CN106409283A - Audio frequency-based man-machine mixed interaction system and method - Google Patents
Audio frequency-based man-machine mixed interaction system and method Download PDFInfo
- Publication number
- CN106409283A CN106409283A CN201610791966.0A CN201610791966A CN106409283A CN 106409283 A CN106409283 A CN 106409283A CN 201610791966 A CN201610791966 A CN 201610791966A CN 106409283 A CN106409283 A CN 106409283A
- Authority
- CN
- China
- Prior art keywords
- message
- unit
- module
- intervention
- voice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
- G10L13/08—Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
- G10L13/10—Prosody rules derived from text; Stress or intonation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Abstract
The invention discloses an audio frequency-based man-machine mixed interaction system, a voice recognition module and a semantic recognition module are interconnected and used for transmitting word information corresponding to voice, an exception handling module is connected with the voice recognition module and the semantic recognition module, the voice recognition module is used for transmitting the word information to the exception handling module, the semantic recognition module is used for transmitting semantic parsing results to the exception handling module, and the exception handling module and a voice synthesis module are interconnected and used for transmitting intervention information. The invention also discloses an audio frequency-based man-machine mixed interaction method, voice information is converted into the word information via the voice recognition module, the word information is output to a semantic recognition unit, a user aim and corresponding key information are extracted from the word information via the semantic recognition unit, and whether anomaly occurs during a current human computer dialogue is determined by the exception handling module according to the word information of the voice recognition module and semantic information of the semantic recognition module, and an information reply for the anomaly is given. The audio frequency-based man-machine mixed interaction system and method disclosed in a technical solution of the invention can provide unified human computer dialogue experience.
Description
Technical field
The present invention relates to technical field of information processing, more particularly, to a kind of man-machine mixing interactive system based on audio frequency and side
Method.
Background technology
As shown in figure 1, the interactive system being currently based on audio frequency all replies as finally replying using machine and presents to
User, when machine decision system can not specify user view, most of conversational system selects to assume " pardon " etc
The input to allow user carry out again for the reply, wherein part interactive system introduces the manual intervention based on telephone traffic center
Method.
Existing human computer conversation's abnormality processing is mainly realized by telephone traffic center form at present, cannot process user in machine defeated
Enter audio frequency or user explicitly indicate that need manual service when, the intervention of business center, now user and traffic if request is artificial
Set up man-to-man call between member to connect, operator is directly exchanged with user, know the demand of user and pass through traffic
Platform issues corresponding instruction.
The problem that the manual intervention mode at live traffic center exists mainly has：Man efficiency is low, and intervening teacher is needed with user
Set up man-to-man speech exchange, in the time period waiting user input, cannot be serviced other people；High cost, exhales on a large scale
Make center need a series of telecommunication apparatus and respective service integrated, simultaneously because efficiency is low, need more intervention Shi Jinhang
Intervene service, thus indirectly improve human cost；Big by network environment influence：Directly transmit audio frequency needs using Internet resources
Stable network connection, the fluctuation of network environment can lead to audio quality to decline thus affecting dialogue experience, or even interrupts man-machine
Conversation process.
Therefore, those skilled in the art is devoted to developing a kind of man-machine mixing interactive system based on audio frequency and method,
Manual intervention reply is replied with machine and combines, thus unified interactive flow process and lifting Consumer's Experience.
Content of the invention
In view of the drawbacks described above of prior art, the technical problem to be solved be how to improve customer service during
Interactive efficiency and Consumer's Experience.
For achieving the above object, the invention provides a kind of man-machine mixing interactive system based on audio frequency, know including voice
Other module, voice synthetic module, semantics recognition module and exception processing module, wherein, described sound identification module is configured
It is to be connected with described semantics recognition module and transmit the corresponding Word message of voice, described exception processing module is configured to and institute
State sound identification module to be connected with described semantics recognition module, described sound identification module is configured to transmit Word message to institute
State exception processing module, described semantics recognition module is configured to transmit semantic analysis result to described exception processing module；Institute
State exception processing module to be configured to be connected with described voice synthetic module and transmit intervention information.
Further, described sound identification module includes signal processing and feature extraction unit, acoustic model, language model
And decoder, wherein, described signal processing and feature extraction unit are configured to be connected with described acoustic model and transmit sound
Learn characteristic information, described decoder is configured to be connected with described acoustic model and described language model and export recognition result.
Further, described voice synthetic module includes text analysis unit, prosodic control unit and synthesis voice list
Unit, wherein, described text analysis unit is configured to receive text message and described text message is processed, and will process knot
Fruit is transferred to described prosodic control unit and described synthesis voice unit, and described prosodic control unit is configured to and described synthesis
Voice unit is connected, and transmits pitch, the duration of a sound, loudness of a sound, pause and prosody information, and described synthesis voice unit is configured to institute
State the voice of the analysis result receiving text analysis unit and the control parameter synthesis output of described prosodic control unit.
Further, described semantics recognition module includes field mark unit, intention determination unit, information extraction unit,
Wherein, described field mark unit is configured to be connected with described intention determination unit and transmission field information, and described intention is sentenced
Disconnected unit is configured to be connected with described information extraction unit and transmit user intent information, and described information extraction unit exports language
The result of justice analysis.
Further, described exception processing module includes abnormality detecting unit, data base querying unit and intervenes Shi Dan
Unit, wherein, described abnormality detecting unit is configured to receive the output of described sound identification module and described semantics recognition module,
And deciding whether to take intervening measure, described data base querying unit is configured to receive the intervention letter of described abnormality detecting unit
Number, and receive the semantic information of described semantics recognition module, inquire about and export intervention message, described intervention Shi Danyuan is configured to
Using intervene teacher's described intervention message that described data base querying unit export carry out necessary preferentially and change, finally defeated
Go out replying message to user.
Present invention also offers a kind of man-machine mixing exchange method based on audio frequency, comprise the following steps：
Step 1, offer sound identification module, voice synthetic module, semantics recognition module and exception processing module；
Voice messaging is converted to Word message and exports to described semantics recognition list by step 2, described sound identification module
Unit；
Step 3, described semantics recognition unit extract customer objective and corresponding key message from Word message；
Step 4, described exception processing module are according to the Word message of described sound identification module and described semantics recognition
The semantic information of module judges whether human computer conversation abnormal and for abnormality processing message reply currently.
Further, in step 2, following steps are specifically included：
Step 2.1, from input audio stream extract feature supply acoustic model process, simultaneously reduce environment noise, channel
The impact described feature being caused with speaker's factor；
Step 2.2, decoder, according to acoustics, linguistic model and dictionary, the result to described acoustic model, are found
The word string of described audio stream can be exported with maximum of probability, as the recognition result of voice.
Further, in step 3, following steps are specifically included：
Step 3.1, using the significant field belonging to keyword tag current session in Word message；
Step 3.2, rule-based in described field user view is judged；
Step 3.3, according to described field and described user view, binding rule, specific key message is carried
Take.
Further, in step 4, following steps are specifically included：
Step 4.1, abnormality detecting unit are according to the Word message of described sound identification module and described semantics recognition mould
The semantic information of block judges whether current human computer conversation exception, if abnormal, takes over human computer conversation by intervening Shi Danyuan；
Step 4.2, data base querying unit carry out the inquiry of data base according to semantic information, obtain thering is the dry of recommendation degree
Pre- message, if the recommendation degree of intervention message is higher, is directly intervened using this intervention message, if recommendation degree is relatively low,
Then intervention required Shi Jinhang manpower intervention；
Step 4.3, when machine algorithm cannot find the intervention message of high recommendations degree, intervene teacher and intervene and carry out intervention message
Selection and modification, subsequently amended intervention message is sent to client.
Further, described key message includes dialogue field, dialogue key word, and described dialogue key word includes content and closes
Keyword and emotion key word.
Compared with prior art, the technique effect of the present invention includes:
1st, efficiency improves：Take full advantage of the time intervening teacher's wait user input so that intervention teacher can be simultaneously to multiple
User carries out intervening service, improves the efficiency intervened.
2nd, cost reduces：A series of related telecommunication apparatus of telephone traffic center need not be purchased, using existing computer and
Server can build Interference service platform.
3rd, operative scenario is enriched：Employ B/S (Browser/Server browser/server) knot due to intervening teacher interface
Structure, intervention teacher opens the corresponding website of browser login and can carry out intervention operation it is not necessary to receive calls on station, permissible
The mobile terminals such as PAD, smart mobile phone, personal notebook carry out intervening service.
4th, network requirement is low：The data volume very little of File Transfer, thus the requirement to network reduces, user's uppick simultaneously
Voice by locally synthesizing, do not affected by network condition.
5th, unified human computer conversation's experience：For user, it is transparent for intervening teacher, and the experience of user is as filled with one
" machine " that divide intelligence, can be with the current man-machine conversation mode of seamless connection in dialogue.
Technique effect below with reference to design, concrete structure and generation to the present invention for the accompanying drawing is described further, with
It is fully understood from the purpose of the present invention, feature and effect.
Brief description
Fig. 1 is the intervention mode schematic diagram of existing tradition telephone traffic center；
Fig. 2 is the system module schematic diagram of the present invention；
Fig. 3 is the system flow schematic diagram of a preferred embodiment of the present invention；
Fig. 4 is the part dialog schematic flow sheet of a preferred embodiment of the present invention.
Specific embodiment
The present invention is achieved by the following technical solutions：
As shown in Fig. 2 the present invention relates to a kind of human computer conversation's abnormality processing system based on audio frequency, including：Speech recognition
Module, voice synthetic module, semantics recognition module and exception processing module, wherein：Sound identification module and semantics recognition mould
Block is connected and transmits the corresponding Word message of voice, sound identification module and semantics recognition module all with exception processing module phase
Even, and respectively Word message and semantic analysis result are transmitted, exception processing module is connected with voice synthetic module and transmits intervention
Information.
Described sound identification module includes：Signal processing and feature extraction unit, acoustic model, language model and solution
Code device, wherein：Signal processing and feature extraction unit are connected with acoustic model and transmit acoustic featuress information, decoder and acoustics
Model is connected with language model, exports recognition result to external world.
Described voice synthetic module includes：Text analysis unit, prosodic control unit and synthesis voice unit, its
In：Text analysis unit receives text message and it is processed, and result is transferred to prosodic control unit and synthesis
Voice unit, prosodic control unit is connected with synthesis voice unit, and the pitch of transmission objectives, the duration of a sound, loudness of a sound, pause and intonation
Etc. information, synthesize voice unit and receive the analysis result of text analysis unit and the control parameter of prosodic control unit, to external world
The voice of output synthesis.
Described semantics recognition module includes：Field mark unit, intention determination unit, information extraction unit, wherein：Neck
Domain mark unit is connected with intention determination unit and transmission field information is it is intended that judging unit is connected with information extraction unit and passes
Defeated user intent information, information unit is connected with the external world and transmits the information of semantic analysis.
Described exception processing module includes：Abnormality detecting unit, data base querying unit, intervention Shi Danyuan are with wherein：
Abnormality detecting unit receives the output of sound identification module and semantics recognition module, and decides whether to take intervening measure, data
The intervention signal of library inquiry unit reception abnormality detecting unit, and receive the semantic information of semantics recognition module, inquire about and export
Intervention message, intervene Shi Danyuan using intervene teacher's intervention message that data base querying unit is exported carry out necessary preferentially and
Modification, final output user reply message.
The present invention relates to human computer conversation's abnormality eliminating method of said system, specifically include following steps：
Step 1, offer sound identification module, voice synthetic module, semantics recognition module and exception processing module.
Voice messaging is converted to Word message and exports to semantics recognition unit by step 2, sound identification module, concrete step
Rapid inclusion：
2.1 front-end processing audio streams, extract feature from input signal, process for acoustic model.Reduce as far as possible simultaneously
The impact that the factors such as environment noise, channel, speaker cause to feature.
To the signal inputting according to acoustics, linguistic model and dictionary, searching can be exported 2.2 decoders with maximum of probability
The word string of this signal, as the recognition result of voice.
Step 3, semantics recognition unit extract customer objective and corresponding key message, concrete steps from Word message
Including：
3.1 utilize the significant field belonging to keyword tag current session in Word message.
3.2 in specific field the rule-based intention to user judge.
3.3 according to field and user view, binding rule, and template for example set in advance, to specific key message
Extracted.
Step 4, exception processing module are believed according to the Word message of sound identification module and the semantic of semantics recognition module
Breath judges whether human computer conversation currently exception and carry out the reply of abnormal process and message, and concrete steps include：
4.1 abnormality detecting unit are sentenced according to the Word message of sound identification module and the semantic information of semantics recognition module
Whether current human computer conversation of breaking exception.Abnormal then processed by local client, abnormal then by intervention server
Adapter human computer conversation.
4.2 data base querying units carry out the inquiry of data base according to semantic information, obtain the intervention message recommended, if
The recommendation degree of intervention message is higher, then directly intervened using this intervention message, if recommendation degree is relatively low, intervention required teacher
Carry out manpower intervention.
4.3, when machine algorithm cannot find the intervention message of high recommendation degree, intervene the choosing that teacher's intervention carries out intervention message
Select and change, subsequently send amended intervention message to client.
During human computer conversation's abnormality processing, the speech recognition of machine and semantic solution are passed through in the phonetic entry of user
After analysis, the result of the recognition result of voice and semantic parsing can be passed to intervention Shi Duan in a text form, intervene teacher and accept
Can select to send conversation message or transmitting order to lower levels message to after message.Conversation message is transferred to machine in a text form
Device, subsequently synthesizes voice by speech synthesis system (TTS) and plays to user, command messages are then directly to be executed by machine
Order.
The present embodiment comprises the following steps, as shown in Figure 3 and Figure 4, i.e. user input -->Intervention message generates -->Client
Machine pushes the introduction that three steps of intervention message carry out technical scheme respectively：
1) user input
During user carries out phonetic entry, using speech recognition system the phonetic entry audio frequency of user is converted to
Word, this word is carried out with semantic analysis simultaneously, and (result of semantic analysis includes the current dialogue field of user, user's request
Key message of service etc.), finally the result of word and semantic analysis is passed through in the form of text the POST side of http protocol
Method is transferred to exception processing module.
2) intervention message generates
Exception processing module in abnormal cases, inquire about by the text message according to speech recognition and the semantic groove of semantics recognition
Data base, obtains alternative intervention message.If the recommendation degree of intervention message is higher, directly done using this intervention message
In advance, if recommendation degree is relatively low, intervention required Shi Jinhang manpower intervention.Intervene teacher can see by abnormality processing mould on interface
Result of the recognition result of assistance data such as user input of block offer and semantic analysis etc., intervenes teacher's energy in conjunction with these information
Enough more quickly and accurately candidate's intervention message is screened and changed.Intervention message is divided into conversation message and command messages, all
Be transmitted using unified Websocket agreement in a text form, its difference from the different of transferring content and machine
Processing mode different.
3) client computer pushes intervention message
Client computer immediately returns to after receiving intervention message intervene the confirmation of teacher's " message has been received by ", and by intervention message
It is buffered in message queue.Client computer can be monitored current human computer conversation's state and attempt under certain condition from message queue
Take out message to push to user, specific push opportunity includes：1st, intervention message reach when, 2, TTS synthesis speech message
When report completes；Need the condition meeting be 1, message queue be not empty, 2, the audio player current idle of client computer.If
Intervention message successfully pushes, and returns the confirmation intervening teacher's " intervention message pushes ".
For example：
1st, user A sends phonetic order " I will go to a joyful place ".
2nd, phonetic entry is converted to word by sound identification module.
3rd, semantic module obtains user view after processing is " navigation ", and the label on the target ground of navigation is " joyful ".
4th, the abnormality detecting unit in exception processing module receives the service request of user A, comprises complete speech recognition
Result " I will go to a joyful place ", and the result " navigation " of semantic analysis, " joyful ", are detected simultaneously by current dialogue
State occurs abnormal.
5th, the data base querying unit in exception processing module according to " navigation ", " joyful " carry out data base querying, obtain
Some alternate message are such as " may I ask the joyful snack in your Suzhou to be gone？", " be you look for 5 to joyful related place ",
Recommendation degree all ratios of this two message are relatively low, therefore the manpower intervention of intervention required Shi Danyuan.Intervene Shi Liyong exception processing module
The text results of the database query result obtaining and semantic analysis result and speech recognition carry out intervention message selection and
Modification, intervention message is changed to " may I ask what kind of entertainment way you want？", send text message to user.
6th, client computer is deposited into message queue after receiving intervention message, sends " message has been received by " to exception processing module
Feedback, and attempt being pushed.
7th, condition carries out the speech synthesis system synthesis of intervention message and reports after meeting, and user hears that audio frequency " be may I ask
What kind of entertainment way you want ", client computer sends " message pushes " feedback to exception processing module.
8th, client carries out further phonetic entry " I will go to sing "
9th, phonetic entry is converted to word by ASR system
10th, semantic analysis obtain user view is " navigation ", and the target of navigation is " KTV "
11st, abnormality detecting unit obtains the specific service demand of user A, and " I will go to comprise complete voice identification result
Sing ", and the result of semantic analysis " navigation ", " KTV ".
12nd, data base querying unit according to " navigation ", " KTV " and the relevant information of user carries out the search of data base,
Obtain alternative intervention message " recommend xxx may I ask for you whether to go to？", simultaneously because recommendation degree is very high, therefore bypass intervention Shi Dan
Unit, directly sends word message to client computer " recommend xxx may I ask for you whether to go to？“
13rd, user confirms to go to
14th, abnormality processing system user pushes the intervention message of command type, comprises command type " navigation " and purpose
The POI on ground.
15th, client computer takes out the message of command type " navigation " and corresponding POI from message queue, is led
Boat operation, client computer sends " message pushes " feedback to exception processing module, and interaction terminates.
The preferred embodiment of the present invention described in detail above.It should be appreciated that the ordinary skill of this area need not be created
The property made work just can make many modifications and variations according to the design of the present invention.Therefore, all technical staff in the art
Pass through the available technology of logical analysis, reasoning, or a limited experiment under this invention's idea on the basis of existing technology
Scheme, all should be in the protection domain being defined in the patent claims.
Claims (10)
1. a kind of man-machine mixing interactive system based on audio frequency is it is characterised in that include sound identification module, phonetic synthesis mould
Block, semantics recognition module and exception processing module, wherein, described sound identification module is configured to and described semantics recognition mould
Block is connected and transmits the corresponding Word message of voice, and described exception processing module is configured to and described sound identification module and institute
Predicate justice identification module is connected, and described sound identification module is configured to transmit Word message to described exception processing module, institute
Predicate justice identification module is configured to transmit semantic analysis result to described exception processing module；Described exception processing module is joined
It is set to and be connected with described voice synthetic module and transmit intervention information.
2. the man-machine mixing interactive system based on audio frequency as claimed in claim 1 is it is characterised in that described sound identification module
Including signal processing and feature extraction unit, acoustic model, language model and decoder, wherein, described signal processing and spy
Levy extraction unit to be configured to be connected and transmit acoustic featuress information with described acoustic model, described decoder is configured to and institute
State acoustic model to be connected with described language model and export recognition result.
3. the man-machine mixing interactive system based on audio frequency as claimed in claim 1 is it is characterised in that described voice synthetic module
Including text analysis unit, prosodic control unit and synthesis voice unit, wherein, described text analysis unit is configured to connect
Receive text message and described text message is processed, result is transferred to described prosodic control unit and described synthesis
Voice unit, described prosodic control unit be configured to described synthesis voice unit be connected, and transmit pitch, the duration of a sound, loudness of a sound,
Pause and prosody information, described synthesis voice unit be configured to by described receive text analysis unit analysis result with described
The voice of the control parameter synthesis output of prosodic control unit.
4. the man-machine mixing interactive system based on audio frequency as claimed in claim 1 is it is characterised in that described semantics recognition module
Including field mark unit, intention determination unit, information extraction unit, wherein, described field mark unit is configured to and institute
State intention determination unit to be connected and transmission field information, described intention determination unit is configured to and described information extraction unit phase
Connect and transmit user intent information, described information extraction unit exports the result of semantic analysis.
5. the man-machine mixing interactive system based on audio frequency as claimed in claim 1 is it is characterised in that described exception processing module
Including abnormality detecting unit, data base querying unit and intervention Shi Danyuan, wherein, described abnormality detecting unit is configured to connect
Receive described sound identification module and the output of described semantics recognition module, and decide whether to take intervening measure, described data base
Query unit is configured to receive the intervention signal of described abnormality detecting unit, and receives the semantic letter of described semantics recognition module
Breath, inquires about and exports intervention message, and it is defeated to described data base querying unit that described intervention Shi Danyuan is configured to, with intervention teacher
The described intervention message going out carry out necessary preferentially and modification, final output replying message to user.
6. a kind of man-machine mixing exchange method based on audio frequency is it is characterised in that comprise the following steps：
Step 1, offer sound identification module, voice synthetic module, semantics recognition module and exception processing module；
Voice messaging is converted to Word message and exports to described semantics recognition unit by step 2, described sound identification module；
Step 3, described semantics recognition unit extract customer objective and corresponding key message from Word message；
Step 4, described exception processing module are according to the Word message of described sound identification module and described semantics recognition module
Semantic information judge whether human computer conversation reply that is abnormal and being directed to abnormality processing message currently.
7. the man-machine mixing exchange method based on audio frequency as claimed in claim 6 it is characterised in that in step 2, specifically wraps
Include following steps：
Step 2.1, extract feature from the audio stream of input and supply acoustic model to process, reduce environment noise, channel and say simultaneously
The impact that words people's factor causes to described feature；
, according to acoustics, linguistic model and dictionary, the result to described acoustic model, searching can for step 2.2, decoder
Export the word string of described audio stream with maximum of probability, as the recognition result of voice.
8. the man-machine mixing exchange method based on audio frequency as claimed in claim 6 it is characterised in that in step 3, specifically wraps
Include following steps：
Step 3.1, using the significant field belonging to keyword tag current session in Word message；
Step 3.2, rule-based in described field user view is judged；
Step 3.3, according to described field and described user view, binding rule, specific key message is extracted.
9. the man-machine mixing exchange method based on audio frequency as claimed in claim 6 it is characterised in that in step 4, specifically wraps
Include following steps：
Step 4.1, abnormality detecting unit are according to the Word message of described sound identification module and described semantics recognition module
Semantic information judges whether current human computer conversation exception, if abnormal, takes over human computer conversation by intervening Shi Danyuan；
Step 4.2, data base querying unit carry out the inquiry of data base according to semantic information, and the intervention obtaining having recommendation degree disappears
Breath, if the recommendation degree of intervention message is higher, is directly intervened using this intervention message, if recommendation degree is relatively low, please
Seek intervention Shi Jinhang manpower intervention；
Step 4.3, when machine algorithm cannot find the intervention message of high recommendations degree, intervene teacher and intervene the choosing carrying out intervention message
Select and change, subsequently send amended intervention message to client.
10. the man-machine mixing exchange method based on audio frequency as described in claim 6 or 8 is it is characterised in that described key message
Including dialogue field, dialogue key word, described dialogue key word includes content keyword and emotion key word.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610791966.0A CN106409283B (en) | 2016-08-31 | 2016-08-31 | Man-machine mixed interaction system and method based on audio |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610791966.0A CN106409283B (en) | 2016-08-31 | 2016-08-31 | Man-machine mixed interaction system and method based on audio |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106409283A true CN106409283A (en) | 2017-02-15 |
| CN106409283B CN106409283B (en) | 2020-01-10 |
Family
ID=58001464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610791966.0A Active CN106409283B (en) | 2016-08-31 | 2016-08-31 | Man-machine mixed interaction system and method based on audio |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106409283B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122807A (en) * | 2017-05-24 | 2017-09-01 | 努比亚技术有限公司 | A kind of family's monitoring method, service end and computer-readable recording medium |
| CN107733780A (en) * | 2017-09-18 | 2018-02-23 | 上海量明科技发展有限公司 | Task smart allocation method, apparatus and JICQ |
| CN107992587A (en) * | 2017-12-08 | 2018-05-04 | 北京百度网讯科技有限公司 | A kind of voice interactive method of browser, device, terminal and storage medium |
| CN109697226A (en) * | 2017-10-24 | 2019-04-30 | 上海易谷网络科技股份有限公司 | Text silence seat monitoring robot interactive method |
| CN110069607A (en) * | 2017-12-14 | 2019-07-30 | 株式会社日立制作所 | For the method, apparatus of customer service, electronic equipment, computer readable storage medium |
| CN110602334A (en) * | 2019-09-03 | 2019-12-20 | 上海航动科技有限公司 | Intelligent outbound method and system based on man-machine cooperation |
| WO2020057446A1 (en) * | 2018-09-17 | 2020-03-26 | Huawei Technologies Co., Ltd. | Method and system for generating a semantic point cloud map |
| CN110926493A (en) * | 2019-12-10 | 2020-03-27 | 广州小鹏汽车科技有限公司 | Navigation method, navigation device, vehicle and computer readable storage medium |
| CN110970017A (en) * | 2018-09-27 | 2020-04-07 | 北京京东尚科信息技术有限公司 | Human-computer interaction method and system and computer system |
| CN111125384A (en) * | 2018-11-01 | 2020-05-08 | 阿里巴巴集团控股有限公司 | Multimedia answer generation method and device, terminal equipment and storage medium |
| CN111540353A (en) * | 2020-04-16 | 2020-08-14 | 重庆农村商业银行股份有限公司 | Semantic understanding method, device, equipment and storage medium |
| CN112509575A (en) * | 2020-11-26 | 2021-03-16 | 上海济邦投资咨询有限公司 | Financial consultation intelligent guiding system based on big data |
| CN112735410A (en) * | 2020-12-25 | 2021-04-30 | 中国人民解放军63892部队 | Automatic voice interactive force model control method and system |
| CN112735427A (en) * | 2020-12-25 | 2021-04-30 | 平安普惠企业管理有限公司 | Radio reception control method and device, electronic equipment and storage medium |
| CN107204185B (en) * | 2017-05-03 | 2021-05-25 | 深圳车盒子科技有限公司 | Vehicle-mounted voice interaction method and system and computer readable storage medium |
| CN116453540A (en) * | 2023-06-15 | 2023-07-18 | 山东贝宁电子科技开发有限公司 | Underwater frogman voice communication quality enhancement processing method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1920948A (en) * | 2005-08-24 | 2007-02-28 | 富士通株式会社 | Voice recognition system and voice processing system |
| CN101276584A (en) * | 2007-03-28 | 2008-10-01 | 株式会社东芝 | Prosody-pattern generating apparatus, speech synthesizing apparatus, and computer program product and method thereof |
| CN102509483A (en) * | 2011-10-31 | 2012-06-20 | 苏州思必驰信息科技有限公司 | Distributive automatic grading system for spoken language test and method thereof |
| CN102982799A (en) * | 2012-12-20 | 2013-03-20 | 中国科学院自动化研究所 | Speech recognition optimization decoding method integrating guide probability |
| CN104678868A (en) * | 2015-01-23 | 2015-06-03 | 贾新勇 | Business and equipment operation and maintenance monitoring system |
| CN105227790A (en) * | 2015-09-24 | 2016-01-06 | 北京车音网科技有限公司 | A kind of voice answer method, electronic equipment and system |
| CN105723362A (en) * | 2013-10-28 | 2016-06-29 | 余自立 | Natural expression processing method, processing and response method, device, and system |
-
2016
- 2016-08-31 CN CN201610791966.0A patent/CN106409283B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1920948A (en) * | 2005-08-24 | 2007-02-28 | 富士通株式会社 | Voice recognition system and voice processing system |
| CN101276584A (en) * | 2007-03-28 | 2008-10-01 | 株式会社东芝 | Prosody-pattern generating apparatus, speech synthesizing apparatus, and computer program product and method thereof |
| CN102509483A (en) * | 2011-10-31 | 2012-06-20 | 苏州思必驰信息科技有限公司 | Distributive automatic grading system for spoken language test and method thereof |
| CN102982799A (en) * | 2012-12-20 | 2013-03-20 | 中国科学院自动化研究所 | Speech recognition optimization decoding method integrating guide probability |
| CN105723362A (en) * | 2013-10-28 | 2016-06-29 | 余自立 | Natural expression processing method, processing and response method, device, and system |
| CN104678868A (en) * | 2015-01-23 | 2015-06-03 | 贾新勇 | Business and equipment operation and maintenance monitoring system |
| CN105227790A (en) * | 2015-09-24 | 2016-01-06 | 北京车音网科技有限公司 | A kind of voice answer method, electronic equipment and system |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107204185B (en) * | 2017-05-03 | 2021-05-25 | 深圳车盒子科技有限公司 | Vehicle-mounted voice interaction method and system and computer readable storage medium |
| CN107122807A (en) * | 2017-05-24 | 2017-09-01 | 努比亚技术有限公司 | A kind of family's monitoring method, service end and computer-readable recording medium |
| CN107122807B (en) * | 2017-05-24 | 2021-05-21 | 努比亚技术有限公司 | Home monitoring method, server and computer readable storage medium |
| CN107733780B (en) * | 2017-09-18 | 2020-07-03 | 上海量明科技发展有限公司 | Intelligent task allocation method and device and instant messaging tool |
| CN107733780A (en) * | 2017-09-18 | 2018-02-23 | 上海量明科技发展有限公司 | Task smart allocation method, apparatus and JICQ |
| CN109697226A (en) * | 2017-10-24 | 2019-04-30 | 上海易谷网络科技股份有限公司 | Text silence seat monitoring robot interactive method |
| CN107992587A (en) * | 2017-12-08 | 2018-05-04 | 北京百度网讯科技有限公司 | A kind of voice interactive method of browser, device, terminal and storage medium |
| CN110069607A (en) * | 2017-12-14 | 2019-07-30 | 株式会社日立制作所 | For the method, apparatus of customer service, electronic equipment, computer readable storage medium |
| CN110069607B (en) * | 2017-12-14 | 2024-03-05 | 株式会社日立制作所 | Method, apparatus, electronic device, and computer-readable storage medium for customer service |
| WO2020057446A1 (en) * | 2018-09-17 | 2020-03-26 | Huawei Technologies Co., Ltd. | Method and system for generating a semantic point cloud map |
| US10983526B2 (en) | 2018-09-17 | 2021-04-20 | Huawei Technologies Co., Ltd. | Method and system for generating a semantic point cloud map |
| CN110970017A (en) * | 2018-09-27 | 2020-04-07 | 北京京东尚科信息技术有限公司 | Human-computer interaction method and system and computer system |
| CN111125384A (en) * | 2018-11-01 | 2020-05-08 | 阿里巴巴集团控股有限公司 | Multimedia answer generation method and device, terminal equipment and storage medium |
| CN111125384B (en) * | 2018-11-01 | 2023-04-07 | 阿里巴巴集团控股有限公司 | Multimedia answer generation method and device, terminal equipment and storage medium |
| CN110602334A (en) * | 2019-09-03 | 2019-12-20 | 上海航动科技有限公司 | Intelligent outbound method and system based on man-machine cooperation |
| CN110926493A (en) * | 2019-12-10 | 2020-03-27 | 广州小鹏汽车科技有限公司 | Navigation method, navigation device, vehicle and computer readable storage medium |
| CN111540353A (en) * | 2020-04-16 | 2020-08-14 | 重庆农村商业银行股份有限公司 | Semantic understanding method, device, equipment and storage medium |
| CN112509575A (en) * | 2020-11-26 | 2021-03-16 | 上海济邦投资咨询有限公司 | Financial consultation intelligent guiding system based on big data |
| CN112735427A (en) * | 2020-12-25 | 2021-04-30 | 平安普惠企业管理有限公司 | Radio reception control method and device, electronic equipment and storage medium |
| CN112735410A (en) * | 2020-12-25 | 2021-04-30 | 中国人民解放军63892部队 | Automatic voice interactive force model control method and system |
| CN112735427B (en) * | 2020-12-25 | 2023-12-05 | 海菲曼（天津）科技有限公司 | Radio reception control method and device, electronic equipment and storage medium |
| CN116453540A (en) * | 2023-06-15 | 2023-07-18 | 山东贝宁电子科技开发有限公司 | Underwater frogman voice communication quality enhancement processing method |
| CN116453540B (en) * | 2023-06-15 | 2023-08-29 | 山东贝宁电子科技开发有限公司 | Underwater frogman voice communication quality enhancement processing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106409283B (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106409283A (en) | Audio frequency-based man-machine mixed interaction system and method | |
| CN110266899B (en) | Client intention identification method and customer service system | |
| US10911596B1 (en) | Voice user interface for wired communications system | |
| US10412206B1 (en) | Communications for multi-mode device | |
| CN101207586B (en) | Method and system for real-time automatic communication | |
| US20190332679A1 (en) | Auto-translation for multi user audio and video | |
| EP2411977B1 (en) | Service oriented speech recognition for in-vehicle automated interaction | |
| US20180054506A1 (en) | Enabling voice control of telephone device | |
| CN109961792B (en) | Method and apparatus for recognizing speech | |
| US20120253823A1 (en) | Hybrid Dialog Speech Recognition for In-Vehicle Automated Interaction and In-Vehicle Interfaces Requiring Minimal Driver Processing | |
| CN101207655A (en) | Method and system switching between voice and text exchanging forms in a communication conversation | |
| CN104010267A (en) | Method and system for supporting a translation-based communication service and terminal supporting the service | |
| US10194023B1 (en) | Voice user interface for wired communications system | |
| CN106230689A (en) | Method, device and the server that a kind of voice messaging is mutual | |
| US9390426B2 (en) | Personalized advertisement device based on speech recognition SMS service, and personalized advertisement exposure method based on partial speech recognition SMS service | |
| US10326886B1 (en) | Enabling additional endpoints to connect to audio mixing device | |
| CN110119514A (en) | The instant translation method of information, device and system | |
| CN112866086A (en) | Information pushing method, device, equipment and storage medium for intelligent outbound | |
| CN111554280A (en) | Real-time interpretation service system for mixing interpretation contents using artificial intelligence and interpretation contents of interpretation experts | |
| CN108881507B (en) | System comprising voice browser and block chain voice DNS unit | |
| CN116863935B (en) | Speech recognition method, device, electronic equipment and computer readable medium | |
| KR20090076318A (en) | Realtime conversational service system and method thereof | |
| CN110740212B (en) | Call answering method and device based on intelligent voice technology and electronic equipment | |
| US20020072916A1 (en) | Distributed speech recognition for internet access | |
| CN1427394A (en) | Speech sound browsing network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200619 Address after: Room 105G, 199 GuoShoujing Road, Pudong New Area, Shanghai, 200120 Patentee after: Shanghai Jiaotong University Intellectual Property Management Co.,Ltd. Address before: 200240 Dongchuan Road, Shanghai, No. 800, No. Patentee before: SHANGHAI JIAO TONG University |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201105 Address after: 215123 14 Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou, Jiangsu. Patentee after: AI SPEECH Ltd. Address before: Room 105G, 199 GuoShoujing Road, Pudong New Area, Shanghai, 200120 Patentee before: Shanghai Jiaotong University Intellectual Property Management Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Patentee after: Sipic Technology Co.,Ltd. Address before: 215123 building 14, Tengfei Innovation Park, 388 Xinping street, Suzhou Industrial Park, Suzhou City, Jiangsu Province Patentee before: AI SPEECH Ltd. |