CN109410952A - A kind of voice awakening method, apparatus and system - Google Patents
A kind of voice awakening method, apparatus and system Download PDFInfo
- Publication number
- CN109410952A CN109410952A CN201811482267.3A CN201811482267A CN109410952A CN 109410952 A CN109410952 A CN 109410952A CN 201811482267 A CN201811482267 A CN 201811482267A CN 109410952 A CN109410952 A CN 109410952A
- Authority
- CN
- China
- Prior art keywords
- voice
- control logic
- user
- speech control
- wake
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
Abstract
The embodiment of the invention discloses a kind of methods that voice wakes up, comprising: step 101, judge whether to meet preset condition, if so, 103 are thened follow the steps, it is no to then follow the steps 105；Step 103, activation exempts to wake up the operation that word wakes up Speech Control Logic；Step 105, it does not activate and exempts to wake up the operation that word wakes up Speech Control Logic.By above-mentioned voice awakening method, the process of interactive voice between user and Speech Control Logic can be simplified, keep interactive voice more convenient, it is more humane, intelligent, the efficiency of interactive voice is improved, user experience is improved.
Description
Technical field
The present embodiments relate to artificial intelligence field, in particular to a kind of voice awakening method, apparatus and system.
Background technique
With the continuous development of artificial intelligence technology, user more and more passes through interactive voice mode in daily life
Various services are obtained from terminal, various APP application programs.
Usually user says fixed wake-up keyword when people carry out interactive voice at present, and terminal acquires the keyword
Corresponding service, such as voice assistant are waken up afterwards, starts interactive voice process, and the voice for then acquiring user carries out man-machine friendship
Mutually.Either fixed wake-up keyword and user command is collected simultaneously, after terminal judgement collects wake-up keyword, according to
Thereafter user command and intelligent terminal carries out human-computer interaction process.
During above-mentioned interactive voice, user needs using fixed wake-up keyword, and interactive process is cumbersome wordy, hands over
It is mutually at high cost, especially forget to wake up keyword or user time in emergency as user nervous, needs to start voice as early as possible
When interactive process, above-mentioned interactive voice mode is too inflexible, and the time that interactive voice result needed for user obtains waits is too
It is long, reduce user experience.
Summary of the invention
For the above-mentioned problems in the prior art, the present invention proposes a kind of voice awakening method, apparatus and system.
The embodiment of the invention provides a kind of voice awakening methods, comprising:
A kind of method that voice wakes up, the voice awakening method the following steps are included:
Step 101, judge whether to meet preset condition, if so, 103 are thened follow the steps, it is no to then follow the steps 105；
Step 103, activation exempts to wake up the operation that word wakes up Speech Control Logic；
Step 105, it does not activate and exempts to wake up the operation that word wakes up Speech Control Logic.
It is described to judge whether that meeting preset condition includes:
Judge whether one-man meets preset condition as an only people in Speech Control Logic preset range；
And/or
Judge whether user issues flash appeal, if so, meeting preset condition；
And/or
The volume that interior driver speaks is detected, determines whether to meet preset condition according to the volume that it is spoken；
And/or
Judge whether Speech Control Logic is located at specific region, if so, meeting preset condition.
When Speech Control Logic indoors when, the preset range be room in；
When Speech Control Logic outdoors when, the preset range be using Speech Control Logic present position as the center of circle, R is
In the circle of radius, R is the number greater than 0；
When Speech Control Logic in vehicle or is installed in vehicle, the preset range is in vehicle.
Preferably, described to judge whether one-man expires as an only people in Speech Control Logic preset range
Sufficient preset condition includes:
Judge in Speech Control Logic preset range whether one-man, if so, determining that the artificial voice control is patrolled
The user collected meets preset condition if Speech Control Logic obtains the voice of user's sending；
Alternatively,
Obtain judge in Speech Control Logic preset range after the voice that user issues whether one-man, if then expiring
Sufficient preset condition.
It is described to judge whether user issues flash appeal, if so, meeting preset condition and including:
The voice that user issues is obtained,
Judge in the voice whether to include flash appeal, if so, meeting preset condition.
Preferably, it is described judge in Speech Control Logic preset range whether one-man, as an only people, into
One step,
Acoustic information is obtained, judges the voice whether acquired acoustic information is issued by personnel in preset range, if
It is then to meet preset condition.
Preferably, the volume that interior driver speaks is detected, determines whether to meet preset condition according to the volume that it is spoken
Including
Obtain the voice that driver issues, judge it is interior whether one-man, if so, when its speech volume is more than or equal to
When the first preset value, then meet preset condition；If interior more than one people, when its speech volume is more than or equal to the second preset value
When, then meet preset condition；Or the speech volume of driver be more than or equal to third preset value when, meet preset condition；
First preset value is lower than the second preset value.
Preferably, when the preset range is in vehicle,
Further judge whether only people is driver, if driver, then meets preset condition.
Preferably, judge whether Speech Control Logic is located at specific region, if so, meeting preset condition and including:
The voice for obtaining user, judge user voice whether with the specific region there are relevance, if so, meeting pre-
If condition.
Preferably, pre-establish user speech and specific region is associated with sexual intercourse, judge user voice whether with this
There are relevances for specific region includes
Obtain user voice and Speech Control Logic present position region, judge obtain voice and the band of position whether
With the relevance relationship match pre-established, if so, meeting preset condition.
Preferably, judge whether user is carrying out the relevant business of voice, wake up voice if so, not activating and exempting to wake up word
The operation of control logic.
Preferably, it determines whether user opens and exempts to wake up the function that word wakes up Speech Control Logic, if so, user opens
The function executes step 101.
Preferably, whether the voice for judging that the user obtained issues includes fixed wake-up keyword, is fixed if not including
Wake-up keyword, then follow the steps 101.
If the voice that the user obtained issues includes fixed wake-up keyword, waken up based on fixed wake-up keyword
Speech Control Logic.
It is described activation exempt from wake up word wake up Speech Control Logic operation include:
Speech Control Logic executes corresponding movement according to the voice of acquisition.
It is described do not activate exempt from wake up word wake up Speech Control Logic operation include:
Speech Control Logic wakes up Speech Control Logic according to other wake-up modes.
The embodiment of the present invention also provides a kind of voice Rouser, which includes:
Judgment module meets preset condition for judging whether；If meeting preset condition, triggering active module activation exempts to call out
Awake word wake operation；Otherwise, triggering active module, which does not execute, exempts to wake up word wake operation；
Active module, for the trigger signal according to judgment module, activation exempt to wake up word wake up Speech Control Logic or
It does not activate and exempts to wake up word wake-up Speech Control Logic.
Judge whether that meeting preset condition includes:
Judge whether one-man meets preset condition as an only people in Speech Control Logic preset range；
And/or
Judge whether user issues flash appeal, if so, meeting preset condition；
And/or
The volume that interior driver speaks is detected, determines whether to meet preset condition according to the volume that it is spoken；
And/or
Judge whether Speech Control Logic is located at specific region, if so, meeting preset condition；
Preferably, when Speech Control Logic indoors when, the preset range be room in；
When Speech Control Logic outdoors when, the preset range be using Speech Control Logic present position as the center of circle, R is
In the circle of radius, R is the number greater than 0；
When Speech Control Logic in vehicle or is installed in vehicle, the preset range is in vehicle.
Preferably, described to judge whether one-man expires as an only people in Speech Control Logic preset range
Sufficient preset condition includes:
Judge in Speech Control Logic preset range whether one-man, if so, determining that the artificial voice control is patrolled
The user collected meets preset condition if Speech Control Logic obtains the voice of user's sending；
Alternatively,
Obtain judge in Speech Control Logic preset range after the voice that user issues whether one-man, if then expiring
Sufficient preset condition.
Preferably, described to judge whether user issues flash appeal, if so, meeting preset condition and including:
Judge in the voice of the user obtained sending whether to include flash appeal, if so, meeting preset condition.
Preferably, described to judge whether one-man expires as an only people in Speech Control Logic preset range
Sufficient preset condition includes
The voice whether acoustic information obtained is issued by personnel in preset range is judged, if so, meeting default item
Part.
Preferably, the volume that interior driver speaks is detected, determines whether to meet preset condition according to the volume that it is spoken
Including
Obtain the voice that driver issues, judge it is interior whether one-man, if so, when its speech volume is more than or equal to
When the first preset value, then meet preset condition；If interior more than one people, when its speech volume is more than or equal to the second preset value
When, then meet preset condition；Or the speech volume of driver be more than or equal to third preset value when, meet preset condition；
First preset value is lower than the second preset value.
Preferably, when the preset range is in vehicle, further judge whether only people is driving
Member, if driver, then meets preset condition.
Preferably, judge whether terminal is located at specific region, if so, meeting preset condition and including:
Judge user voice whether with the specific region there are relevances, if so, meeting preset condition.
Preferably, pre-establish user speech and specific region is associated with sexual intercourse, judge user voice whether with this
There are relevances for specific region includes
According to the voice of the user of acquisition and Speech Control Logic present position region, the voice obtained and position area are judged
Domain whether with the relevance relationship match that pre-establishes, if so, meeting preset condition.
Preferably, the judgment module is also used to, and judges whether user is carrying out the relevant business of voice, if so, judgement
It is unsatisfactory for preset condition.
Preferably, device further includes switch module, is turned on or off for user's selection and exempts to wake up word arousal function；When
When user selects to open, then opens and exempt to wake up the function that word wakes up Speech Control Logic.
Preferably, which further includes speech detection module, for judge obtain user issue voice whether include
Fixed wake-up keyword triggers judgment module and executes its function if not including fixed wake-up keyword；If comprising,
Triggering active module, which does not activate, exempts to wake up the operation that word wakes up Speech Control Logic.
It includes waking up key based on fixed that triggering active module, which does not activate the operation for exempting to wake up word wake-up Speech Control Logic,
Word wakes up Speech Control Logic.
The device further includes
Module is obtained, for obtaining the voice of user's sending.
The embodiment of the present invention also provides a kind of Speech Control Logic, including device as described above.
The embodiment of the invention provides a kind of computer equipment, the computer equipment includes processor and memory, institute
The computer instruction that memory storage can be executed by processor is stated, when processor executes above-mentioned computer instruction, is realized as above
The method.
The embodiment of the invention provides a kind of computer readable storage mediums, which is characterized in that storage computer instruction, institute
Computer instruction is stated for realizing method as described above.
Voice awakening method, device through the invention, user are not necessarily to when carrying out interactive voice with Speech Control Logic
Wake-up word is said every time, its wake-up mode is judged according to preset condition Speech Control Logic, improves wake-up voice control
Logic efficiency keeps the interactive voice of user and Speech Control Logic more natural, more humanized and intelligent.Particularly, this hair
The voice awakening method of bright proposition executes different deterministic processes according to the difference of environment, is capable of the wake-up language of more precise and high efficiency
Sound control logic.In addition, the present invention determines whether that execution is exempted from wake-up voice control and patrolled by judging whether to voice service
The operation collected, so that the false wake-up rate to Speech Control Logic reduces.
Detailed description of the invention
Fig. 1 is the method that the voice in an embodiment of the present invention wakes up.
Fig. 2 is the device that the voice in an embodiment of the present invention wakes up.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Fig. 1 is the method for exempting to wake up word wake-up that one embodiment of the invention proposes.
This method can be applied to Speech Control Logic, which includes that one-way or bi-directional can be realized voice
Software, hardware, firmware of interactive function etc., Speech Control Logic can be executed by one or more equipment.
Referring to Fig. 1, the voice awakening method the following steps are included:
Step 101, judge whether to meet preset condition, if so, 103 are thened follow the steps, it is no to then follow the steps 105；
Step 103, activation exempts to wake up word wake operation；
Step 105, it does not activate and exempts to wake up word wake operation.
Specifically, in a step 101, judging whether that meeting preset condition includes:
Judge whether one-man meets preset condition as an only people in Speech Control Logic preset range,
Then activation exempts to wake up word wake operation.When judging one-man in preset range, Speech Control Logic obtains user and issues
Voice, then wake up Speech Control Logic, corresponding movement executed according to voice.If it is determined that the default model of Speech Control Logic
Interior one-man is enclosed, and gets the voice " When the Rain Comes in Shanghai " of user, then wakes up Speech Control Logic, identifies user's
Voice calls other to service or program, in local search or by cloud server inquiry Shanghai weather, and to user feedback
Query result wakes up Speech Control Logic, chats with user if the voice for getting user is " I wants to chat with you "
It.
Alternatively,
When Speech Control Logic gets the voice of user's sending, then whether only to judge in Speech Control Logic preset range
There is a people, if one-man, starting exempts to wake up word wake operation, wakes up Speech Control Logic, holds according to user speech
Row corresponding operation.If the voice that user issues " When the Rain Comes in Shanghai " is got, to personnel's number in environment in preset range
Amount is detected, and when being judged as one-man, then starting exempts to wake up word wake operation, and the voice that identification user issues calls
Other services or program, execute the operation of inquiry weather, if user speech is chat etc. without calling other programs or service
When voice, then Speech Control Logic is only waken up, is exchanged according to user speech with it.
In the present invention, first judge in Speech Control Logic preset range whether one-man, then obtain user's hair
Voice out still first obtains the voice that user issues, then judge in preset range whether one-man both modes can be with
It is replaced mutually, is not limited to only with a certain mode therein.
And/or
The voice for obtaining user, judges whether user issues flash appeal, if so, meeting preset condition.As user says
" dialing 120 " after Speech Control Logic gets the voice that user says, judges the voice for flash appeal, then without using solid
Fixed wake-up keyword, directly wake-up Speech Control Logic, execute the order in voice, call call function, dial 120 electricity
Words.When for judging whether voice belongs to flash appeal, the voice of acquisition is identified for example, by semantic analysis, if belonging to
Flash appeal situation determines that user issues flash appeal when urgent call, emergency relief.
And/or
Judge whether Speech Control Logic is located at specific region, if so, meeting preset condition.When Speech Control Logic position
When specific region, the voice of user is obtained, directly wake-up Speech Control Logic, corresponding operating is executed according to voice, or work as
After getting the voice of user, judge whether Speech Control Logic is located at specific region, is patrolled if so, directly waking up voice control
Volume, without using fixed wake-up keyword.Such as specific region is market, supermarket, gas station, family etc. with specific function
Region, when Speech Control Logic is in the region, it will usually execute specific operation, at the region, wake up word by exempting from
Voice directly wakes up Speech Control Logic, can simplify user's operation, more convenient.Above-mentioned detection voice control is patrolled in the present invention
The position collected and the execution sequence for obtaining voice without limitation, can first carry out any of the above steps.
Further, to different specific regions, judge whether the order of voice is associated with the region, if so, meeting pre-
If condition, execution exempts to wake up word wake-up mode, e.g., when user is located at hospital, after getting the voice of user, identifies user's language
Whether sound is related to medical treatment, such as registers, payment, inquiry laboratory test report etc., wakes up voice control if so, executing and exempting to wake up keyword
The mode of logic calls other programs or service by Speech Control Logic, such as the APP of hospital, executes life indicated by voice
It enables.When user is located at market or supermarket, obtains the voice of user's progress price queries or payment or inquiry restaurant etc., sentence
Whether the voice of disconnected user is related to locating region, if so, waking up Speech Control Logic according to voice, executes respective operations.
By above-mentioned restriction, false wake-up Speech Control Logic can be avoided to a certain extent.
Preferably, the voice of user is obtained, and obtains the band of position of Speech Control Logic, voice is identified,
The relevance for judging user speech Yu Speech Control Logic position region meets preset condition if related, otherwise, no
Meet preset condition.
Relevance judgement for user speech and the band of position, can be executed, or pass through net by Speech Control Logic
Voice and the band of position are sent server by network, are executed, can also be executed by Speech Control Logic first by server, when its not
When can judge relevance between the two, then server is sent by network, judgement is executed by server, and by judging result
Feed back to Speech Control Logic.
Preferably, can pre-establish user speech and specific region is associated with sexual intercourse, which can lead to
Cross big data carry out model training, when judgement identification voice and the band of position there are when relevance, meet preset condition；Or
The voice interacted with Speech Control Logic to user in the region, and/or user are trained in the operation that the region executes, and lead to
The deep learning to user's history data is crossed, operation, and/or user speech and position area that user executes in specific region are established
The voice of the relevance relational model in domain, operation, sending which executes according to user in specific region is constantly updated, and
According to the voice command of false wake-up more new model, when the voice command of false wake-up is met certain condition, then ordered according to the voice
More new model is enabled, the relevance of the voice command and the band of position is rejected, when the voice for judging user is deposited with present position region
In relevance, Speech Control Logic is directly waken up according to the voice, executes operation corresponding with the voice of identification.
Further, which can also be customized by the user or user is voluntarily to the relevance in model
Relationship is modified, for example, user can be in the relevance of Speech Control Logic or server setting voice and the band of position
Relation table includes the band of position in list, exempts to wake up word wake up instruction, and wherein the band of position and the instruction be there are corresponding relationship,
After getting user speech, exist according to whether the phonetic decision user speech of identification and present position region belong in list
Otherwise the entry of corresponding relationship, is unsatisfactory for if so, meeting preset condition.Or user wishes to delete or increase to exempt to call out in model
Awake phonetic order can directly delete phonetic order or increase and accordingly exempt to wake up phonetic order.
Preferably, after obtaining user speech and Speech Control Logic present position region, first determine whether it matches use
The customized association sexual intercourse in family or the model according to the training of user's history data, if so, meet preset condition, otherwise, into
One step is judged according to the model of big data training, if so, meeting preset condition.By the above-mentioned means, on the one hand to sentence
Disconnected result more meets user's use habit, and quickening judges speed, on the other hand can improve user experience according to big data model.
And/or
The voice that user issues is obtained, the voice is identified, judges that the function of the voice and foreground APP and/or backstage APP is
It is no associated, if so, meeting preset condition.If foreground APP or backstage APP be music player, obtain user speech be " under
One is first ", judge that the voice is associated with above-mentioned APP, then meets preset condition.
Preferably, when executing judgement operation, first determine whether voice is associated with foreground APP, if so, meeting pre-
If condition, if it is not, further determining whether associated with backstage APP, if meeting preset condition, otherwise, it is unsatisfactory for default item
Part.It is above-mentioned successively judge by way of, can satisfy same voice simultaneously it is associated with multiple APP when, user it is expected pair
Foreground APP is controlled, without the situation controlled backstage APP.
And/or
The voice interacted to user with Speech Control Logic learns, and the higher order of utilization rate is counted, by above-mentioned height
Frequency order, which is used as, exempts to wake up word wake-up command.Such as the voice of user is obtained, voice is identified, judges the language of the identification
Whether sound belongs to high-frequency order, if so, meeting preset condition, is otherwise unsatisfactory for.By constantly learning user speech, analysis system
The mode for counting high-frequency order, can make Speech Control Logic is more flexible to exchange with user.Likewise, for false wake-up
Order, timely update rejecting.
And/or
When Speech Control Logic is in vehicle or Speech Control Logic is set on vehicle, detection driver speaks sound
Amount, determines whether to meet preset condition according to its speaking volume.After the voice for such as obtaining driver's sending, judge car whether only
There is one people of driver, if so, then meeting preset condition when its speech volume is more than or equal to the first preset value；If interior more
Then meet preset condition when its speech volume is more than or equal to the second preset value in a people；First preset value is lower than the
Two preset values.As one-man in vehicle, environment is relatively quiet, and driver can meet default item with lower volume
Part, when car is more than a people, other people one's voices in speech are interfered in order to prevent, are preset when driver's volume is higher than second
When value, meet preset condition.
For environment inside car, occupant's quantity can not also be judged, when the speech volume of driver is more than or equal to third
When preset value, it is determined as meeting preset condition；
Wherein first preset value, the second preset value, third preset value can be that user is preset or voice control
According to historical data when logic processed wakes up according to volume, as volume adaptively adjusts when volume when correct wake up and false wake-up,
It is also possible to producer's setting when factory.
In the volume for judging voice, denoising first can be carried out to voice signal, then be compared, such as compare again
The decibel of voice and default decibel value.
The above-mentioned each specific embodiment for judging whether to meet preset condition can in any combination, including said one or more
A actual conditions.
By the above method, it can simplify the operation for waking up Speech Control Logic, do not need user frequently to voice control
Logic processed repeats to say wake-up keyword, and the interactive voice process between user and Speech Control Logic is more succinct, more humane,
Intelligence improves the efficiency of man machine language's interaction.
For the above embodiment, which can be interior, in outdoor or vehicle.
1) when Speech Control Logic is located at interior
Preset range is room where Speech Control Logic.
Judge room where Speech Control Logic whether one-man, if so, swashing when getting one's voice in speech
It is living to exempt to wake up word wake operation, wake up Speech Control Logic.Preferably, external sound interferes in order to prevent, to acquisition
Sound further judges, judges whether the sound is that personnel speak the sound of generation in the room, if then meeting preset condition；
Otherwise it is unsatisfactory for the preset condition.Auditory localization technology is such as used, determines whether sound source is identical as personnel positions in room,
If they are the same, then judge what the sound obtained issued for personnel in room, then wake up Speech Control Logic, identify the voice of user,
Corresponding operation is executed according to the voice of identification.
2) when Speech Control Logic outdoors when,
Preset range is outdoor environment.
The range of Speech Control Logic detection can be set, such as using Speech Control Logic present position as the center of circle, R is radius
Circle in be detection range, R is number greater than zero, and it is pre-set that the value of R can be user.If there was only one in detection range
Individual then meets preset condition, if in detection range when more than one people, being unsatisfactory for preset condition.Likewise, can be to obtaining
Judgement operation when the sound taken is further executed such as above-mentioned terminal in the room.
3) when preset range is in vehicle
When personnel amount is a people in vehicle, meet above-mentioned preset condition.Environment inside car can also be exempted to wake up
Word wake-up condition further limits, and when the personnel are driver, meets preset condition, otherwise, when the personnel are not drivers
When, it is unsatisfactory for preset condition.Or judge whether the personnel are authorized user, if so, meeting preset condition, otherwise, it is unsatisfactory for
Preset condition.For judging whether personnel are driver, can judge by the way that whether detection user is sitting in operator seat, this
Outside, for judging whether personnel are that perhaps authorized user can also shift to an earlier date the letter of typing driver or authorized user to driver
Breath, such as finger print information, head image information, voice messaging perhaps the related information of other biological feature or other can determine people
The relevant information of member's identity, detects occupant, judges whether the personal information obtained matches with the information of preparatory typing, if
Matching, then judge the personnel for driver or authorized user.Such as shift to an earlier date the typing voice messaging of driver or authorized user, when
When occupant speaks, voice messaging is obtained, and the voice messaging of typing in advance compares, and judges whether the people for belonging to typing voice
Member, if so, being determined as driver or authorized user, meets above-mentioned preset condition, can start and exempt to wake up word wake-up voice control
The operation of logic, Speech Control Logic execute corresponding movement according to the voice of the acquisition.
Further, to different personnel be arranged it is different exempt to wake up word wake-up condition, for driver, all voices are equal
It may be implemented to exempt to wake up the function that word wakes up Speech Control Logic, for other staff, then for being related to the voice of traffic safety
Order exempts to wake up word wake-up Speech Control Logic failure.Therefore, after the voice for obtaining user, judge whether the user is driving
Otherwise member further judges whether user speech is related to traffic safety if so then execute exempting to wake up word arousal function, if so,
It then cannot achieve and exempt to wake up word arousal function, otherwise directly wake up Speech Control Logic.
In step 103, when determining to meet preset condition according to any of the above-described mode, then voice control can directly be waken up
Logic processed executes corresponding movement according to the voice of the user obtained.
As described above, after meeting preset condition, Speech Control Logic is waken up, identifies user speech, when needing to call
When other programs or function execute user voice command, then other programs or function are called, and to user feedback implementing result, when
When without calling other programs or function, then speech exchange is carried out according to the voice of identification and user.
In step 105, it when determining to be unsatisfactory for preset condition, does not activate and exempts to wake up word wake-up Speech Control Logic
Operation.
According to above-mentioned judgment step judgement be unsatisfactory for preset condition when, then do not activate exempt from wake up word wake up voice control patrol
The operation collected, needs to wake up Speech Control Logic using fixed wake-up keyword or other commonly wake up voice controls and patrol
The mode collected is waken up.
The method that the voice that present embodiment provides wakes up Speech Control Logic, by judging whether Speech Control Logic is full
Sufficient preset condition, when meeting preset condition, activation exempts to wake up the mode that word wakes up Speech Control Logic, simplifies man machine language
Interactive process improves the experience of user, and making Speech Control Logic more easily is user service.
In another embodiment, above-mentioned in order to prevent to exempt to wake up the method false wake-up voice that word wakes up Speech Control Logic
Control logic further detects whether the user is carrying out voice when Speech Control Logic gets the voice of user's sending
Communication service does not activate when user lifts up one's voice if user is carrying out voice communication service and exempts to wake up word wake operation, otherwise
Do further judgement in the present inventive method again.For example the user has calling to access perhaps outgoing call or making a phone call,
Or carrying out video communication service or voice communication service with other people, then it does not activate and exempts to wake up word wake operation.At this
In the case of kind, if user needs to wake up Speech Control Logic, language can be waken up using existing wake-up mode in the prior art
Sound control logic such as wakes up Speech Control Logic using fixed wake-up word.For example, user is and friend calls, inquiry
Friend " Shanghai rain not ", in this case, Speech Control Logic obtains and identifies the voice of user, according to exempting from wake-up word
Wake-up mode, Speech Control Logic can inquire weather condition by false wake-up, and influencing user makes a phone call, embodiment party through the invention
Formula, Speech Control Logic detect that user is making a phone call, then only when user utilize existing wake-up mode, such as say including
When the fixed voice for waking up keyword, such as " small suddenly, When the Rain Comes in Shanghai " or " When the Rain Comes in Shanghai, small suddenly ", voice control
Logic identification go out it is fixed wake up keyword " small suddenly ", then waken up by the way of keyword wake-up Speech Control Logic using fixed to language
Sound control logic wakes up, and identifies voice associated with " small suddenly ", executes corresponding movement according to voice, such as acquisition user says
Voice within the scope of " small suddenly " Shi Qianhou certain time out, analyzes the voice, judges which content is and voice control
The content of analog voice intercorrelation, the content which content is user and other side makes a phone call identify and Speech Control Logic
After the related content of interactive voice, corresponding movement is executed according to the related content, such as inquires the weather in Shanghai.If judging user
Voice communication service is not carried out, thens follow the steps 101, further determines whether to meet preset condition, side according to the invention
Method executes.
By the above-mentioned means, effectively preventing when Speech Control Logic enabling is exempted to wake up word wake operation, just because of user
The false wakeups Speech Control Logic in the voice of progress relevant business achievees the effect that the probability for reducing false wake-up.
In another embodiment, the choosing for whether enabling and exempting to wake up word arousal function can be set in Speech Control Logic
, if user opens the function, the above method is executed, if user closes the function, is called out using commonly used in the prior art
The mode of waking up, such as fixed wake-up keyword wake up Speech Control Logic.By the setting, user can be more flexible according to it
It needs to select its voice wake-up mode.
In another embodiment, when Speech Control Logic obtains the voice that user issues, first the voice is known
Not, judge whether comprising fixed wake-up keyword, if so, by voice control is waken up using the fixed word that wakes up in the prior art
The mode and Speech Control Logic of logic carry out interactive voice, and interactive mode can be carried out in a manner of as previously described.If not wrapping
Containing fixed wake-up keyword, 101 are thened follow the steps, voice awakening method according to the invention executes.
Such as user says " small suddenly, When the Rain Comes in Shanghai ", Speech Control Logic collects the voice of user, identify including
It is fixed to wake up keyword " small suddenly ", then Speech Control Logic is waken up by the method for the prior art, executes the movement of voice instruction.Or
Person, user say " When the Rain Comes in Shanghai, small suddenly ", are located at behind the movement that user speech indicates although waking up keyword, language
Sound control logic by the word as a whole, identify including it is fixed wake up keyword " small suddenly ", then using solid
Surely the mode for waking up keyword wake-up Speech Control Logic wakes up Speech Control Logic, executes the movement indicated in the voice, looks into
Ask the weather in Shanghai, it is determined whether rain, and to user feedback result.
When user says " When the Rain Comes in Shanghai ", due to not including fixed wake-up keyword in the voice, then according to this hair
The mode of bright wake-up Speech Control Logic carries out Speech Control Logic wake-up, i.e. execution above-mentioned steps 101.
Preferably, in voice awakening method of the invention, the above-mentioned method and step for preventing false wake-up Speech Control Logic
With this judge in the voice obtained whether include fixed wake-up keyword the step of can be carried out, or execution the two
One.When being wherein carried out, above-mentioned steps are in no particular order.
The method for waking up Speech Control Logic to voice of the present invention above is described in detail.
Fig. 2 is the structural schematic diagram of voice Rouser provided by the invention, for executing the above method, as shown in Fig. 2,
Voice Rouser provided in this embodiment includes:
Judgment module meets preset condition for judging whether；If meeting preset condition, triggering active module activation exempts to call out
Awake word wake operation；Otherwise, triggering active module, which does not execute, exempts to wake up word wake operation；
Active module, for the trigger signal according to judgment module, activation exempt to wake up word wake up Speech Control Logic or
It does not activate and exempts to wake up word wake-up Speech Control Logic；
Preferably, judge whether that meeting preset condition includes:
Judge whether one-man meets preset condition as an only people in Speech Control Logic preset range；
And/or
Judge whether user issues flash appeal, if so, meeting preset condition；
And/or
The volume that interior driver speaks is detected, determines whether to meet preset condition according to the volume that it is spoken；
And/or
Judge whether Speech Control Logic is located at specific region, if so, meeting preset condition；
And/or
Judge whether the voice of the user obtained is associated with the function of foreground APP and/or backstage APP, if so, meeting
Preset condition；
And/or
Judge whether the voice of the user obtained belongs to high-frequency order, if so, meeting preset condition.
Further,
When Speech Control Logic indoors when, the preset range be room in；
When Speech Control Logic outdoors when, the preset range be using Speech Control Logic present position as the center of circle, R is
In the circle of radius, R is the number greater than 0；
When Speech Control Logic in vehicle or is installed in vehicle, the preset range is in vehicle.
Further, it is described judge in Speech Control Logic preset range whether one-man, as an only people,
Meeting preset condition includes:
Judge in Speech Control Logic preset range whether one-man, if so, determining that the artificial voice control is patrolled
The user collected meets preset condition if obtaining the voice of user's sending；
Alternatively,
Obtain judge in Speech Control Logic preset range after the voice that user issues whether one-man, if then expiring
Sufficient preset condition.
It is described to judge whether user issues flash appeal, if so, meeting preset condition and including:
Judge in the voice of the user obtained sending whether to include flash appeal, if so, meeting preset condition.
Preferably, described to judge whether one-man expires as an only people in Speech Control Logic preset range
Sufficient preset condition includes
The voice whether acoustic information obtained is issued by personnel in preset range is judged, if so, meeting default item
Part.
Preferably, the volume that interior driver speaks is detected, determines whether to meet preset condition according to the volume that it is spoken
Including
After obtaining the voice that driver issues, judge it is interior whether one-man, if so, when its speech volume is greater than etc.
When the first preset value, then meet preset condition；If interior more than one people, when its speech volume is more than or equal to the second preset value
When, then meet preset condition；Or the speech volume of driver be more than or equal to third preset value when, meet preset condition；
First preset value is lower than the second preset value.
When the preset range is in vehicle, further judge whether only people is driver, if
Driver then meets preset condition.
Preferably, the judgment module is also used to, and judges whether user is carrying out the relevant business of voice, if so, judgement
It is unsatisfactory for preset condition.
Preferably, which further includes switch module, is turned on or off for user's selection and exempts to wake up word arousal function；
When user selects to open, then opens and exempt to wake up the function that word wakes up Speech Control Logic, execute method of the invention, otherwise,
The function is closed, using wake-up mode commonly used in the prior art, such as fixed wake-up keyword wakes up Speech Control Logic.
Preferably, which further includes speech detection module, for judge obtain user issue voice whether include
Fixed wake-up keyword triggers judgment module and executes its function if not including fixed wake-up keyword；If comprising,
Triggering active module, which does not activate, exempts to wake up the operation that word wakes up Speech Control Logic, using wake-up side commonly used in the prior art
Formula, such as fixed wake-up keyword wake up Speech Control Logic.
Optionally, the device further include:
Module is obtained, for obtaining the voice of user's sending；
The acquisition module can be microphone or microphone array.
It includes that Speech Control Logic is corresponding according to the execution of the voice of acquisition that activation, which exempts to wake up word to wake up Speech Control Logic,
Movement, if desired calls other programs or service, then other programs or service is called, and to user feedback implementing result, if nothing
When need to call other programs or the voice of service, then Speech Control Logic is only waken up, is exchanged according to user speech with it.
It does not activate and exempts from wake-up word to wake up Speech Control Logic to include waking up Speech Control Logic according to other wake-up modes.
The mode that above-mentioned modules specifically execute above-mentioned each step is same as mentioned above.
The present invention also provides a kind of Speech Control Logic, which includes above-mentioned voice Rouser.
The present invention also provides a kind of computer equipment, the computer equipment includes processor and memory, the storage
The computer instruction that device storage can be executed by processor is realized as described above when processor executes above-mentioned computer instruction
Method.
The present invention also provides a kind of computer readable storage mediums, store computer instruction, and the computer instruction is used for
Realize method as described above.
It can be using any combination of one or more computer-readable media.Computer-readable medium can be calculating
Machine readable signal medium or computer readable storage medium.Computer readable storage medium can for example be but not limited to electricity,
Magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Computer-readable storage
Medium may include: the electrical connection with one or more conducting wires, portable computer diskette, hard disk, random access memory
(RAM), read-only memory (ROM), flash memory, erasable programmable read only memory (EPROM), optical fiber, portable compact disc
Read-only memory (CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document,
Computer readable storage medium can be any tangible medium for including or store program, which can be commanded and execute system
System, device or device use or in connection.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code.
It is described above to be intended merely to facilitate the example for understanding the present invention and enumerating, it is not used in and limits the scope of the invention.?
When specific implementation, those skilled in the art can according to the actual situation change the component of device, increase, reduce, not
The step of method, can be changed according to the actual situation on the basis of the function that influence method is realized, increased, reduced or
Change sequence.
Although an embodiment of the present invention has been shown and described, it should be understood by those skilled in the art that: do not departing from this
These embodiments can be carried out with a variety of change, modification, replacement and modification in the case where the principle and objective of invention, it is of the invention
Range is limited by claim and its equivalent replacement, without creative work improvements introduced etc., should be included in this hair
Within bright protection scope.
Claims (16)
1. a kind of method that voice wakes up, which is characterized in that the voice awakening method the following steps are included:
Step 101, judge whether to meet preset condition, if so, 103 are thened follow the steps, it is no to then follow the steps 105；
Step 103, activation exempts to wake up the operation that word wakes up Speech Control Logic；
Step 105, it does not activate and exempts to wake up the operation that word wakes up Speech Control Logic.
2. the method according to claim 1, wherein
It is described to judge whether that meeting preset condition includes:
Judge whether one-man meets preset condition as an only people in Speech Control Logic preset range；
And/or
Judge whether user issues flash appeal, if so, meeting preset condition；
And/or
The volume that interior driver speaks is detected, determines whether to meet preset condition according to the volume that it is spoken；
And/or
Judge whether Speech Control Logic is located at specific region, if so, meeting preset condition.
3. according to the method described in claim 2, it is characterized in that,
When Speech Control Logic indoors when, the preset range be room in；
When Speech Control Logic outdoors when, the preset range be using Speech Control Logic present position as the center of circle, R is radius
Circle in, R is number greater than 0；
When Speech Control Logic in vehicle or is installed in vehicle, the preset range is in vehicle.
4. according to the method described in claim 2, it is characterized in that,
It is described to judge whether one-man meets preset condition as an only people in Speech Control Logic preset range
Include:
Judge in Speech Control Logic preset range whether one-man, if so, determining the artificial Speech Control Logic
User meets preset condition if Speech Control Logic obtains the voice of user's sending；
Alternatively,
Obtain judge in Speech Control Logic preset range after the voice that user issues whether one-man, if then meeting in advance
If condition.
5. according to the method described in claim 2, it is characterized in that,
It is described to judge whether user issues flash appeal, if so, meeting preset condition and including:
The voice that user issues is obtained,
Judge in the voice whether to include flash appeal, if so, meeting preset condition.
6. according to the method described in claim 2, it is characterized in that, further comprising
It is described judge in Speech Control Logic preset range whether one-man, as an only people, further,
Acoustic information is obtained, judges the voice whether acquired acoustic information is issued by personnel in preset range, if so,
Meet preset condition.
7. according to the method described in claim 2, it is characterized in that,
The volume that interior driver speaks is detected, determines whether that meeting preset condition includes according to the volume that it is spoken
Obtain the voice that driver issues, judge it is interior whether one-man, if so, when its speech volume is more than or equal to first
When preset value, then meet preset condition；If interior more than one people, when its speech volume is more than or equal to the second preset value, then
Meet preset condition；Or the speech volume of driver be more than or equal to third preset value when, meet preset condition；
First preset value is lower than the second preset value.
8. according to the method described in claim 3, it is characterized in that,
When the preset range is in vehicle,
Further judge whether only people is driver, if driver, then meets preset condition.
9. according to the method described in claim 2, it is characterized in that,
Judge whether Speech Control Logic is located at specific region, if so, meeting preset condition and including:
The voice for obtaining user, judge user voice whether with the specific region there are relevance, if so, meeting default item
Part.
10. according to the method described in claim 9, it is characterized in that,
Pre-establish user speech and specific region is associated with sexual intercourse, judges whether the voice of user exists with the specific region
Relevance includes
Obtain user voice and Speech Control Logic present position region, judge obtain voice and the band of position whether in advance
The relevance relationship match first established, if so, meeting preset condition.
11. the method according to claim 1, wherein this method further includes
Judge whether user is carrying out the relevant business of voice, wakes up Speech Control Logic if so, not activating and exempting to wake up word
Operation.
12. the method according to claim 1, wherein
It determines whether user opens and exempts to wake up the function that word wakes up Speech Control Logic, if so, user opens the function, execute
Step 101.
13. the method according to claim 1, wherein
Whether the voice for judging that the user obtained issues includes fixed wake-up keyword, if it is crucial not include fixed wake-up
Word thens follow the steps 101.
14. according to the method for claim 11, which is characterized in that
If the voice that the user obtained issues includes fixed wake-up keyword, voice is waken up based on fixed wake-up keyword
Control logic.
15. the method according to claim 1, wherein
It is described activation exempt from wake up word wake up Speech Control Logic operation include:
Speech Control Logic executes corresponding movement according to the voice of acquisition.
16. the method according to claim 1, wherein
It is described do not activate exempt from wake up word wake up Speech Control Logic operation include:
Speech Control Logic is waken up according to other wake-up modes.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811261773 | 2018-10-26 | ||
| CN201811261773X | 2018-10-26 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109410952A true CN109410952A (en) | 2019-03-01 |
| CN109410952B CN109410952B (en) | 2020-02-28 |
Family
ID=65457390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811482267.3A Active CN109410952B (en) | 2018-10-26 | 2018-12-05 | Voice awakening method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109410952B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110047487A (en) * | 2019-06-05 | 2019-07-23 | 广州小鹏汽车科技有限公司 | Awakening method, device, vehicle and the machine readable media of vehicle-mounted voice equipment |
| CN110727821A (en) * | 2019-10-12 | 2020-01-24 | 深圳海翼智新科技有限公司 | Method, apparatus, system and computer storage medium for preventing device from being awoken by mistake |
| CN111028846A (en) * | 2019-12-25 | 2020-04-17 | 北京梧桐车联科技有限责任公司 | Method and device for registration of wake-up-free words |
| CN111145749A (en) * | 2019-12-31 | 2020-05-12 | 联想(北京)有限公司 | Control method and control device |
| 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 |
| CN111354360A (en) * | 2020-03-17 | 2020-06-30 | 北京百度网讯科技有限公司 | Voice interaction processing method and device and electronic equipment |
| CN111816192A (en) * | 2020-07-07 | 2020-10-23 | 云知声智能科技股份有限公司 | Voice equipment and control method, device and equipment thereof |
| CN112017651A (en) * | 2019-05-31 | 2020-12-01 | 百度在线网络技术（北京）有限公司 | Voice control method and device of electronic equipment, computer equipment and storage medium |
| CN112037786A (en) * | 2020-08-31 | 2020-12-04 | 百度在线网络技术（北京）有限公司 | Voice interaction method, device, equipment and storage medium |
| CN113301247A (en) * | 2020-02-05 | 2021-08-24 | 佳能株式会社 | Voice input device, control method thereof 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 |
| CN113823062A (en) * | 2021-09-13 | 2021-12-21 | 百度在线网络技术（北京）有限公司 | Emergency rescue method, device, electronic equipment and storage medium |
| WO2023241473A1 (en) * | 2022-06-13 | 2023-12-21 | 华为技术有限公司 | Method for processing speech data, and terminal device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441869A (en) * | 2007-11-21 | 2009-05-27 | 联想(北京)有限公司 | Method and terminal for speech recognition of terminal user identification |
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| CN103813003A (en) * | 2012-11-15 | 2014-05-21 | 三星电子（中国）研发中心 | Data sharing method of mobile terminal in communication and mobile terminal |
| CN105183081A (en) * | 2015-09-07 | 2015-12-23 | 北京君正集成电路股份有限公司 | Voice control method of intelligent glasses and intelligent glasses |
| US20160196823A1 (en) * | 2015-01-02 | 2016-07-07 | Atieva, Inc. | Voice Command Activated Vehicle Camera System |
| CN106143452A (en) * | 2016-09-24 | 2016-11-23 | 华北理工大学 | Selectivity acoustic control brake system and method |
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | A kind of method and apparatus waking up voice service up |
| CN106775569A (en) * | 2017-01-12 | 2017-05-31 | 环旭电子股份有限公司 | Setting position prompt system and method |
| CN107949880A (en) * | 2015-09-09 | 2018-04-20 | 三菱电机株式会社 | Vehicle-mounted speech recognition equipment and mobile unit |
| CN108337362A (en) * | 2017-12-26 | 2018-07-27 | 百度在线网络技术（北京）有限公司 | Voice interactive method, device, equipment and storage medium |
-
2018
- 2018-12-05 CN CN201811482267.3A patent/CN109410952B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441869A (en) * | 2007-11-21 | 2009-05-27 | 联想(北京)有限公司 | Method and terminal for speech recognition of terminal user identification |
| CN103813003A (en) * | 2012-11-15 | 2014-05-21 | 三星电子（中国）研发中心 | Data sharing method of mobile terminal in communication and mobile terminal |
| CN103561175A (en) * | 2013-11-05 | 2014-02-05 | 广东欧珀移动通信有限公司 | Method using mobile terminal to carry out voice awakening and device thereof |
| US20160196823A1 (en) * | 2015-01-02 | 2016-07-07 | Atieva, Inc. | Voice Command Activated Vehicle Camera System |
| CN105183081A (en) * | 2015-09-07 | 2015-12-23 | 北京君正集成电路股份有限公司 | Voice control method of intelligent glasses and intelligent glasses |
| CN107949880A (en) * | 2015-09-09 | 2018-04-20 | 三菱电机株式会社 | Vehicle-mounted speech recognition equipment and mobile unit |
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | A kind of method and apparatus waking up voice service up |
| CN106143452A (en) * | 2016-09-24 | 2016-11-23 | 华北理工大学 | Selectivity acoustic control brake system and method |
| CN106775569A (en) * | 2017-01-12 | 2017-05-31 | 环旭电子股份有限公司 | Setting position prompt system and method |
| CN108337362A (en) * | 2017-12-26 | 2018-07-27 | 百度在线网络技术（北京）有限公司 | Voice interactive method, device, equipment and storage medium |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017651A (en) * | 2019-05-31 | 2020-12-01 | 百度在线网络技术（北京）有限公司 | Voice control method and device of electronic equipment, computer equipment and storage medium |
| CN110047487A (en) * | 2019-06-05 | 2019-07-23 | 广州小鹏汽车科技有限公司 | Awakening method, device, vehicle and the machine readable media of vehicle-mounted voice equipment |
| CN110047487B (en) * | 2019-06-05 | 2022-03-18 | 广州小鹏汽车科技有限公司 | Wake-up method and device for vehicle-mounted voice equipment, vehicle and machine-readable medium |
| CN110727821A (en) * | 2019-10-12 | 2020-01-24 | 深圳海翼智新科技有限公司 | Method, apparatus, system and computer storage medium for preventing device from being awoken by mistake |
| 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 |
| CN111028846A (en) * | 2019-12-25 | 2020-04-17 | 北京梧桐车联科技有限责任公司 | Method and device for registration of wake-up-free words |
| CN111028846B (en) * | 2019-12-25 | 2022-08-16 | 北京梧桐车联科技有限责任公司 | Method and device for registration of wake-up-free words |
| CN111145749A (en) * | 2019-12-31 | 2020-05-12 | 联想(北京)有限公司 | Control method and control device |
| CN111145749B (en) * | 2019-12-31 | 2023-05-02 | 联想(北京)有限公司 | Control method and control device |
| US11600277B2 (en) | 2020-02-05 | 2023-03-07 | Canon Kabushiki Kaisha | Voice input apparatus, control method thereof, and storage medium for executing processing corresponding to voice instruction |
| CN113301247A (en) * | 2020-02-05 | 2021-08-24 | 佳能株式会社 | Voice input device, control method thereof and storage medium |
| CN113301247B (en) * | 2020-02-05 | 2023-12-05 | 佳能株式会社 | Image pickup apparatus, control method thereof, and storage medium |
| CN111354360A (en) * | 2020-03-17 | 2020-06-30 | 北京百度网讯科技有限公司 | Voice interaction processing method and device and electronic equipment |
| CN111816192A (en) * | 2020-07-07 | 2020-10-23 | 云知声智能科技股份有限公司 | Voice equipment and control method, device and equipment thereof |
| CN112037786A (en) * | 2020-08-31 | 2020-12-04 | 百度在线网络技术（北京）有限公司 | Voice interaction 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 |
| CN113823062A (en) * | 2021-09-13 | 2021-12-21 | 百度在线网络技术（北京）有限公司 | Emergency rescue method, device, electronic equipment and storage medium |
| WO2023241473A1 (en) * | 2022-06-13 | 2023-12-21 | 华为技术有限公司 | Method for processing speech data, and terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109410952B (en) | 2020-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109410952A (en) | A kind of voice awakening method, apparatus and system | |
| US10770073B2 (en) | Reducing the need for manual start/end-pointing and trigger phrases | |
| EP3158427B1 (en) | System and method for speech-enabled personalized operation of devices and services in multiple operating environments | |
| KR102444165B1 (en) | Apparatus and method for providing a meeting adaptively | |
| CN105868827B (en) | A kind of multi-modal exchange method of intelligent robot and intelligent robot | |
| US20200068304A1 (en) | Terminal and vehicle control method of mobile terminal using machine learning | |
| US10565509B2 (en) | Adaptive virtual intelligent agent | |
| CN109243431A (en) | A kind of processing method, control method, recognition methods and its device and electronic equipment | |
| CN106201424A (en) | A kind of information interacting method, device and electronic equipment | |
| CN105284099B (en) | For hands-free interaction come adjust automatically user interface | |
| CN109102802A (en) | System for handling user spoken utterances | |
| CN109256134A (en) | A kind of voice awakening method, storage medium and terminal | |
| KR20190096308A (en) | electronic device | |
| CN106774845A (en) | A kind of intelligent interactive method, device and terminal device | |
| KR20200074690A (en) | Electonic device and Method for controlling the electronic device thereof | |
| CN108897517A (en) | A kind of information processing method and electronic equipment | |
| CN116417003A (en) | Voice interaction system, method, electronic device and storage medium | |
| JPWO2019163247A1 (en) | Information processing equipment, information processing methods, and programs | |
| US11381675B2 (en) | Command based interactive system and a method thereof | |
| KR102612835B1 (en) | Electronic device and method for executing function of electronic device | |
| CN109285549A (en) | Method of speech processing and device | |
| TWM648143U (en) | Speech recognition device | |
| CN114543306A (en) | Method and device for controlling air conditioner, air conditioner and storage medium | |
| CN110119083A (en) | The awakening method of smartwatch |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |