CN109509471A - A method of the dialogue of intelligent sound robot is interrupted based on vad algorithm - Google Patents
A method of the dialogue of intelligent sound robot is interrupted based on vad algorithm Download PDFInfo
- Publication number
- CN109509471A CN109509471A CN201811626883.1A CN201811626883A CN109509471A CN 109509471 A CN109509471 A CN 109509471A CN 201811626883 A CN201811626883 A CN 201811626883A CN 109509471 A CN109509471 A CN 109509471A
- Authority
- CN
- China
- Prior art keywords
- user
- intelligent sound
- sound
- robot
- 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 16
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 230000000694 effects Effects 0.000 claims abstract description 16
- 238000005070 sampling Methods 0.000 claims description 16
- 230000000977 initiatory effect Effects 0.000 claims description 8
- 238000011897 real-time detection Methods 0.000 claims description 5
- 230000006854 communication Effects 0.000 abstract description 11
- 238000004891 communication Methods 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L15/222—Barge in, i.e. overridable guidance for interrupting prompts
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/1066—Session management
- H04L65/1101—Session protocols
- H04L65/1104—Session initiation protocol [SIP]
-
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- General Business, Economics & Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of methods for interrupting the dialogue of intelligent sound robot based on vad algorithm, which comprises user initiates speech exchange by webpage instant messaging module in web interface, and intelligent sound robot carries out voice broadcasting according to default words art；Voice Activity Detection module judges whether user makes a sound by vad algorithm detection, and filter background sound and noise；Identification user makes a sound, and interrupts the voice output of intelligent sound robot, and user's speech is waited to terminate；User's speech audio data is sent to Real-time speech recognition module identification user's speech content, and identifies that user is intended to by natural language understanding module；Identification user's speech terminates, and intelligent sound robot is intended to change according to identification user, selection switching newspeak art node；Identification user is intended to have not been changed, and continues current words art node.The present invention solves the technical issues of can not interrupting the output of intelligent sound robot voice, switching words art in user and the communication of intelligent sound robot in real time.
Description
Technical field
The present invention relates to Intelligent voice dialog fields, more particularly to a kind of vad algorithm that is based on to interrupt intelligent sound robot
The method of dialogue.
Background technique
With the rapid development of computer and artificial intelligence technology, Intelligent voice dialog is by extensive development and application, intelligence
Energy robot has been come into more and more in people's lives and work, and the robot application field in life and work is got over
Come wider, the intelligent robot epoch at hand, and are largely widely used in society.
Currently, ASR(Real-time speech recognition can be passed through) and NLP(natural language understanding), realize that machine understands people in real time
Class voice language carries out AI in scenes such as customer service, sale and intelligently links up, and carries out large-scale corpus training to human sound language,
Under given scenario, the preferable identification model of available identification quality, robot sends the sound of the mankind in ASR in real time
Identified, obtain the recognition result of textual form, be used for keyword match or semantic processes, obtain default problem with
Answer is played back with audio form, is linked up with matching man-machine voice.
Although existing scheme can support robot and the language communication of the mankind, asked substantially between people and robot one
Based on one form answered, it is difficult to accomplish the exchange of chipping in of human levels, it is more inflexible and unnatural.For chipping in suddenly for visitor
Access, if robot is unmoved, it appears rude, exchange is unfriendly, and user must hear out the default words art of complete robot,
And can not be interrupted or statement into question within the period of robot words art output, it is difficult to realize in communication timely, quick；Another party
Face, chipping in for visitor interrupt, and may have the inquiry of more urgent problems, if being switched on relevant issues node not in time, can waste
Client's time.In conclusion the speech exchange scheme of existing intelligent sound machine person to person in interactive experience, communication efficiency still
It is to be improved.
Summary of the invention
In order to improve intelligent sound robot, art is horizontal, and it is defeated to realize that user interrupts intelligent sound robot voice at any time
Out, intelligent sound robot switches the function of words art in communication, and the invention proposes one kind to interrupt intelligent language based on vad algorithm
The method of sound robot dialogue.
The present invention adopts the following technical scheme:
A method of the dialogue of intelligent sound robot is interrupted based on vad algorithm, which comprises
S1, user initiate speech exchange by webpage instant messaging module in web interface, and intelligent sound robot is according to pre-
If talking about art carries out voice broadcasting；
Voice Activity Detection module in S2, intelligent sound robot judges whether user sends out by vad algorithm real-time detection
Sound out, and filter background sound and noise；
If S3, Voice Activity Detection module identification user make a sound, the voice output of intelligent sound robot is interrupted, etc.
To the end of user's speech；
User's speech audio data is sent to Real-time speech recognition module identification user's hair in real time by S4, intelligent sound robot
It says content, and identifies that user is intended to by natural language understanding module；
S5, Voice Activity Detection module identification user's speech terminate, and intelligent sound robot is intended to change according to identification user,
Selection switching newspeak art node；Identification user is intended to have not been changed, and continues current words art node.
Preferably, the intelligent sound robot further includes the first SIP client, the web interface further includes second
SIP client, first SIP client are broadcast by Session initiation Protocol, real-time transport protocol to the second SIP client
Art of saying content, the webpage instant messaging module is by Session initiation Protocol, real-time transport protocol to intelligent sound robot
Transmit the realaudio data of user.
Preferably, described judge that the step of whether user makes a sound is as follows by vad algorithm:
(1) Voice Activity Detection module calculates a plurality of sampling sections in nearest 1 second based on the audio data that user makes a speech
The sound frequency of point；
(2) threshold value is set, when the sound frequency of sampling node reaches threshold valueWhen, then sampling node is calculated as primary effective
Audio；
(3) when continuous n sampling nodes are effective audio, it is calculated as primary sound segment；
(4) when the sound segment in a period of time is more than m, then judge that active user is in floor status.
The beneficial effects of the present invention are: 1, for the deficiency of existing scheme, the present invention provides interrupting based on vad algorithm
Intelligent sound robot talks with scheme, to promote interactive experience, improve communication efficiency；2, the present invention includes and is not limited by each
Class VAD intelligent sound detection technique checks in intelligent sound robot and the real-time communication process of user, identification that user is intended to,
Switching, intelligent sound robot timely respond to visitor's problem and are intended to, and accomplish the experience closer to the daily communication of the mankind；3, user
Or intelligent sound robot initiate speech exchange after, always in real time check user whether sounding, identify and do speech analysis, check
The more specific problem of current session user and it is intended to, and finds related reply in art if default；4, in dialog procedure, intelligence
Speech robot people also identifies user's most new meaning all the time by natural language understanding module when carrying out the speech exchange of present node
Figure, and when recognizing latest intention, it timely responds to, the dialogue of progress is retained into scene, is switched in new dialogue node；5,
After the completion of new dialogue node, intelligent sound robot can converse before automatic switchback node, continue to exchange, also hold including user
It is continuous to interrupt dialogue, and constantly switch to new node；6, real-time detection during robot is exchanged with visitor's real-time voice
Voice of customers, and identify intention, timely respond to newest visitor's problem.The service of more friendly, more intimate Human communication can be brought
Experience, greatly promotes communication efficiency and interactive experience.
Detailed description of the invention
Fig. 1 is flow diagram of the invention；
Fig. 2 is to judge whether user makes a sound flow diagram by vad algorithm in the present invention；
Fig. 3 is the structural schematic diagram of intelligent sound robot and web interface in the present invention.
In Fig. 1-3: 1, intelligent sound robot, the 2, first SIP client, 3, Real-time speech recognition module, 4, natural language
Say Understanding Module, 5, Voice Activity Detection module, 6, web interface, 7, webpage instant messaging module, the 8, second SIP client.
Specific embodiment
Below by specific embodiment, and in conjunction with attached drawing, technical scheme of the present invention is further described:
Embodiment: a kind of method that the dialogue of intelligent sound robot is interrupted based on vad algorithm as illustrated in the accompanying drawings from 1 to 3, institute
The method of stating includes:
S1, user initiate speech exchange, intelligent sound robot 1 by webpage instant messaging module 7 in web interface 6
Voice broadcasting is carried out according to default words art；
Voice Activity Detection module 5 in S2, intelligent sound robot 1 judges that user is by vad algorithm real-time detection
It is no to make a sound, and filter background sound and noise；
If S3, Voice Activity Detection module 5 identification user make a sound, the voice output of intelligent sound robot 1 is interrupted,
User's speech is waited to terminate；
User's speech audio data is sent to the identification of Real-time speech recognition module 3 in real time and used by S4, intelligent sound robot 1
Family speech content, and identify that user is intended to by natural language understanding module 4；
S5, Voice Activity Detection module 5 identify that user's speech terminates, and intelligent sound robot 1 is intended to according to identification user
Change, selection switching newspeak art node；Identification user is intended to have not been changed, and continues current words art node.
When user or intelligent sound robot 1 initiate speech exchange, intelligent sound robot 1 can be in real time by visitor's sound
It is sent into Real-time speech recognition module 3 and natural language understanding module 4 and carries out speech recognition and speech processes, analyze voice content
It is intended to user；When intelligent sound robot 1 plays voice, at the same real-time detection user whether sounding, and filter background sound
1 voice of intelligent sound robot is interrupted when the vad algorithm in Voice Activity Detection module 5, which recognizes user, speaks with noise
Output waits user to speak end；The audio data of user is transported to Real-time speech recognition module 3 simultaneously and natural language is managed
It solves identification user's speech content in module 4 and is intended to, match relevant issues and reply words art；At the end of user speaks, voice
Activity detection module 5 identifies that user's speech terminates, and the art content according to newest matching of intelligent sound robot 1 carries out language
Sound is replied.
The intelligent sound robot 1 further includes the first SIP client 2, and the web interface 6 further includes the 2nd SIP
Client 8, first SIP client 2 are broadcast by Session initiation Protocol, real-time transport protocol to the second SIP client 8
Art of saying content, the webpage instant messaging module 7 is by Session initiation Protocol, real-time transport protocol to intelligent sound robot
The realaudio data of 1 transmission user, by the first SIP client 2 and web interface 6 in intelligent sound robot 1
Second SIP client 8, webpage instant messaging module 7 realize the full duplex real-time voice between user, intelligent sound robot 1
Call, intelligent sound robot 1 are objective from the first SIP client 2 to the 2nd SIP by Session initiation Protocol, real-time transport protocol
Family end 8 sends art content if reply, and user is by webpage by Session initiation Protocol, real-time transport protocol in web interface 6
When communication module 7 to intelligent sound robot 1 transmit user realaudio data.
It is described to judge that the step of whether user makes a sound is as follows by vad algorithm:
(1) Voice Activity Detection module 5 calculates a plurality of samplings in nearest 1 second based on the audio data that user makes a speech
The sound frequency of node；
(2) threshold value is set, when the sound frequency of sampling node reaches threshold valueWhen, then sampling node is calculated as primary effective
Audio；
(3) when continuous n sampling nodes are effective audio, it is calculated as primary sound segment；
(4) when the sound segment in a period of time is more than m, then judge that active user is in floor status.
Using every 1 second as one basic calculation unit, every 1 second sampling node quantity is adjusted according to actual needs, to not
The same age, different sexes the different threshold value of user setting, the sound frequency of sampling node reaches threshold valueShi Jiwei once has
Audio data is imitated, primary sound segment is calculated as when continuous n sampling node is effective audio data, in a period of time
When sound segment is more than m, judge that user is in floor status, similarly, when the sound segment in a period of time is lower than m,
Judge that user is in non-floor status.In the present embodiment, threshold value, sampling node quantity n and sound number of fragments m according to
Place to use, object crowd difference different parameters can be set.
Above-mentioned embodiment is only a preferred solution of the present invention, not the present invention is made in any form
Limitation, there are also other variations and modifications on the premise of not exceeding the technical scheme recorded in the claims.
Claims (3)
1. a kind of method for interrupting the dialogue of intelligent sound robot based on vad algorithm, characterized in that the described method includes:
S1, user initiate speech exchange by webpage instant messaging module in web interface, and intelligent sound robot is according to default
It talks about art and carries out voice broadcasting；
Voice Activity Detection module in S2, intelligent sound robot judges whether user issues by vad algorithm real-time detection
Sound, and filter background sound and noise；
If S3, Voice Activity Detection module identification user make a sound, the voice output of intelligent sound robot is interrupted, is waited stand-by
Family speech terminates；
User's speech audio data is sent to the identification user's speech of Real-time speech recognition module in real time by S4, intelligent sound robot
Content, and identify that user is intended to by natural language understanding module；
S5, Voice Activity Detection module identification user's speech terminate, and intelligent sound robot is intended to change according to identification user, choosing
Select switching newspeak art node；Identification user is intended to have not been changed, and continues current words art node.
2. a kind of method for interrupting the dialogue of intelligent sound robot based on vad algorithm according to claim 1, feature
It is that the intelligent sound robot further includes the first SIP client, and the web interface further includes the second SIP client, described
First SIP client plays words art content, the net to the second SIP client by Session initiation Protocol, real-time transport protocol
Page instant messaging module by Session initiation Protocol, real-time audio from real-time transport protocol to intelligent sound robotic transfer user
Data.
3. a kind of method for interrupting the dialogue of intelligent sound robot based on vad algorithm according to claim 1, feature
It is, described to judge that the step of whether user makes a sound is as follows by VAD nature algorithm:
(1) Voice Activity Detection module calculates a plurality of sampling nodes in nearest 1 second based on the audio data that user makes a speech
Sound frequency；
(2) threshold value is set, when the sound frequency of sampling node reaches threshold valueWhen, then sampling node is calculated as primary effective sound
Frequently；
(3) when continuous n sampling nodes are effective audio, it is calculated as primary sound segment；
(4) when the sound segment in a period of time is more than m, then judge that active user is in floor status.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811626883.1A CN109509471A (en) | 2018-12-28 | 2018-12-28 | A method of the dialogue of intelligent sound robot is interrupted based on vad algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811626883.1A CN109509471A (en) | 2018-12-28 | 2018-12-28 | A method of the dialogue of intelligent sound robot is interrupted based on vad algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109509471A true CN109509471A (en) | 2019-03-22 |
Family
ID=65756636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811626883.1A Pending CN109509471A (en) | 2018-12-28 | 2018-12-28 | A method of the dialogue of intelligent sound robot is interrupted based on vad algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109509471A (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977218A (en) * | 2019-04-22 | 2019-07-05 | 浙江华坤道威数据科技有限公司 | A kind of automatic answering system and method applied to session operational scenarios |
| CN110125946A (en) * | 2019-04-23 | 2019-08-16 | 北京淇瑀信息科技有限公司 | Automatic call method, device, electronic equipment and computer-readable medium |
| CN110287299A (en) * | 2019-06-17 | 2019-09-27 | 浙江百应科技有限公司 | Loquacity term sentence intelligent switch method in a kind of call |
| CN110379429A (en) * | 2019-07-16 | 2019-10-25 | 招联消费金融有限公司 | Method of speech processing, device, computer equipment and storage medium |
| CN110517697A (en) * | 2019-08-20 | 2019-11-29 | 中信银行股份有限公司 | Prompt tone intelligence cutting-off device for interactive voice response |
| CN110853638A (en) * | 2019-10-23 | 2020-02-28 | 吴杰 | Method and equipment for interrupting voice robot in real time in voice interaction process |
| CN110867197A (en) * | 2019-10-23 | 2020-03-06 | 吴杰 | Method and equipment for interrupting voice robot in real time in voice interaction process |
| CN111080926A (en) * | 2019-12-09 | 2020-04-28 | 神思电子技术股份有限公司 | Auxiliary interaction method and device for self-service equipment |
| CN111312242A (en) * | 2020-02-13 | 2020-06-19 | 上海凯岸信息科技有限公司 | Intelligent voice robot scheme capable of interrupting intention without influencing dialogue management |
| CN111464701A (en) * | 2020-03-12 | 2020-07-28 | 云知声智能科技股份有限公司 | Method and device for carrying out simulation multi-round test on robot outbound telephone system |
| CN111752523A (en) * | 2020-05-13 | 2020-10-09 | 深圳追一科技有限公司 | Human-computer interaction method and device, computer equipment and storage medium |
| CN111916072A (en) * | 2020-06-16 | 2020-11-10 | 深圳追一科技有限公司 | Question-answering method and device based on voice recognition, computer equipment and storage medium |
| CN112017629A (en) * | 2020-07-15 | 2020-12-01 | 马上消费金融股份有限公司 | Conversation control method and equipment of voice robot and storage medium |
| CN112185392A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing system for power supply intelligent client |
| CN112185393A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing method for power supply intelligent client |
| CN112242135A (en) * | 2019-07-18 | 2021-01-19 | 北京声智科技有限公司 | Voice data processing method and intelligent customer service device |
| CN111508477B (en) * | 2019-08-02 | 2021-03-19 | 马上消费金融股份有限公司 | Voice broadcasting method, device, equipment and computer readable storage medium |
| WO2021051506A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Voice interaction method and apparatus, computer device and storage medium |
| CN112567457A (en) * | 2019-12-13 | 2021-03-26 | 华为技术有限公司 | Voice detection method, prediction model training method, device, equipment and medium |
| CN112951226A (en) * | 2021-01-29 | 2021-06-11 | 成都锐美动力科技有限公司 | Voice processing system supporting natural conversation |
| CN113096644A (en) * | 2021-03-31 | 2021-07-09 | 闽江学院 | Telephone voice processing system |
| CN113345437A (en) * | 2021-08-06 | 2021-09-03 | 百融云创科技股份有限公司 | Voice interruption method and device |
| CN113488024A (en) * | 2021-05-31 | 2021-10-08 | 杭州摸象大数据科技有限公司 | Semantic recognition-based telephone interruption recognition method and system |
| CN115134466A (en) * | 2022-06-07 | 2022-09-30 | 马上消费金融股份有限公司 | Intention recognition method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102868836A (en) * | 2012-09-17 | 2013-01-09 | 北京讯鸟软件有限公司 | Real person talk skill system for call center and realization method thereof |
| CN105070290A (en) * | 2015-07-08 | 2015-11-18 | 苏州思必驰信息科技有限公司 | Man-machine voice interaction method and system |
| CN108989592A (en) * | 2018-07-25 | 2018-12-11 | 南京瓦尔基里网络科技有限公司 | A kind of intelligence words art interactive system and method for call center |
| CN109005190A (en) * | 2018-08-31 | 2018-12-14 | 杭州数心网络科技有限公司 | A method of full-duplex voice dialogue and page control are realized based on webpage |
-
2018
- 2018-12-28 CN CN201811626883.1A patent/CN109509471A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102868836A (en) * | 2012-09-17 | 2013-01-09 | 北京讯鸟软件有限公司 | Real person talk skill system for call center and realization method thereof |
| CN105070290A (en) * | 2015-07-08 | 2015-11-18 | 苏州思必驰信息科技有限公司 | Man-machine voice interaction method and system |
| CN108989592A (en) * | 2018-07-25 | 2018-12-11 | 南京瓦尔基里网络科技有限公司 | A kind of intelligence words art interactive system and method for call center |
| CN109005190A (en) * | 2018-08-31 | 2018-12-14 | 杭州数心网络科技有限公司 | A method of full-duplex voice dialogue and page control are realized based on webpage |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977218A (en) * | 2019-04-22 | 2019-07-05 | 浙江华坤道威数据科技有限公司 | A kind of automatic answering system and method applied to session operational scenarios |
| CN109977218B (en) * | 2019-04-22 | 2019-10-25 | 浙江华坤道威数据科技有限公司 | A kind of automatic answering system and method applied to session operational scenarios |
| CN110125946A (en) * | 2019-04-23 | 2019-08-16 | 北京淇瑀信息科技有限公司 | Automatic call method, device, electronic equipment and computer-readable medium |
| CN110125946B (en) * | 2019-04-23 | 2021-08-27 | 北京淇瑀信息科技有限公司 | Automatic call method, automatic call device, electronic equipment and computer readable medium |
| CN110287299A (en) * | 2019-06-17 | 2019-09-27 | 浙江百应科技有限公司 | Loquacity term sentence intelligent switch method in a kind of call |
| CN110379429A (en) * | 2019-07-16 | 2019-10-25 | 招联消费金融有限公司 | Method of speech processing, device, computer equipment and storage medium |
| CN110379429B (en) * | 2019-07-16 | 2022-02-11 | 招联消费金融有限公司 | Voice processing method, device, computer equipment and storage medium |
| CN112242135A (en) * | 2019-07-18 | 2021-01-19 | 北京声智科技有限公司 | Voice data processing method and intelligent customer service device |
| CN111508477B (en) * | 2019-08-02 | 2021-03-19 | 马上消费金融股份有限公司 | Voice broadcasting method, device, equipment and computer readable storage medium |
| CN110517697A (en) * | 2019-08-20 | 2019-11-29 | 中信银行股份有限公司 | Prompt tone intelligence cutting-off device for interactive voice response |
| WO2021051506A1 (en) * | 2019-09-18 | 2021-03-25 | 平安科技（深圳）有限公司 | Voice interaction method and apparatus, computer device and storage medium |
| CN110867197A (en) * | 2019-10-23 | 2020-03-06 | 吴杰 | Method and equipment for interrupting voice robot in real time in voice interaction process |
| CN110853638A (en) * | 2019-10-23 | 2020-02-28 | 吴杰 | Method and equipment for interrupting voice robot in real time in voice interaction process |
| CN111080926A (en) * | 2019-12-09 | 2020-04-28 | 神思电子技术股份有限公司 | Auxiliary interaction method and device for self-service equipment |
| CN112567457A (en) * | 2019-12-13 | 2021-03-26 | 华为技术有限公司 | Voice detection method, prediction model training method, device, equipment and medium |
| CN112567457B (en) * | 2019-12-13 | 2021-12-10 | 华为技术有限公司 | Voice detection method, prediction model training method, device, equipment and medium |
| CN111312242A (en) * | 2020-02-13 | 2020-06-19 | 上海凯岸信息科技有限公司 | Intelligent voice robot scheme capable of interrupting intention without influencing dialogue management |
| CN111464701A (en) * | 2020-03-12 | 2020-07-28 | 云知声智能科技股份有限公司 | Method and device for carrying out simulation multi-round test on robot outbound telephone system |
| CN111752523A (en) * | 2020-05-13 | 2020-10-09 | 深圳追一科技有限公司 | Human-computer interaction method and device, computer equipment and storage medium |
| CN111916072A (en) * | 2020-06-16 | 2020-11-10 | 深圳追一科技有限公司 | Question-answering method and device based on voice recognition, computer equipment and storage medium |
| CN112017629A (en) * | 2020-07-15 | 2020-12-01 | 马上消费金融股份有限公司 | Conversation control method and equipment of voice robot and storage medium |
| CN112185392A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing system for power supply intelligent client |
| CN112185393A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Voice recognition processing method for power supply intelligent client |
| CN112951226A (en) * | 2021-01-29 | 2021-06-11 | 成都锐美动力科技有限公司 | Voice processing system supporting natural conversation |
| CN113096644A (en) * | 2021-03-31 | 2021-07-09 | 闽江学院 | Telephone voice processing system |
| CN113488024A (en) * | 2021-05-31 | 2021-10-08 | 杭州摸象大数据科技有限公司 | Semantic recognition-based telephone interruption recognition method and system |
| CN113345437A (en) * | 2021-08-06 | 2021-09-03 | 百融云创科技股份有限公司 | Voice interruption method and device |
| CN113345437B (en) * | 2021-08-06 | 2021-10-29 | 百融云创科技股份有限公司 | Voice interruption method and device |
| CN115134466A (en) * | 2022-06-07 | 2022-09-30 | 马上消费金融股份有限公司 | Intention recognition method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109509471A (en) | A method of the dialogue of intelligent sound robot is interrupted based on vad algorithm | |
| CN109977218B (en) | A kind of automatic answering system and method applied to session operational scenarios | |
| CN110035187A (en) | A method of realizing AI and operator attendance seamless switching in the phone | |
| US6850602B1 (en) | Method and apparatus for answering machine detection in automatic dialing | |
| CN106328166B (en) | Human-computer dialogue abnormality detection system and method | |
| CN110557451B (en) | Dialogue interaction processing method and device, electronic equipment and storage medium | |
| CN104766608A (en) | Voice control method and voice control device | |
| CN105744090A (en) | Voice information processing method and device | |
| CN108777751A (en) | A kind of call center system and its voice interactive method, device and equipment | |
| CN110287299A (en) | Loquacity term sentence intelligent switch method in a kind of call | |
| TWI703473B (en) | Programmable intelligent agent for human-chatbot communication | |
| CN108418981B (en) | The method and device of dialogue service is provided for client | |
| CN103295585A (en) | Processing system and method identifying whether telephone automatic dialing is responded by real human | |
| CN110299152A (en) | Interactive output control method, device, electronic equipment and storage medium | |
| CN112885348A (en) | AI-combined intelligent voice electric marketing method | |
| CN107645523A (en) | A kind of method and system of mood interaction | |
| CN102640084B (en) | For Communications Interface Unit and the method for multi-user and system | |
| CN109005190A (en) | A method of full-duplex voice dialogue and page control are realized based on webpage | |
| CN111128241A (en) | Intelligent quality inspection method and system for voice call | |
| CN101834809A (en) | Internet instant message communication system | |
| CN109525737A (en) | A kind of call Cut-in control method and system | |
| CN111654581A (en) | Intelligent dialogue robot control method and system | |
| CN112242135A (en) | Voice data processing method and intelligent customer service device | |
| CN112202974B (en) | Method, device and system for automatically judging telephone answering state | |
| JP7304627B2 (en) | Answering machine judgment device, method and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190322 |