CN110335600A - The multi-modal exchange method and system of household appliance - Google Patents
The multi-modal exchange method and system of household appliance Download PDFInfo
- Publication number
- CN110335600A CN110335600A CN201910616247.9A CN201910616247A CN110335600A CN 110335600 A CN110335600 A CN 110335600A CN 201910616247 A CN201910616247 A CN 201910616247A CN 110335600 A CN110335600 A CN 110335600A
- Authority
- CN
- China
- Prior art keywords
- voice
- module
- speech
- household appliance
- speaker
- 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 32
- 230000002452 interceptive effect Effects 0.000 claims abstract description 45
- 230000003993 interaction Effects 0.000 claims abstract description 21
- 230000000694 effects Effects 0.000 claims abstract description 19
- 238000002347 injection Methods 0.000 claims abstract description 5
- 239000007924 injection Substances 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 16
- 230000001815 facial effect Effects 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000013179 statistical model Methods 0.000 claims description 3
- 230000003213 activating effect Effects 0.000 abstract description 3
- 230000004913 activation Effects 0.000 abstract description 3
- 230000002262 irrigation Effects 0.000 abstract 1
- 238000003973 irrigation Methods 0.000 abstract 1
- 238000004378 air conditioning Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000002045 lasting effect Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention proposes the multi-modal exchange method and system of a kind of household appliance, belongs to household electrical appliance field of speech recognition.The present invention solve the problems, such as the single interactive voice of tradition deposit mode misrecognition, rely on activation word and disagreeableness, the drip irrigation device of interaction are as follows: obtain the image and voice signal under current environment;According to voice signal, detect whether that there are speech activities;If detecting the presence of speech activity, according to picture signal, judges whether someone's positive injection depending on equipment and speaking;If detecting that someone is just watching equipment attentively and speaking, start voice interactive function, and store present user speech feature and characteristics of image;When starting voice interactive function, according to phonetic feature, the speech content of current speaker is identified;Also, intention assessment is used, judge the intention of current speaker and corresponding service is provided.It can judge automatically and whether need to start interactive voice, without activating word, and user can be helped to carry out services selection.
Description
Technical field
The present invention relates to household electrical appliance speech recognition technologies, the in particular to multi-modal exchange method and system of household appliance
Technology.
Background technique
In smart machine interactive process, interactive mode more common at present is interactive voice, is joined by the voice of acquisition
The operating or search service of number control household appliance.But there is misrecognition in single speech parameter, especially when surrounding ring
Border noise is big, distance farther out when, the probability of bigger misrecognition.Meanwhile current interactive voice is first to need that word is activated to wake up
The strong interactive mode of equipment, inconvenient, interactive mode is unfriendly.To sum up, existing household appliance exchange method and system are deposited
In misrecognition, rely on activation word and the disagreeableness problem of interaction.
Summary of the invention
The object of the present invention is to provide the multi-modal exchange methods and system of a kind of household appliance, solve the single language of tradition
Sound interaction deposit mode misrecognition, rely on activation word and the disagreeableness problem of interaction.
The present invention solves its technical problem, the technical solution adopted is that: the multi-modal exchange method of household appliance, including with
Lower step:
S1. the image and voice signal under current environment are obtained;
S2. according to voice signal, detect whether that there are speech activities;
S3. if detecting the presence of speech activity, according to picture signal, judge whether someone's positive injection depending on equipment and saying
Words;
S4. if detecting that someone is just watching equipment attentively and speaking, start voice interactive function, and store active user
Phonetic feature and characteristics of image;
S5. when starting voice interactive function, according to phonetic feature, the speech content of current speaker is identified;
S6. when starting voice interactive function, using intention assessment, judge the intention of current speaker and phase is provided
The service answered.
Particularly, in step S1, by the voice receiver device built in household appliance, the language under current environment is obtained
Sound signal;By the cam device built in household appliance, the picture signal under current environment is obtained.
Further, step S2 specifically includes the following steps:
S201. voice signal traditional characteristic or depth characteristic are extracted;
S202. feature is made decisions based on thresholding, statistical model and machine learning, detects whether that there are speech activities.
Particularly, step S3 specifically includes the following steps:
S301. according to described image signal, the facial orientation of current speaker is calculated with computer vision technique, judgement is worked as
Whether someone is just watching equipment attentively in preceding environment;
S302. if someone is just watching equipment attentively, according to picture signal, judgement is calculated using computer vision technique and is watched attentively
Whether the people of equipment is speaking.
Further, the phonetic feature includes age, gender and the identity of speaker in step S4;Described image
Feature includes face, position, gender, age and the identity of speaker.
Particularly, in step S5, by extracting the speech parameter in phonetic feature, identify that speaking for current speaker is interior
Hold.
Further, step S6 specifically includes the following steps:
S601. intention assessment is used, speech content is analyzed, extracts the intention of current speaker;
S602. household appliance built-in command word database;
S603. by the intention and database matching of current speaker, confirm that user thinks the order of input;
S604., service needed for current speaker is provided.
The multi-modal interactive system of household appliance, the multi-modal exchange method applied to the household appliance includes signal
Module, Speaker change detection module, voice interaction module, characteristic storage module, speech recognition module and intention assessment module are obtained,
Signal acquisition module is connected with Speaker change detection module, and Speaker change detection module is connected with voice interaction module, interactive voice mould
Block is connected with characteristic storage module, and characteristic storage module is connected with speech recognition module, speech recognition module and intention assessment mould
Block is connected;
The signal acquisition module, for obtaining voice and picture signal;
The Speaker change detection module, for judging whether that someone is speaking to household appliance;
The voice interaction module starts voice interactive function for judging whether according to described image, voice signal;
The characteristic storage module, for storing the phonetic feature and characteristics of image of current speaker;
The speech recognition module, for identification user's speech content;
The intention assessment module, for understanding that user is intended to, recommendation service content.
The invention has the advantages that figure can be passed through by the multi-modal exchange method and system of above-mentioned household appliance
The input of picture, voice signal is judged automatically using computer vision technique and speech recognition technology and whether is needed to start voice friendship
Mutually, it without activating word, makes interaction more accurate, more efficient, improves the intelligent level of household appliance, and pass through speech recognition skill
Art and intention assessment technology confirm user search intent, help user to carry out services selection, improve interactive accuracy rate and efficiency,
Bring more good interactive experience.
Detailed description of the invention
Fig. 1 is the flow chart of the multi-modal exchange method of present inventor's electric equipment.
Specific embodiment
Below with reference to examples and drawings, the technical schemes of the invention are described in detail.
The multi-modal exchange method of household appliance of the present invention, flow chart is referring to Fig. 1, wherein this method include with
Lower step:
S1. the image and voice signal under current environment are obtained.
Wherein, it is more convenient to save input cost and acquire voice signal, preferably passes through the voice built in household appliance
Acceptor device obtains the voice signal under current environment;In order to precisely obtain picture signal, preferably pass through household appliance
Built-in cam device obtains the picture signal under current environment.
S2. according to voice signal, detect whether that there are speech activities.
Wherein, step S2 specifically includes the following steps:
S201. voice signal traditional characteristic or depth characteristic are extracted;
S202. feature is made decisions based on thresholding, statistical model and machine learning, detects whether that there are speech activities.
S3. if detecting the presence of speech activity, according to picture signal, judge whether someone's positive injection depending on equipment and saying
Words.
Wherein, step S3 specifically includes the following steps:
S301. according to described image signal, the facial orientation of current speaker is calculated with computer vision technique, judgement is worked as
Whether someone is just watching equipment attentively in preceding environment;
S302. if someone is just watching equipment attentively, according to picture signal, judgement is calculated using computer vision technique and is watched attentively
Whether the people of equipment is speaking.
S4. if detecting that someone is just watching equipment attentively and speaking, start voice interactive function, and store active user
Phonetic feature and characteristics of image.
Wherein, the phonetic feature includes age, gender and identity of speaker etc.;Described image feature includes speaker
Face, position, gender, age and identity etc..
S5. when starting voice interactive function, according to phonetic feature, the speech content of current speaker is identified.
Wherein, under general operating condition, speaking for current speaker can be identified by extracting the speech parameter in phonetic feature
Content.
S6. when starting voice interactive function, using intention assessment, judge the intention of current speaker and phase is provided
The service answered.
Wherein, step S6 specifically includes the following steps:
S601. intention assessment is used, speech content is analyzed, extracts the intention of current speaker;
S602. household appliance built-in command word database;
S603. by the intention and database matching of current speaker, confirm that user thinks the order of input;
S604., service needed for current speaker is provided.
The multi-modal interactive system of household appliance, the multi-modal exchange method applied to the household appliance includes signal
Module, Speaker change detection module, voice interaction module, characteristic storage module, speech recognition module and intention assessment module are obtained,
Signal acquisition module is connected with Speaker change detection module, and Speaker change detection module is connected with voice interaction module, interactive voice mould
Block is connected with characteristic storage module, and characteristic storage module is connected with speech recognition module, speech recognition module and intention assessment mould
Block is connected;
The signal acquisition module, for obtaining voice and picture signal;
The Speaker change detection module, for judging whether that someone is speaking to household appliance;
The voice interaction module starts voice interactive function for judging whether according to described image, voice signal;
The characteristic storage module, for storing the phonetic feature and characteristics of image of current speaker;
The speech recognition module, for identification user's speech content;
The intention assessment module, for understanding that user is intended to, recommendation service content.
Embodiment 1
Present embodiments provide a kind of multi-modal exchange method of household appliance, comprising the following steps:
S1. the image and voice signal under current environment are obtained.Wherein, it is filled by voice receiver built in household appliance
It sets, as remote controler or far field microphone array obtain the voice signal under current environment;It is filled by household appliance built-in camera
It sets, if RGB camera or infrared camera, obtains the picture signal under current environment.
S2. according to voice signal, detect whether that there are speech activities.Wherein, firstly, extract voice signal traditional characteristic or
Depth characteristic can calculate the energy of each moment voice as feature in the present embodiment;Then, threshold value k is set, if
Energy is greater than k and is denoted as 1, i.e. voice, 0, i.e. non-voice is otherwise denoted as, and judge the lasting interval of voice, if more than given threshold
T then detects the presence of speech activity.
S3. if detecting the presence of speech activity, according to picture signal, judge whether someone's positive injection depending on equipment and saying
Words.Wherein, firstly, according to picture signal, Face datection and crucial point location are carried out to the picture signal of acquisition, before judging equipment
Whether someone, while to the people of positioning by key point carry out head pose estimation obtain facial orientation, judge its relative device
Deflection angle, if its be less than threshold value r, be determined as face equipment;Then, if someone is just watching equipment attentively, according to image
Signal judges the key point of the continuous several frames of face people, sees whether its upperlip spacing is greater than threshold from dynamic range
Value d, if more than then determining that it is speaking, i.e., someone is just watching equipment attentively and is speaking.
S4. if detecting that someone is just watching equipment attentively and speaking, start voice interactive function, and store active user
Phonetic feature and characteristics of image.Wherein, firstly, storing the phonetic feature of speaker, including age " 25 ", gender " male ", identity
" user 1 " etc.;Secondly, the characteristics of image of storage speaker, including facial image and coordinate, position " equipment is 30 degree left ", gender
" male ", age " 25 ", identity user 1 " etc..
S5. when starting voice interactive function, according to phonetic feature, the speech content of current speaker is identified.Its
In, by extracting the speech parameter in phonetic feature, identify user's speech content, such as " I wants to see for the instruction of TV interaction
Journey to the West ", " sound is more greatly ", the instruction " temperature height a bit " interactive for air-conditioning, " wind is a little bit smaller " etc..
S6. when starting voice interactive function, using intention assessment, judge the intention of current speaker and phase is provided
The service answered.Wherein, firstly, using intention assessment, speech content is analyzed, user is extracted and is intended to, as " I thinks for TV interactive instruction
See Journey to the West ", analyze " Journey to the West ";Air-conditioning interactive instruction " wind is a little bit smaller " analyzes " wind ", " small ";Secondly, household appliance
Built-in command word database, such as " Journey to the West ", " wind ", " small ";Then, user is intended to and database matching, confirmation user thinks
The order of input;Finally, service needed for providing current speaker, such as searches for Journey to the West film source and selects for user, turns down air-conditioning
Wind speed.
Embodiment 2
The present embodiment provides a kind of multi-modal interactive systems of household appliance, specifically include within the system: signal acquisition
Module, Speaker change detection module, voice interaction module, characteristic storage module, speech recognition module and intention assessment module, signal
Obtain module be connected with Speaker change detection module, Speaker change detection module is connected with voice interaction module, voice interaction module and
Characteristic storage module is connected, and characteristic storage module is connected with speech recognition module, speech recognition module and intention assessment module phase
Even.
Signal acquisition module obtains image and voice signal under current scene by sensor, wherein image acquisition is set
Standby such as RGB camera, speech ciphering equipment receiver such as remote controler or far field microphone array.
Speaker change detection module is mainly used for judging whether that someone speaks to household appliance, if not face household electrical appliances are spoken
Or face household electrical appliances are not spoken, then are not connected to voice interaction module.Judgment method is as follows:
A. the energy of each moment voice can be calculated in the present embodiment by extracting voice signal traditional characteristic or depth characteristic
Amount is used as feature;
B. threshold value k is set, if energy is greater than k and is denoted as 1, i.e. voice, is otherwise denoted as 0, i.e. non-voice, and judge voice
Lasting interval then detects the presence of speech activity if more than given threshold t;
If C. detecting speech activity, according to image parameter, Face datection and key point are carried out to the picture signal of acquisition
Positioning, judge before equipment whether someone, while facial orientation is obtained by key point progress head pose estimation to the people of positioning,
Judge the deflection angle of its relative device, if it is less than threshold value r, is determined as face equipment;
D. if someone is just watching equipment attentively, according to picture signal, the key point of the continuous several frames of face people is judged,
See whether its upperlip spacing is greater than threshold value d from dynamic range, if more than then determining that it is speaking, i.e., someone just watches attentively and sets
It is standby and speaking.
Voice interaction module judges whether to start voice interactive function according to described image, voice signal:
If speech activity is not detected, do not start voice interactive function;If detecting speech activity, someone is being not detected just
Watch equipment attentively to speak, does not start voice interactive function;If detecting speech activity, and detect that someone is just watching equipment attentively and speaking,
Start voice interactive function.
Characteristic storage module is used to store the phonetic feature and characteristics of image of current speaker, including phonetic feature and image
Feature: phonetic feature of speaker, including age " 25 ", gender " male ", identity " user 1 " etc. are stored;Store the figure of speaker
As feature, including facial image and coordinate, position " equipment is 30 degree left ", gender " male ", age " 25 ", identity user 1 " etc..
The speech content of speech recognition module identification speaker, instruction " I wants to see Journey to the West " such as interactive for TV,
" sound is more greatly ", the instruction " temperature height a bit " interactive for air-conditioning, " wind is a little bit smaller " etc..
Intention assessment module carries out intention assessment to current speaker, understands after the speech content of identification speaker
User is intended to, such as " Journey to the West ", " wind ", " small ".Journey to the West piece is such as searched in service needed for household appliance provides current speaker
Source selects for user, turns down air conditioner wind speed.
Embodiment 1 and the embodiment 2 also expansible interactive voice for other household appliances, such as the temperature of refrigerator, lamp
Switch etc..So as to and carry out multimodal recognition, improve interactive efficiency without activating word to start voice interactive function, for
Family provides more intelligent service.
Claims (8)
1. the multi-modal exchange method of household appliance, which comprises the following steps:
S1. the image and voice signal under current environment are obtained;
S2. according to voice signal, detect whether that there are speech activities;
S3. if detecting the presence of speech activity, according to picture signal, judge whether someone's positive injection depending on equipment and speaking;
S4. if detecting that someone is just watching equipment attentively and speaking, start voice interactive function, and store present user speech
Feature and characteristics of image;
S5. when starting voice interactive function, according to phonetic feature, the speech content of current speaker is identified;
S6. when starting voice interactive function, using intention assessment, judge the intention of current speaker and provide corresponding
Service.
2. the multi-modal exchange method of household appliance according to claim 1, which is characterized in that in step S1, pass through house
Voice receiver device built in electric equipment obtains the voice signal under current environment;Pass through the camera built in household appliance
Device obtains the picture signal under current environment.
3. the multi-modal exchange method of household appliance according to claim 1, which is characterized in that step S2 specifically include with
Lower step:
S201. voice signal traditional characteristic or depth characteristic are extracted;
S202. feature is made decisions based on thresholding, statistical model and machine learning, detects whether that there are speech activities.
4. the multi-modal exchange method of household appliance according to claim 1, which is characterized in that step S3 specifically include with
Lower step:
S301. according to described image signal, the facial orientation of current speaker is calculated with computer vision technique, front ring is worked as in judgement
Whether someone is just watching equipment attentively in border;
S302. if someone is just watching equipment attentively, according to picture signal, judgement is calculated using computer vision technique and watches equipment attentively
People whether speaking.
5. the multi-modal exchange method of household appliance according to claim 1, which is characterized in that in step S4, institute's predicate
Sound feature includes age, gender and the identity of speaker;Described image feature includes the face of speaker, position, gender, age
And identity.
6. the multi-modal exchange method of household appliance according to claim 1, which is characterized in that in step S5, by mentioning
The speech parameter in phonetic feature is taken, identifies the speech content of current speaker.
7. the multi-modal exchange method of household appliance according to claim 1, which is characterized in that step S6 specifically include with
Lower step:
S601. intention assessment is used, speech content is analyzed, extracts the intention of current speaker;
S602. household appliance built-in command word database;
S603. by the intention and database matching of current speaker, confirm that user thinks the order of input;
S604., service needed for current speaker is provided.
8. the multi-modal interactive system of household appliance, the multimode applied to household appliance described in claim 1-7 any one
State exchange method, which is characterized in that including signal acquisition module, Speaker change detection module, voice interaction module, characteristic storage mould
Block, speech recognition module and intention assessment module, signal acquisition module are connected with Speaker change detection module, Speaker change detection module
It is connected with voice interaction module, voice interaction module is connected with characteristic storage module, characteristic storage module and speech recognition module
It is connected, speech recognition module is connected with intention assessment module;
The signal acquisition module, for obtaining voice and picture signal;
The Speaker change detection module, for judging whether that someone is speaking to household appliance;
The voice interaction module starts voice interactive function for judging whether according to described image, voice signal;
The characteristic storage module, for storing the phonetic feature and characteristics of image of current speaker;
The speech recognition module, for identification user's speech content;
The intention assessment module, for understanding that user is intended to, recommendation service content.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910616247.9A CN110335600A (en) | 2019-07-09 | 2019-07-09 | The multi-modal exchange method and system of household appliance |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910616247.9A CN110335600A (en) | 2019-07-09 | 2019-07-09 | The multi-modal exchange method and system of household appliance |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110335600A true CN110335600A (en) | 2019-10-15 |
Family
ID=68143944
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910616247.9A Pending CN110335600A (en) | 2019-07-09 | 2019-07-09 | The multi-modal exchange method and system of household appliance |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110335600A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110718225A (en) * | 2019-11-25 | 2020-01-21 | 深圳康佳电子科技有限公司 | Voice control method, terminal and storage medium |
CN111048066A (en) * | 2019-11-18 | 2020-04-21 | 云知声智能科技股份有限公司 | Voice endpoint detection system assisted by images on child robot |
CN111128157A (en) * | 2019-12-12 | 2020-05-08 | 珠海格力电器股份有限公司 | Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner |
CN111145739A (en) * | 2019-12-12 | 2020-05-12 | 珠海格力电器股份有限公司 | Vision-based awakening-free voice recognition method, computer-readable storage medium and air conditioner |
CN111276140A (en) * | 2020-01-19 | 2020-06-12 | 珠海格力电器股份有限公司 | Voice command recognition method, device, system and storage medium |
CN111341350A (en) * | 2020-01-18 | 2020-06-26 | 南京奥拓电子科技有限公司 | Man-machine interaction control method and system, intelligent robot and storage medium |
CN111367489A (en) * | 2020-02-19 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Voice interaction method, voice device, medium and electronic device |
CN111625094A (en) * | 2020-05-25 | 2020-09-04 | 北京百度网讯科技有限公司 | Interaction method and device for intelligent rearview mirror, electronic equipment and storage medium |
CN111767785A (en) * | 2020-05-11 | 2020-10-13 | 南京奥拓电子科技有限公司 | Man-machine interaction control method and device, intelligent robot and storage medium |
CN113139491A (en) * | 2021-04-30 | 2021-07-20 | 厦门盈趣科技股份有限公司 | Video conference control method, system, mobile terminal and storage medium |
CN113593544A (en) * | 2021-06-11 | 2021-11-02 | 青岛海尔科技有限公司 | Device control method and apparatus, storage medium, and electronic apparatus |
CN117119102A (en) * | 2023-03-21 | 2023-11-24 | 荣耀终端有限公司 | Awakening method of voice interaction function and electronic equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105389097A (en) * | 2014-09-03 | 2016-03-09 | 中兴通讯股份有限公司 | Man-machine interaction device and method |
CN107230476A (en) * | 2017-05-05 | 2017-10-03 | 众安信息技术服务有限公司 | A kind of natural man machine language's exchange method and system |
CN107665708A (en) * | 2016-07-29 | 2018-02-06 | 科大讯飞股份有限公司 | Intelligent sound exchange method and system |
CN109941231A (en) * | 2019-02-21 | 2019-06-28 | 初速度(苏州)科技有限公司 | Vehicle-mounted terminal equipment, vehicle-mounted interactive system and exchange method |
-
2019
- 2019-07-09 CN CN201910616247.9A patent/CN110335600A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105389097A (en) * | 2014-09-03 | 2016-03-09 | 中兴通讯股份有限公司 | Man-machine interaction device and method |
CN107665708A (en) * | 2016-07-29 | 2018-02-06 | 科大讯飞股份有限公司 | Intelligent sound exchange method and system |
CN107230476A (en) * | 2017-05-05 | 2017-10-03 | 众安信息技术服务有限公司 | A kind of natural man machine language's exchange method and system |
CN109941231A (en) * | 2019-02-21 | 2019-06-28 | 初速度(苏州)科技有限公司 | Vehicle-mounted terminal equipment, vehicle-mounted interactive system and exchange method |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111048066A (en) * | 2019-11-18 | 2020-04-21 | 云知声智能科技股份有限公司 | Voice endpoint detection system assisted by images on child robot |
CN110718225A (en) * | 2019-11-25 | 2020-01-21 | 深圳康佳电子科技有限公司 | Voice control method, terminal and storage medium |
CN111128157B (en) * | 2019-12-12 | 2022-05-27 | 珠海格力电器股份有限公司 | Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner |
CN111128157A (en) * | 2019-12-12 | 2020-05-08 | 珠海格力电器股份有限公司 | Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner |
CN111145739A (en) * | 2019-12-12 | 2020-05-12 | 珠海格力电器股份有限公司 | Vision-based awakening-free voice recognition method, computer-readable storage medium and air conditioner |
CN111341350A (en) * | 2020-01-18 | 2020-06-26 | 南京奥拓电子科技有限公司 | Man-machine interaction control method and system, intelligent robot and storage medium |
CN111276140A (en) * | 2020-01-19 | 2020-06-12 | 珠海格力电器股份有限公司 | Voice command recognition method, device, system and storage medium |
CN111276140B (en) * | 2020-01-19 | 2023-05-12 | 珠海格力电器股份有限公司 | Voice command recognition method, device, system and storage medium |
CN111367489A (en) * | 2020-02-19 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Voice interaction method, voice device, medium and electronic device |
CN111767785A (en) * | 2020-05-11 | 2020-10-13 | 南京奥拓电子科技有限公司 | Man-machine interaction control method and device, intelligent robot and storage medium |
CN111625094A (en) * | 2020-05-25 | 2020-09-04 | 北京百度网讯科技有限公司 | Interaction method and device for intelligent rearview mirror, electronic equipment and storage medium |
CN113139491A (en) * | 2021-04-30 | 2021-07-20 | 厦门盈趣科技股份有限公司 | Video conference control method, system, mobile terminal and storage medium |
CN113593544A (en) * | 2021-06-11 | 2021-11-02 | 青岛海尔科技有限公司 | Device control method and apparatus, storage medium, and electronic apparatus |
CN117119102A (en) * | 2023-03-21 | 2023-11-24 | 荣耀终端有限公司 | Awakening method of voice interaction function and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110335600A (en) | The multi-modal exchange method and system of household appliance | |
WO2018210219A1 (en) | Device-facing human-computer interaction method and system | |
US11308963B2 (en) | Query endpointing based on lip detection | |
US11580983B2 (en) | Sign language information processing method and apparatus, electronic device and readable storage medium | |
CN110730115B (en) | Voice control method and device, terminal and storage medium | |
CN107450390B (en) | intelligent household appliance control device, control method and control system | |
US8719015B2 (en) | Dialogue system and method for responding to multimodal input using calculated situation adaptability | |
US20170139470A1 (en) | Method for intelligently controlling controlled equipment and device | |
CN105204628A (en) | Voice control method based on visual awakening | |
WO2016150001A1 (en) | Speech recognition method, device and computer storage medium | |
US20150254062A1 (en) | Display apparatus and control method thereof | |
KR102409303B1 (en) | Method and Apparatus for Voice Recognition | |
US20180293236A1 (en) | Fast identification method and household intelligent robot | |
CN104714642A (en) | Mobile terminal and gesture recognition processing method and system thereof | |
WO2013128999A1 (en) | Equipment operation system, equipment operation device, server, equipment operation method, and program | |
CN105301997A (en) | Intelligent prompting method and system based on mobile robot | |
CN107360157A (en) | A kind of user registering method, device and intelligent air conditioner | |
CN109410957A (en) | Positive human-computer interaction audio recognition method and system based on computer vision auxiliary | |
WO2017166462A1 (en) | Method and system for reminding about change in environment, and head-mounted vr device | |
CN106462646A (en) | Control device, control method, and computer program | |
CN111583937A (en) | Voice control awakening method, storage medium, processor, voice equipment and intelligent household appliance | |
WO2022042274A1 (en) | Voice interaction method and electronic device | |
WO2020192215A1 (en) | Interactive method and wearable interactive device | |
CN110853430B (en) | Learning tutoring method and device based on smart home and storage medium | |
CN112565396B (en) | Information pushing method and device, robot and storage medium |
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: 20191015 |