CN105869639A - Speech recognition method and system - Google Patents
Speech recognition method and system Download PDFInfo
- Publication number
- CN105869639A CN105869639A CN201610165978.2A CN201610165978A CN105869639A CN 105869639 A CN105869639 A CN 105869639A CN 201610165978 A CN201610165978 A CN 201610165978A CN 105869639 A CN105869639 A CN 105869639A
- Authority
- CN
- China
- Prior art keywords
- distance
- user face
- less
- equal
- identified
- 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 39
- 230000009471 action Effects 0.000 claims description 31
- 238000001514 detection method Methods 0.000 claims description 26
- 230000001921 mouthing effect Effects 0.000 abstract 1
- 230000008859 change Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 230000007613 environmental effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000007423 decrease Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 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
- G10L15/24—Speech recognition using non-acoustical features
- G10L15/25—Speech recognition using non-acoustical features using position of the lips, movement of the lips or face analysis
-
- 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)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a speech recognition method and a speech recognition system. The speech recognition method is characterized by comprising the following steps: detecting that the distance from the face of a user is smaller than or equal to a preset distance; recognizing that the mouthing shape on the face of the user changes; and recognizing the recorded speech. With the adoption of the method and the system, when the user speaks by facing the device, the speech recognition is started automatically, so that the speech of the user is recognized, the opening operation is reduced, and thus the user experience is promoted.
Description
Technical field
The present invention relates to technical field of data storage, particularly relate to the method and system of a kind of speech recognition.
Background technology
The opening module of voice to the experience of whole speech recognition it is critical that, with fashion open mode also
The biggest help is played to avoiding noise jamming.Existing speech recognition open mode mainly has two kinds: a kind of
It is unlatching speech recognition after touch operation, such as: by releasing the button on screen, or defines the behaviour such as screen sliding
Make to open, or pressing entity button key opens the speech identifying function of a function, but this mode is being opened
When opening speech identifying function, need to operate with hands, it appears the most convenient, intelligent, have impact on the use of user
Wish, in some occasion, as more seemed inconvenient when driving；Another kind is that user says the simple life provided
Order is opened, such as the intelligent watch of Huawei, it is simply that by saying wrist-watch: " hello, Android " so simply and
The order provided is to open its speech recognition mode.But this mode seems unnatural, intelligence sense fall
Low, and will have individual command recognition process before speech recognition, efficiency also can be allowed to reduce.
How after user talks facing to equipment, system just can identify automatically, it is not necessary to user has one
The breakdown action of voice, can automatically just automatically turn on when user starts to talk, make speech recognition more convenient,
Intelligence, improving Consumer's Experience is urgent problem.
Summary of the invention
The invention provides the method and system of a kind of speech recognition, by according to the distance of user face and
The change of nozzle type carries out speech recognition, it is achieved that when user carries out voice facing to equipment, automatically turn on language
Sound identification, is identified the voice of user, decreases the operation of unlatching, improves Consumer's Experience.
For realizing above-mentioned design, the present invention by the following technical solutions:
On the one hand, it is provided that a kind of method of speech recognition, including:
Detect that the distance with user face is less than or equal to preset distance；
The nozzle type identifying user face changes；
The voice of admission is identified.
Preferably, described in detect distance with user face less than or equal to preset distance, including: by taking the photograph
As head detects that the distance with user face is less than or equal to preset distance；
The described distance detected with user face, less than or equal to before preset distance, also includes: detect and lift
Manually make, open photographic head.
Preferably, described in detect distance with user face less than or equal to preset distance, including:
Utilize the infrared sensor detection distance with object less than or equal to preset distance；
Determine that described object is user face by photographic head.
Preferably, detect that the distance with user face, less than or equal to after preset distance, also includes described in:
Open recording.
Preferably, the described voice to admission is identified, including: remove the nozzle type identifying user face
Recording before changing, the recording when the nozzle type identifying user face changes as starting point,
The voice of admission is identified.
Preferably, after the described voice to admission is identified, also include: to the voice command identified
Respond.
On the other hand, it is provided that the system of a kind of speech recognition, this system, including:
Distance detection module, for detecting that the distance with user face is less than or equal to preset distance；
Nozzle type identification module, changes for identifying the nozzle type of user face；
Sound identification module, for being identified the voice of admission.
Preferably:
Described distance detection module specifically for: detect that the distance with user face is less than by photographic head
In preset distance；
Also include: opening module, be used for detecting action of raising one's hand, open photographic head.
Preferably, described distance detection module specifically for:
The distance with object is less than or equal to preset distance to utilize infrared sensor to detect；
Determine that described object is user face by photographic head.
Preferably, also include:
Recording opening module, for detecting that at distance detection module the distance with user face is less than or equal to pre-
Put distance and open recording afterwards；
Respond module, for responding the voice command identified；
Described sound identification module, specifically for: remove and identify before the nozzle type of user face changes
Recording, the language as starting point, to admission of the recording when the nozzle type identifying user face changes
Sound is identified.
Compared with prior art, the invention have the benefit that and detect that the distance with user face is less than
In preset distance；The nozzle type identifying user face changes；The voice of admission is identified.This
Bright by according to carrying out speech recognition with the distance of user face and the change of nozzle type, it is achieved that user couple
When the equipment of wearing carries out voice, automatically opening voice identification, the voice of user is identified, decreases unlatching
Operation, improve Consumer's Experience.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, the embodiment of the present invention will be retouched below
In stating, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is only
Some embodiments of the present invention, for those of ordinary skill in the art, are not paying creative work
Under premise, it is also possible to content according to embodiments of the present invention and these accompanying drawings obtain other accompanying drawing.
Fig. 1 is the first embodiment of the method for a kind of speech recognition provided in the specific embodiment of the invention
Method flow diagram.
Fig. 2 is the second embodiment of the method for a kind of speech recognition provided in the specific embodiment of the invention
Method flow diagram.
Fig. 3 is the 3rd embodiment of the method for a kind of speech recognition provided in the specific embodiment of the invention
Method flow diagram.
Fig. 4 is the first embodiment of the system of a kind of speech recognition provided in the specific embodiment of the invention
Block diagram.
Fig. 5 is the second embodiment of the system of a kind of speech recognition provided in the specific embodiment of the invention
Block diagram.
Fig. 6 is the 3rd embodiment of the system of a kind of speech recognition provided in the specific embodiment of the invention
Block diagram.
Detailed description of the invention
Technical scheme and the technique effect reached for making to present invention solves the technical problem that, using are more clear
Chu, is described in further detail the technical scheme of the embodiment of the present invention below in conjunction with accompanying drawing, it is clear that
Described embodiment is only a part of embodiment of the present invention rather than whole embodiments.Based on this
Embodiment in bright, those skilled in the art obtained under not making creative work premise all its
His embodiment, broadly falls into the scope of protection of the invention.
Refer to Fig. 1, its be a kind of speech recognition provided in the specific embodiment of the invention method the
The method flow diagram of one embodiment.As it can be seen, the method, including:
Step S101: detect that the distance with user face is less than or equal to preset distance.
When user needs that equipment is carried out Voice command, user can talk near equipment, also corresponds to
User face is near equipment, and for improving the admission quality of voice, the distance that need to detect equipment and user face is
No less than or equal to preset distance, described preset distance is 5cm, 10cm or 15cm etc., can set according to difference
Standby and practical service environment is configured.Described equipment includes: large-scale intelligent equipment, as intelligent watch,
The wearing portable equipment of Intelligent bracelet etc., such as the non-wearing portable equipment etc. of mobile phone, flat board etc..
Step S102: the nozzle type identifying user face changes.
For avoid face near but when not pronouncing, typing environmental noise, affect discrimination, need to carry out
Nozzle type identification, if the nozzle type identifying user has change and the action of pronunciation, just with current point in time for control
The starting point of voice processed.
Step S103: the voice of admission is identified.
The described voice to admission is identified, including: removal identifies the nozzle type of user face and changes
Recording before, the recording when the nozzle type identifying user face changes is as starting point, to admission
Voice be identified.Remove the recording before starting point, remove environment noise to a certain extent to voice
The impact identified, improves discrimination.
In sum, the present embodiment is by according to carrying out voice with the distance of user face and the change of nozzle type
Identify, to identify the starting point as speech recognition of the recording when nozzle type of user face changes,
Eliminating the environment noise impact on speech recognition to a certain extent, improve discrimination, the present embodiment realizes
When user carries out voice facing to equipment, automatically opening voice identification, the voice of user is identified,
Decrease the operation of unlatching, improve Consumer's Experience.
Refer to Fig. 2, its be a kind of speech recognition provided in the specific embodiment of the invention method the
The method flow diagram of two embodiments.As it can be seen, the method, including:
Step S201: detect action of raising one's hand, opens photographic head.
For the wearing portable equipment of intelligent watch, Intelligent bracelet etc., when user needs Voice command,
Needing to raise one's hand, corresponding has an action of raising one's hand, but raises one's hand and not necessarily can carry out Voice command, because of
This, when detect raise one's hand action time, in addition it is also necessary to carry out face recognition, be tested with action of raising one's hand, also identify
Go out face, then explanation user needs to carry out Voice command.The present embodiment utilize photographic head carry out face recognition and
The monitoring of distance, thus when detect raise one's hand action time, open photographic head.Acceleration transducer can be utilized
Detecting action of raising one's hand, this is prior art, and here is omitted.
Step S202: detect that the distance with user face is less than or equal to preset distance by photographic head.
When the distance of user face with equipment is less than or equal to preset distance, illustrate that user needs to carry out Voice command.
Photographic head is utilized to carry out the detection of face recognition and distance, to detect that the distance with user face is less than or equal to
Preset distance, described preset distance is 5cm, 10cm or 15cm etc., can be according to distinct device with actual make
It is configured with environment.Step S202 is a kind of speech recognition of offer in the specific embodiment of the invention
Step S101 in the first embodiment of method: detect that the distance with user face is less than or equal to preset distance
The more particular embodiment of portable equipment is dressed for intelligent watch, Intelligent bracelet etc..
Step S203: open recording.
After detecting that the distance with user face is less than or equal to preset distance, it is switched on recording.
Step S204: the nozzle type identifying user face changes.
For avoid face near but when not pronouncing, typing environmental noise, affect discrimination, need to carry out
Nozzle type identification, if the nozzle type identifying user has change and the action of pronunciation, just with current point in time for control
The starting point of voice processed.
Step S205: the voice of admission is identified.
The described voice to admission is identified, including: removal identifies the nozzle type of user face and changes
Recording before, the recording when the nozzle type identifying user face changes is as starting point, to admission
Voice be identified.Remove the recording before starting point, remove environment noise to a certain extent to voice
The impact identified, improves discrimination.
Step S206: the voice command identified is responded.
The voice command identified is responded, institute's speech commands can be open certain application program,
Close certain level of application, make a phone call, photos and sending messages etc..
The present embodiment is switched on photographic head when detecting and raising one's hand action, utilizes photographic head to carry out face recognition
With the monitoring of distance, when photographic head detects the distance with user face less than or equal to preset distance, open
Recording, removes the recording identified before the nozzle type of user face changes, to identify the nozzle type of user
There are the change of pronunciation and the time point of action as the starting point of control voice, the voice of admission be identified,
And the voice command identified is responded.The present embodiment is raise one's hand action user, carries out near equipment
After pronunciation, can carry out the response of voice command immediately, need not do the action opened in advance, whole process is natural,
Operating efficiency is high, removes the environment noise impact on speech recognition to a certain extent, improves discrimination.
Refer to Fig. 3, its be a kind of speech recognition provided in the specific embodiment of the invention method the
The method flow diagram of three embodiments.As it can be seen, the method, including:
Step S301: utilize the infrared sensor detection distance with object less than or equal to preset distance.
When user needs that equipment is carried out Voice command, user can talk near equipment, therefore can profit
In the range of preset distance, whether have object proximity with infrared sensor detection, be also equivalent to utilize infrared biography
Whether sensor detection equipment is less than or equal to preset distance with the distance of object.
Step S302: determine that described object is user face by photographic head.
When the distance of infrared sensor detection equipment with object is less than or equal to preset distance, object proximity is described,
But not representing must be to need to carry out Voice command, it is also possible to can be other situations, the most just has individual object
It is placed in before equipment, or equipment has been placed on above an object, therefore also need to be determined by photographic head
Described object is user face, and explanation is user near equipment, needs equipment is carried out Voice command.Step
Rapid S301 and step S302 are a kind of method of speech recognition that provides in the specific embodiment of the invention the
Step S101 in one embodiment: detect the distance with user face less than or equal to preset distance more specifically
Embodiment.
Described equipment includes: large-scale intelligent equipment, such as the wearing portable equipment of intelligent watch, Intelligent bracelet etc.,
Non-wearing portable equipment such as mobile phone, flat board etc. etc..Described preset distance is 5cm, 10cm or 15cm
Deng, can be configured according to distinct device and practical service environment.Utilize infrared sensor detection and object
Distance less than or equal to after preset distance, open photographic head, determine that described object is user by photographic head
Face.
Step S303: open recording.
After detecting that the distance with user face is less than or equal to preset distance, it is switched on recording.
Step S304: the nozzle type identifying user face changes.
For avoid face near but when not pronouncing, typing environmental noise, affect discrimination, need to carry out
Nozzle type identification, if the nozzle type identifying user has change and the action of pronunciation, just with current point in time for control
The starting point of voice processed.
Step S305: the voice of admission is identified.
The described voice to admission is identified, including: removal identifies the nozzle type of user face and changes
Recording before, the recording when the nozzle type identifying user face changes is as starting point, to admission
Voice be identified.Remove the recording before starting point, remove environment noise to a certain extent to voice
The impact identified, improves discrimination.
Step S306: the voice command identified is responded.
The voice command identified is responded, institute's speech commands can be open certain application program,
Close certain level of application, make a phone call, photos and sending messages etc..
The present embodiment utilizes infrared sensor detection to be less than or equal to preset distance with the distance of object, by shooting
Head determines that described object is user face, utilize the combination of infrared sensor and photographic head to detect equipment with
The distance of user face, less than or equal to after preset distance, opens recording, removes the nozzle type identifying user face
Recording before changing, using identify the nozzle type of user have the change of pronunciation and the time point of action as
Control the starting point of voice, the voice of admission is identified, and the voice command identified is responded.
The present embodiment after equipment pronounces, can carry out the response of voice command user immediately, need not be prior
Doing the action opened, whole process is natural, and operating efficiency is high, removes environment noise to a certain extent to language
The impact of sound identification, improves discrimination.
The embodiment of the system of a kind of speech recognition provided in the specific embodiment of the invention, system are provided
Embodiment embodiment based on above-mentioned method realize, the most most description, refer to aforementioned side
The embodiment of method.
Refer to Fig. 4, its be a kind of speech recognition provided in the specific embodiment of the invention system the
The block diagram of one embodiment.As it can be seen, this system, including:
Distance detection module 41, for detecting that the distance with user face is less than or equal to preset distance.
When user needs that equipment is carried out Voice command, user can talk near equipment, also corresponds to
User face is near equipment, and for improving the admission quality of voice, the distance that need to detect equipment and user face is
No less than or equal to preset distance, described preset distance is 5cm, 10cm or 15cm etc., can set according to difference
Standby and practical service environment is configured.Described equipment includes: large-scale intelligent equipment, as intelligent watch,
The wearing portable equipment of Intelligent bracelet etc., such as the non-wearing portable equipment etc. of mobile phone, flat board etc..
Nozzle type identification module 42, changes for identifying the nozzle type of user face.
For avoid face near but when not pronouncing, typing environmental noise, affect discrimination, need to carry out
Nozzle type identification, if the nozzle type identifying user has change and the action of pronunciation, just with current point in time for control
The starting point of voice processed.
Sound identification module 43, for being identified the voice of admission.
Described sound identification module 43, specifically for: removal identifies the nozzle type of user face and changes it
Front recording, the recording when the nozzle type identifying user face changes is as starting point, to admission
Voice is identified.Remove the recording before starting point, remove environment noise to a certain extent and voice is known
Other impact, improves discrimination.
In sum, the present embodiment is by according to carrying out voice with the distance of user face and the change of nozzle type
Identify, to identify the starting point as speech recognition of the recording when nozzle type of user face changes,
Eliminating the environment noise impact on speech recognition to a certain extent, improve discrimination, the present embodiment realizes
When user carries out voice facing to equipment, automatically opening voice identification, the voice of user is identified,
Decrease the operation of unlatching, improve Consumer's Experience.
Refer to Fig. 5, its be a kind of speech recognition provided in the specific embodiment of the invention system the
The block diagram of two embodiments.As it can be seen, this system, including:
Opening module 51, is used for detecting action of raising one's hand, and opens photographic head.
For the wearing portable equipment of intelligent watch, Intelligent bracelet etc., when user needs Voice command,
Needing to raise one's hand, corresponding has an action of raising one's hand, but raises one's hand and not necessarily can carry out Voice command, because of
This, when detect raise one's hand action time, in addition it is also necessary to carry out face recognition, be tested with action of raising one's hand, also identify
Go out face, then explanation user needs to carry out Voice command.The present embodiment utilize photographic head carry out face recognition and
The monitoring of distance, thus when detect raise one's hand action time, open photographic head.Acceleration transducer can be utilized
Detecting action of raising one's hand, this is prior art, and here is omitted.
Distance detection module 52, for detecting with the distance of user face less than or equal to preset by photographic head
Distance.
When the distance of user face with equipment is less than or equal to preset distance, illustrate that user needs to carry out Voice command.
Photographic head is utilized to carry out the detection of face recognition and distance, to detect that the distance with user face is less than or equal to
Preset distance, described preset distance is 5cm, 10cm or 15cm etc., can be according to distinct device with actual make
It is configured with environment.
At distance detection module 52, recording opening module 53, for detecting that the distance with user face is less than
Recording is opened after preset distance.
Nozzle type identification module 54, changes for identifying the nozzle type of user face.
For avoid face near but when not pronouncing, typing environmental noise, affect discrimination, need to carry out
Nozzle type identification, if the nozzle type identifying user has change and the action of pronunciation, just with current point in time for control
The starting point of voice processed.
Sound identification module 55, for being identified the voice of admission.
Described sound identification module 55, specifically for: removal identifies the nozzle type of user face and changes it
Front recording, the recording when the nozzle type identifying user face changes is as starting point, to admission
Voice is identified.Remove the recording before starting point, remove environment noise to a certain extent and voice is known
Other impact, improves discrimination.
Respond module 56, for responding the voice command identified.
The present embodiment utilizes photographic head to detect, and the distance with user face is less than or equal to preset distance, to identify
The nozzle type going out user has the change of pronunciation and the time point of the action starting point as control voice, to admission
Voice is identified, and responds the voice command identified.The present embodiment is raise one's hand action user,
After equipment pronounces, the response of voice command can be carried out immediately, the action opened need not be done in advance,
Whole process is natural, and operating efficiency is high, removes the environment noise impact on speech recognition to a certain extent,
Improve discrimination.
Refer to Fig. 6, its be a kind of speech recognition provided in the specific embodiment of the invention system the
The block diagram of three embodiments.As it can be seen, this system, including:
Distance detection module 61, for utilizing infrared sensor to detect, the distance with object is less than or equal to preset
Distance；Determine that described object is user face by photographic head.
When user needs that equipment is carried out Voice command, user can talk near equipment, therefore can profit
In the range of preset distance, whether have object proximity with infrared sensor detection, be also equivalent to utilize infrared biography
Whether sensor detection equipment is less than or equal to preset distance with the distance of object.Described equipment includes: large-scale intelligent
Equipment, such as the wearing portable equipment of intelligent watch, Intelligent bracelet etc., as mobile phone, flat board etc. non-wearing just
Take equipment etc..Described preset distance is 5cm, 10cm or 15cm etc., can be according to distinct device and reality
Use environments to be configured.Utilize infrared sensor detection and the distance of object less than or equal to preset distance it
After, open photographic head, determine that described object is user face by photographic head.
At distance detection module, recording opening module 62, for detecting that the distance with user face is less than or equal to
Recording is opened after preset distance.
Nozzle type identification module 63, changes for identifying the nozzle type of user face.
For avoid face near but when not pronouncing, typing environmental noise, affect discrimination, need to carry out
Nozzle type identification, if the nozzle type identifying user has change and the action of pronunciation, just with current point in time for control
The starting point of voice processed.
Sound identification module 64, for being identified the voice of admission.
Respond module 65, for responding the voice command identified.
The voice command identified is responded, institute's speech commands can be open certain application program,
Close certain level of application, make a phone call, photos and sending messages etc..
In sum, the present embodiment provides the system of speech recognition user after equipment pronounces, energy
Carrying out the response of voice command immediately, need not do the action opened in advance, whole process is natural, operating efficiency
Height, removes the environment noise impact on speech recognition to a certain extent, improves discrimination.
The know-why of the present invention is described above in association with specific embodiment.These describe and are intended merely to explain this
The principle of invention, and limiting the scope of the invention can not be construed to by any way.Based on herein
Explaining, those skilled in the art need not pay performing creative labour can associate other tool of the present invention
Body embodiment, within these modes fall within protection scope of the present invention.
Claims (10)
1. the method for a speech recognition, it is characterised in that including:
Detect that the distance with user face is less than or equal to preset distance；
The nozzle type identifying user face changes；
The voice of admission is identified.
Method the most according to claim 1, it is characterised in that described in detect with user face away from
From less than or equal to preset distance, including: detect that the distance with user face is less than or equal to pre-by photographic head
Put distance；
The described distance detected with user face, less than or equal to before preset distance, also includes: detect and lift
Manually make, open photographic head.
Method the most according to claim 1, it is characterised in that described in detect with user face away from
From less than or equal to preset distance, including:
Utilize the infrared sensor detection distance with object less than or equal to preset distance；
Determine that described object is user face by photographic head.
Method the most according to claim 1, it is characterised in that described in detect with user face away from
After less than or equal to preset distance, also include: open recording.
Method the most according to claim 1, it is characterised in that the described voice to admission is identified,
Including: remove the recording identified before the nozzle type of user face changes, from identifying user face
The voice of admission, as starting point, is identified by recording when nozzle type changes.
Method the most according to claim 1, it is characterised in that the described voice to admission is identified
Afterwards, also include: the voice command identified is responded.
7. the system of a speech recognition, it is characterised in that including:
Distance detection module, for detecting that the distance with user face is less than or equal to preset distance；
Nozzle type identification module, changes for identifying the nozzle type of user face；
Sound identification module, for being identified the voice of admission.
System the most according to claim 7, it is characterised in that:
Described distance detection module specifically for: detect that the distance with user face is less than by photographic head
In preset distance；
Also include: opening module, be used for detecting action of raising one's hand, open photographic head.
System the most according to claim 7, it is characterised in that described distance detection module specifically for:
The distance with object is less than or equal to preset distance to utilize infrared sensor to detect；
Determine that described object is user face by photographic head.
System the most according to claim 7, it is characterised in that also include:
Recording opening module, for detecting that at distance detection module the distance with user face is less than or equal to pre-
Put distance and open recording afterwards；
Respond module, for responding the voice command identified；
Described sound identification module, specifically for: remove and identify before the nozzle type of user face changes
Recording, the language as starting point, to admission of the recording when the nozzle type identifying user face changes
Sound is identified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610165978.2A CN105869639A (en) | 2016-03-21 | 2016-03-21 | Speech recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610165978.2A CN105869639A (en) | 2016-03-21 | 2016-03-21 | Speech recognition method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105869639A true CN105869639A (en) | 2016-08-17 |
Family
ID=56624647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610165978.2A Pending CN105869639A (en) | 2016-03-21 | 2016-03-21 | Speech recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105869639A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107195304A (en) * | 2017-06-30 | 2017-09-22 | 珠海格力电器股份有限公司 | The voice control circuit and method of a kind of electric equipment |
| CN107291451A (en) * | 2017-05-25 | 2017-10-24 | 深圳市冠旭电子股份有限公司 | Voice awakening method and device |
| CN108196769A (en) * | 2017-12-29 | 2018-06-22 | 上海爱优威软件开发有限公司 | A kind of voice message originator method and terminal device |
| CN108198558A (en) * | 2017-12-28 | 2018-06-22 | 电子科技大学 | A kind of audio recognition method based on CSI data |
| CN108538287A (en) * | 2017-03-03 | 2018-09-14 | 深圳会当科技有限公司 | A kind of improvement voice activated control device |
| CN109059199A (en) * | 2018-06-28 | 2018-12-21 | 珠海格力电器股份有限公司 | A kind of voice Rouser, method and voice control air-conditioning system |
| CN110010125A (en) * | 2017-12-29 | 2019-07-12 | 深圳市优必选科技有限公司 | A kind of control method of intelligent robot, device, terminal device and medium |
| CN110164444A (en) * | 2018-02-12 | 2019-08-23 | 优视科技有限公司 | Voice input starting method, apparatus and computer equipment |
| CN110262767A (en) * | 2019-06-03 | 2019-09-20 | 清华大学 | Based on voice input Rouser, method and the medium close to mouth detection |
| CN112578338A (en) * | 2019-09-27 | 2021-03-30 | 阿里巴巴集团控股有限公司 | Sound source positioning method, device, equipment 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 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06124097A (en) * | 1992-10-13 | 1994-05-06 | Hitachi Ltd | Portable terminal device |
| CN104103274A (en) * | 2013-04-11 | 2014-10-15 | 纬创资通股份有限公司 | Speech processing apparatus and speech processing method |
| CN104269172A (en) * | 2014-07-31 | 2015-01-07 | 广东美的制冷设备有限公司 | Voice control method and system based on video positioning |
| CN104781782A (en) * | 2012-11-08 | 2015-07-15 | 索尼公司 | Information processing apparatus, information processing method, and program |
| CN104834222A (en) * | 2015-04-30 | 2015-08-12 | 广东美的制冷设备有限公司 | Control method and apparatus for household electrical appliance |
| CN204561161U (en) * | 2015-04-15 | 2015-08-19 | 许丰 | Intelligent and safe bracelet |
-
2016
- 2016-03-21 CN CN201610165978.2A patent/CN105869639A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06124097A (en) * | 1992-10-13 | 1994-05-06 | Hitachi Ltd | Portable terminal device |
| CN104781782A (en) * | 2012-11-08 | 2015-07-15 | 索尼公司 | Information processing apparatus, information processing method, and program |
| CN104103274A (en) * | 2013-04-11 | 2014-10-15 | 纬创资通股份有限公司 | Speech processing apparatus and speech processing method |
| CN104269172A (en) * | 2014-07-31 | 2015-01-07 | 广东美的制冷设备有限公司 | Voice control method and system based on video positioning |
| CN204561161U (en) * | 2015-04-15 | 2015-08-19 | 许丰 | Intelligent and safe bracelet |
| CN104834222A (en) * | 2015-04-30 | 2015-08-12 | 广东美的制冷设备有限公司 | Control method and apparatus for household electrical appliance |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108538287A (en) * | 2017-03-03 | 2018-09-14 | 深圳会当科技有限公司 | A kind of improvement voice activated control device |
| CN107291451A (en) * | 2017-05-25 | 2017-10-24 | 深圳市冠旭电子股份有限公司 | Voice awakening method and device |
| CN107195304A (en) * | 2017-06-30 | 2017-09-22 | 珠海格力电器股份有限公司 | The voice control circuit and method of a kind of electric equipment |
| CN108198558A (en) * | 2017-12-28 | 2018-06-22 | 电子科技大学 | A kind of audio recognition method based on CSI data |
| CN110010125A (en) * | 2017-12-29 | 2019-07-12 | 深圳市优必选科技有限公司 | A kind of control method of intelligent robot, device, terminal device and medium |
| CN108196769A (en) * | 2017-12-29 | 2018-06-22 | 上海爱优威软件开发有限公司 | A kind of voice message originator method and terminal device |
| CN110164444A (en) * | 2018-02-12 | 2019-08-23 | 优视科技有限公司 | Voice input starting method, apparatus and computer equipment |
| CN109059199A (en) * | 2018-06-28 | 2018-12-21 | 珠海格力电器股份有限公司 | A kind of voice Rouser, method and voice control air-conditioning system |
| WO2020000923A1 (en) * | 2018-06-28 | 2020-01-02 | 珠海格力电器股份有限公司 | Voice wake-up device, method and voice control air conditioning system |
| CN110262767A (en) * | 2019-06-03 | 2019-09-20 | 清华大学 | Based on voice input Rouser, method and the medium close to mouth detection |
| WO2020244401A1 (en) * | 2019-06-03 | 2020-12-10 | 清华大学 | Voice input wake-up apparatus and method based on detection of approaching mouth, and medium |
| CN112578338A (en) * | 2019-09-27 | 2021-03-30 | 阿里巴巴集团控股有限公司 | Sound source positioning method, device, equipment and storage medium |
| CN112578338B (en) * | 2019-09-27 | 2024-05-14 | 阿里巴巴集团控股有限公司 | Sound source positioning method, device, equipment 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105869639A (en) | Speech recognition method and system | |
| KR102216048B1 (en) | Apparatus and method for recognizing voice commend | |
| CN105009204B (en) | Speech recognition power management | |
| WO2018149285A1 (en) | Voice wake-up method and apparatus, electronic device, and storage medium | |
| EP3646318B1 (en) | Electronic device and system for deciding duration of receiving voice input based on context information | |
| CN108172242B (en) | Improved Bluetooth intelligent cloud sound box voice interaction endpoint detection method | |
| CN104820556A (en) | Method and device for waking up voice assistant | |
| CN109166575A (en) | Exchange method, device, smart machine and the storage medium of smart machine | |
| CN107112017A (en) | Operate the electronic equipment and method of speech identifying function | |
| CN105575395A (en) | Voice wake-up method and apparatus, terminal, and processing method thereof | |
| CN104427079B (en) | User speech call method for early warning and device | |
| CN103811003A (en) | Voice recognition method and electronic equipment | |
| WO2015070644A1 (en) | Terminal voice control method, device, and terminal | |
| CN110164440A (en) | Electronic equipment, method and medium are waken up based on the interactive voice for sealing mouth action recognition | |
| WO2020244416A1 (en) | Voice interactive wakeup electronic device and method based on microphone signal, and medium | |
| CN110097875B (en) | Microphone signal based voice interaction wake-up electronic device, method, and medium | |
| CN103002425A (en) | Method and system for automatically triggering emergency calls and mobile terminal | |
| CN104123939A (en) | Substation inspection robot based voice interaction control method | |
| CN110428806B (en) | Microphone signal based voice interaction wake-up electronic device, method, and medium | |
| WO2016201767A1 (en) | Voice control method and device, and computer storage medium | |
| CN105183081A (en) | Voice control method of intelligent glasses and intelligent glasses | |
| US20200075008A1 (en) | Voice data processing method and electronic device for supporting same | |
| US20220116758A1 (en) | Service invoking method and apparatus | |
| KR20190042931A (en) | Electronic device for providing voice based service using external device and operating method thereof, the external device and operating method thereof | |
| CN114360527A (en) | Vehicle-mounted voice interaction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160817 |
|
| RJ01 | Rejection of invention patent application after publication |