
7）, obtain the program information after arrangement and complete the execution of work shown in program.
Known by Fig. 3, the step 4）In voice bearing calibration comprise the following steps：
4.1）, speech text information to be corrected；
4.2）, word for word correct, the speech text information after matching is word for word corrected according to voice association text library；
4.3）, by word correct, by the speech text information after matching according to voice association text library carry out by word correct；
4.4）, sentence by sentence correct, the speech text information after matching is corrected sentence by sentence according to voice association text library；
4.5）, all the match is successful.
For example user issues phonetic order " unlatching manufacturing plan sheet " through speech recognition conversion as " the triumphant miserable level of its monk is spent
Mark ".
First, according to table one, word for word matched, be corrected to " unlatching manufacturing plan sheet "
Table one
| Keyword | Associate word |
| Open | Open, be triumphant, pattern ... |
| Open | Open, its, seven ... |
| It is raw | Raw, Sheng, monk ... |
| Production | Produce, be miserable, gluttonous ... |
| Meter | Meter, swash, level ... |
| Draw | Draw, change, flower ... |
| Table | Table, mark, young tiger ... |
Secondly, according to table two, it corrected text will word for word be matched, be corrected to " opening manufacturing plan sheet " by word.
Detailed process is：Since n-th of word, two words of n, n+1 are first matched, if the match is successful, just in n, n+1, n+2 tri-
Individual word is matched, if success just carries out the matching of tetra- words of n, n+1, n+2, n+3, by that analogy until can not the match is successful, remember
The last keyword that the match is successful of record；If matching is unsuccessful, n-th of word is recorded, is matched again since (n+1)th word；If
When matching a remaining word to the end, the last character is directly recorded.
Table two
| Keyword | Conjunctive word |
| Open | Open, open greatly, be triumphant greatly, answer out, open, calling ... |
| Production | Produce, abound with, monk produces, monk is miserable ... |
| Plan | Plan, intensify, level is drawn, level flower ... |
Finally, according to table three, it will sentence by sentence be matched, be corrected to " opening manufacturing plan sheet " by the corrected text of word.
Table three
| Critical sentence | Associate sentence |
| Open manufacturing plan sheet | Open manufacturing plan sheet, manufacturing plan sheet is opened ... |
The system that a kind of Voice command provided by the invention performs APS system commands, manipulation is flexible, reduces operating personnel
Working strength, improve operating experience, also save use cost for user so that APS systematic differences would be much more convenient
Fast.And by voice correction module, the speech text information after speech recognition is recognized, voice is improved and refers to
The accuracy rate of order.
Claims (6)
- A kind of 1. system that Voice command performs APS system commands, it is characterised in that：The Voice command performs APS systems and referred to The system of order includes voice input module（1）, sound identification module（2）, voice match module（3）, voice correction module（4）、 Keyword and programmatic binding module（5）, programmed logic arrangement link block（6）, program execution module（7）, the speech recognition Module（2）With voice input module（1）Connection, for by the voice input module（1）The speech data of reception is converted into language Sound text message；Voice match module（3）With sound identification module（2）Connection, for speech text information after converting with closing Keyword storehouse is matched, and can judgement match completely；Voice correction module（4）With voice match module（3）Connection, for by institute Predicate sound matching module（3）Judge that the speech text that the speech text information that can not be matched completely matches with keywords database is converted into The speech text information that can be matched completely；Keyword and programmatic binding module（5）With voice correction module（4）Connection, for inciting somebody to action Speech text information after matching, and bound by keyword with corresponding program；Programmed logic arranges link block（6）With Keyword and programmatic binding module（5）Connection, for receiving the program information bound and connecting according to certain logic arrangement Connect program；Program execution module（7）Link block is arranged with programmed logic（6）Connection, for receiving the program after arrangement connects Information and the execution for completing work shown in program.
- 2. the system that a kind of Voice command according to claim 1 performs APS system commands, it is characterised in that：The APS Keywords database is preset with system, voice association text library is provided with keywords database, stores in storehouse and is largely grasped with APS systems Make procedure operation and instruct relevant word, word, sentence.
- 3. the system that a kind of Voice command according to claim 1 performs APS system commands, it is characterised in that：Institute's predicate Sound matching module（3）, voice correction module（4）It is connected with default keywords database in APS systems.
- 4. a kind of method that Voice command according to 1 performs APS system commands, it is characterised in that：Including following operation step Suddenly：1）Obtain, the phonetic order for obtaining issue carries out phonetic entry acquisition speech data；2）Conversion, obtain speech data and carry out speech recognition acquisition speech text information；3）Matching, obtain speech text information and carry out Keywords matching with keywords database, judge whether to match completely；4）Correction, if Incomplete matching, speech text information is subjected to voice correction according to voice association text library；5）Binding, speech text information are bound according to keyword with corresponding program；6）Logic arrangement, obtain the program information after binding and according to certain logic arrangement linker；7）Perform, obtain the program information after arrangement and complete the execution of work shown in program.
- 5. the method that a kind of Voice command according to claim 4 performs APS system commands, it is characterised in that：The behaviour Make step 4）In bearing calibration comprise the following steps：1）, speech text information to be corrected；2）, word for word correct, the speech text information after matching is word for word corrected according to voice association text library；3）, by word correct, by the speech text information after matching according to voice association text library carry out by word correct；4）, sentence by sentence correct, the speech text information after matching is corrected sentence by sentence according to voice association text library；5）, all the match is successful.
- 6. the method that a kind of Voice command according to claim 4 performs APS system commands, it is characterised in that：The behaviour Make step 5）Binding method comprise the following steps：1）, receive completely matching after speech text information, voice is found out with corresponding program relation according to default keyword The program ordered described in text is simultaneously bound；2）, confirm binding, above-mentioned speech text information performs inquiry during being bound according to keyword with corresponding program Whether choosing then with affirmation mode, under the pattern, when keyword and a kind of programmatic binding, can prompt to confirm to perform；Work as keyword When being bound with multiple programs, it may appear that select then function, be just made whether to confirm to perform after carrying out option single choice or double choosings.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610578075.7A CN107342075A (en) | 2016-07-22 | 2016-07-22 | A kind of Voice command performs the System and method for of APS system commands |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610578075.7A CN107342075A (en) | 2016-07-22 | 2016-07-22 | A kind of Voice command performs the System and method for of APS system commands |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107342075A true CN107342075A (en) | 2017-11-10 |
Family
ID=60222176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610578075.7A Pending CN107342075A (en) | 2016-07-22 | 2016-07-22 | A kind of Voice command performs the System and method for of APS system commands |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107342075A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251869A (en) * | 2016-09-22 | 2016-12-21 | 浙江吉利控股集团有限公司 | Method of speech processing and device |
| CN108153875A (en) * | 2017-12-26 | 2018-06-12 | 广州蓝豹智能科技有限公司 | Language material processing method, device, intelligent sound box and storage medium |
| CN110019679A (en) * | 2017-12-13 | 2019-07-16 | 联易软件有限公司 | Food and drug administration method and apparatus |
| CN110162802A (en) * | 2019-06-24 | 2019-08-23 | 付金龙 | A kind of Sino-British voice translator of intelligence |
| CN110265014A (en) * | 2019-06-24 | 2019-09-20 | 付金龙 | A kind of method, apparatus and translator of voice control |
| CN110880316A (en) * | 2019-10-16 | 2020-03-13 | 苏宁云计算有限公司 | Audio output method and system |
| CN110909127A (en) * | 2019-11-07 | 2020-03-24 | 中铁大桥科学研究院有限公司 | Method and system for inputting and inquiring bridge inspection information |
| CN111292752A (en) * | 2018-12-06 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | User intention identification method and device, electronic equipment and storage medium |
| CN111653279A (en) * | 2020-05-28 | 2020-09-11 | 广东电网有限责任公司 | Power transmission line picture voice naming device and naming method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1312543A (en) * | 2000-02-28 | 2001-09-12 | 索尼公司 | Speech-sound identifying device, identifying method and recording medium |
| CN103277974A (en) * | 2013-06-19 | 2013-09-04 | 江苏华音信息科技有限公司 | Device for controlling intelligent refrigerator by utilizing Chinese speeches |
| CN103279363A (en) * | 2013-06-19 | 2013-09-04 | 江苏华音信息科技有限公司 | Chinese speech remote control computer program operating device |
| CN103546787A (en) * | 2012-07-12 | 2014-01-29 | 三星电子株式会社 | Method for correcting voice recognition error and broadcast receiving apparatus applying the same |
| CN103646646A (en) * | 2013-11-27 | 2014-03-19 | 联想(北京)有限公司 | Voice control method and electronic device |
| JP2016014967A (en) * | 2014-07-01 | 2016-01-28 | パナソニック インテレクチュアル プロパティ コーポレーション オブアメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ | Information management method |
-
2016
- 2016-07-22 CN CN201610578075.7A patent/CN107342075A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1312543A (en) * | 2000-02-28 | 2001-09-12 | 索尼公司 | Speech-sound identifying device, identifying method and recording medium |
| CN103546787A (en) * | 2012-07-12 | 2014-01-29 | 三星电子株式会社 | Method for correcting voice recognition error and broadcast receiving apparatus applying the same |
| CN103277974A (en) * | 2013-06-19 | 2013-09-04 | 江苏华音信息科技有限公司 | Device for controlling intelligent refrigerator by utilizing Chinese speeches |
| CN103279363A (en) * | 2013-06-19 | 2013-09-04 | 江苏华音信息科技有限公司 | Chinese speech remote control computer program operating device |
| CN103646646A (en) * | 2013-11-27 | 2014-03-19 | 联想(北京)有限公司 | Voice control method and electronic device |
| JP2016014967A (en) * | 2014-07-01 | 2016-01-28 | パナソニック インテレクチュアル プロパティ コーポレーション オブアメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ | Information management method |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251869A (en) * | 2016-09-22 | 2016-12-21 | 浙江吉利控股集团有限公司 | Method of speech processing and device |
| CN106251869B (en) * | 2016-09-22 | 2020-07-24 | 浙江吉利控股集团有限公司 | Voice processing method and device |
| US11011170B2 (en) | 2016-09-22 | 2021-05-18 | Zhejiang Geely Holding Group Co., Ltd. | Speech processing method and device |
| CN110019679A (en) * | 2017-12-13 | 2019-07-16 | 联易软件有限公司 | Food and drug administration method and apparatus |
| CN108153875A (en) * | 2017-12-26 | 2018-06-12 | 广州蓝豹智能科技有限公司 | Language material processing method, device, intelligent sound box and storage medium |
| CN111292752A (en) * | 2018-12-06 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | User intention identification method and device, electronic equipment and storage medium |
| CN111292752B (en) * | 2018-12-06 | 2023-05-12 | 北京嘀嘀无限科技发展有限公司 | User intention recognition method and device, electronic equipment and storage medium |
| CN110162802A (en) * | 2019-06-24 | 2019-08-23 | 付金龙 | A kind of Sino-British voice translator of intelligence |
| CN110265014A (en) * | 2019-06-24 | 2019-09-20 | 付金龙 | A kind of method, apparatus and translator of voice control |
| CN110880316A (en) * | 2019-10-16 | 2020-03-13 | 苏宁云计算有限公司 | Audio output method and system |
| CN110909127A (en) * | 2019-11-07 | 2020-03-24 | 中铁大桥科学研究院有限公司 | Method and system for inputting and inquiring bridge inspection information |
| CN111653279A (en) * | 2020-05-28 | 2020-09-11 | 广东电网有限责任公司 | Power transmission line picture voice naming device and naming method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107342075A (en) | A kind of Voice command performs the System and method for of APS system commands | |
| CN103279363B (en) | The device that Chinese speech remote control computer program is run | |
| CN107329967B (en) | Question answering system and method based on deep learning | |
| CN103279190B (en) | Chinese language text calls the device that computer program runs | |
| US11494161B2 (en) | Coding system and coding method using voice recognition | |
| CN109101545A (en) | Natural language processing method, apparatus, equipment and medium based on human-computer interaction | |
| CN108170835A (en) | A kind of intelligent customer service system of combinatorial artificial and AI | |
| CN103277874A (en) | Device for nonspecific persons to remotely control intelligent air conditioner by Chinese speech | |
| CN104462600A (en) | Method and device for achieving automatic classification of calling reasons | |
| CN105184575B (en) | Transaction system construction method, transaction flow control device and third party transaction platform | |
| CN103189826A (en) | Multimodal user notification system to assist in data capture | |
| US8543406B2 (en) | Method and system for communicating with an interactive voice response (IVR) system | |
| CN110096516B (en) | User-defined database interaction dialog generation method and system | |
| CN111179928A (en) | Intelligent control method for power transformation and distribution station based on voice interaction | |
| CN111597318A (en) | Method, device and system for executing business task | |
| CN110266900A (en) | Recognition methods, device and the customer service system that client is intended to | |
| CN104020840A (en) | Method for remotely controlling computer program to operate by foreign language text | |
| CN109670020A (en) | A kind of voice interactive method, system and device | |
| CN113284502A (en) | Intelligent customer service voice interaction method and system | |
| CN105550361B (en) | Log processing method and device and question and answer information processing method and device | |
| CN104049964B (en) | Chinese speech low coverage or the method for long-range control electromechanical equipment operation | |
| CN106331393A (en) | Control method and control device | |
| CN104235998A (en) | Method for non-specified people to remotely control intelligent air conditioner through Chinese phonetic symbols | |
| CN104049961A (en) | Method for performing remote control on computer program execution by use of Chinese speech | |
| CN103428363B (en) | The method and apparatus that improved voice activation function is provided |
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 |
Application publication date: 20171110 |
|
| WD01 | Invention patent application deemed withdrawn after publication |