CN107704275A - Smart machine awakening method, device, server and smart machine - Google Patents
Smart machine awakening method, device, server and smart machine Download PDFInfo
- Publication number
- CN107704275A CN107704275A CN201710786739.3A CN201710786739A CN107704275A CN 107704275 A CN107704275 A CN 107704275A CN 201710786739 A CN201710786739 A CN 201710786739A CN 107704275 A CN107704275 A CN 107704275A
- Authority
- CN
- China
- Prior art keywords
- smart machine
- wake
- word
- voice signal
- server
- 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
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000002618 waking effect Effects 0.000 claims abstract description 42
- 238000004590 computer program Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 16
- 230000006870 function Effects 0.000 description 8
- 235000013399 edible fruits Nutrition 0.000 description 6
- 239000000463 material Substances 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 5
- 230000003993 interaction Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 244000050510 Cunninghamia lanceolata Species 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/4401—Bootstrapping
- G06F9/4418—Suspend and resume; Hibernate and awake
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Theoretical Computer Science (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Security & Cryptography (AREA)
- Telephonic Communication Services (AREA)
Abstract
The present invention proposes a kind of smart machine awakening method, device, server and smart machine, wherein, this method includes：Obtain the voice signal that smart machine is sent；The voice signal is identified, determines recognition result corresponding to the voice signal；When it is determined that any matching degree for waking up word model corresponding with the smart machine is more than threshold value in the recognition result, wake-up instruction is issued to the smart machine.Thus, voice signal is identified by using server and wake-up control is carried out to smart machine, reduce the consumption of hardware performance in wakeup process, and user is allowd to wake up smart machine using customized wake-up word, enrich wake-up word, the flexibility of wake-up is improved, the individual demand of user can be better met, improves Consumer's Experience.
Description
Technical field
The present invention relates to intelligent device management technical field, more particularly to a kind of smart machine awakening method, device, service
Device and smart machine.
Background technology
At present, as the development and the improvement of people's living standards of science and technology, the smart machine of such as intelligent sound box are extensive
Applied in the life of people, study and work.
Prior art, when being controlled to smart machine, it is necessary to be waken up first with word is waken up to smart machine, then
Smart machine is controlled by control instruction.When being waken up to smart machine, mode that generally use wakes up offline,
Using single fixed wake-up word set in advance or several wake-up words of fixation, smart machine is waken up.
The above-mentioned mode waken up to smart machine, wake-up word is single, renewal is dumb, it is impossible to meets the individual character of user
Change demand, and wakeup process may consume more hardware performance, poor user experience.
The content of the invention
It is contemplated that at least solves one of technical problem in correlation technique to a certain extent.
Therefore, the present invention proposes a kind of smart machine awakening method, voice signal is identified by using server
And wake-up control is carried out to smart machine, the consumption of hardware performance in wakeup process is reduced, and user is utilized certainly
The wake-up word of definition wakes up smart machine, enriches wake-up word, improves the flexibility of wake-up, can better meet user's
Individual demand, improve Consumer's Experience.
The present invention also proposes another smart machine awakening method.
The present invention also proposes a kind of smart machine Rouser.
The present invention also proposes another smart machine Rouser.
The present invention also proposes a kind of server.
The present invention also proposes a kind of smart machine.
The present invention also proposes a kind of computer-readable recording medium.
The present invention also proposes another computer-readable recording medium.
First aspect present invention embodiment proposes a kind of smart machine awakening method, including：Smart machine is obtained to send
Voice signal；The voice signal is identified, determines recognition result corresponding to the voice signal；It is determined that the knowledge
When any matching degree for waking up word model corresponding with the smart machine is more than threshold value in other result, under the smart machine
Hair wakes up instruction.
The smart machine awakening method of the embodiment of the present invention, the voice signal that smart machine is sent is obtained first, it is then right
Voice signal is identified, and determines recognition result corresponding to the voice signal, it is determined that the recognition result and the intelligence
When any matching degree for waking up word model is more than threshold value corresponding to equipment, wake-up instruction is issued to the smart machine.Thus, lead to
Cross and voice signal is identified using server and wake-up control is carried out to smart machine, reduce hardware in wakeup process
The consumption of energy, and allow user to wake up smart machine using customized wake-up word, wake-up word is enriched, improves wake-up
Flexibility, the individual demand of user can be better met, improve Consumer's Experience.
Second aspect of the present invention embodiment proposes a kind of smart machine awakening method, including：To the voice signal of acquisition
It is identified, obtains recognition result；It is determined that the recognition result is respectively less than threshold with default N number of matching degree for waking up word model
During value, the voice signal is sent to server, so that the speech signal is identified the server, wherein N is
Positive integer more than or equal to 1；If getting the wake-up instruction that the server returns, smart machine is waken up.
The smart machine awakening method of the embodiment of the present invention, it is identified in the voice signal to acquisition, obtains identification knot
After fruit, however, it is determined that recognition result is respectively less than threshold value with default N number of matching degree for waking up word model, then is sent to voice signal
Server, so that voice signal is identified server, if getting the wake-up instruction of server return, wakes up intelligence and set
It is standby.Hereby it is achieved that wake-up control is carried out to smart machine by way of waking up offline, and using server to voice signal
It is identified and wake-up control is carried out to smart machine, reduce the consumption of hardware performance in wakeup process, and make it that user can
To wake up smart machine using customized wake-up word, wake-up word is enriched, improves the flexibility of wake-up, can preferably be expired
The individual demand of sufficient user, improve Consumer's Experience.
Third aspect present invention embodiment proposes a kind of smart machine Rouser, including：First acquisition module, is used for
Obtain the voice signal that smart machine is sent；First determining module, for the voice signal to be identified, determine institute's predicate
Recognition result corresponding to sound signal；First sending module, for it is determined that in the recognition result it is corresponding with the smart machine
The matching degree of any wake-up word model when being more than threshold value, issue wake-up instruction to the smart machine.
The smart machine Rouser of the embodiment of the present invention, the voice signal that smart machine is sent is obtained first, it is then right
Voice signal is identified, and determines recognition result corresponding to the voice signal, it is determined that the recognition result and the intelligence
When any matching degree for waking up word model is more than threshold value corresponding to equipment, wake-up instruction is issued to the smart machine.Thus, lead to
Cross and voice signal is identified using server and wake-up control is carried out to smart machine, reduce hardware in wakeup process
The consumption of energy, and allow user to wake up smart machine using customized wake-up word, wake-up word is enriched, improves wake-up
Flexibility, the individual demand of user can be better met, improve Consumer's Experience.
Fourth aspect present invention embodiment proposes a kind of smart machine Rouser, including：Second acquisition module, is used for
The voice signal of acquisition is identified, obtains recognition result；Second sending module, for it is determined that the recognition result with it is pre-
If the matching degree of N number of wake-up word model when being respectively less than threshold value, the voice signal is sent to server, so that the service
The speech signal is identified device, and wherein N is the positive integer more than or equal to 1；Wake module, for get it is described
During the wake-up instruction that server returns, smart machine is waken up.
The smart machine Rouser of the embodiment of the present invention, it is identified in the voice signal to acquisition, obtains identification knot
After fruit, however, it is determined that recognition result is respectively less than threshold value with default N number of matching degree for waking up word model, then is sent to voice signal
Server, so that voice signal is identified server, if getting the wake-up instruction of server return, wakes up intelligence and set
It is standby.Hereby it is achieved that wake-up control is carried out to smart machine by way of waking up offline, and using server to voice signal
It is identified and wake-up control is carried out to smart machine, reduce the consumption of hardware performance in wakeup process, and make it that user can
To wake up smart machine using customized wake-up word, wake-up word is enriched, improves the flexibility of wake-up, can preferably be expired
The individual demand of sufficient user, improve Consumer's Experience.
Fifth aspect present invention embodiment proposes a kind of server, including：
Memory, processor and the computer program that can be run on the memory and on the processor is stored in,
Smart machine awakening method as described in relation to the first aspect is realized during the computing device described program.
Sixth aspect present invention embodiment proposes a kind of smart machine, including：
Memory, processor and the computer program that can be run on the memory and on the processor is stored in,
The smart machine awakening method as described in second aspect is realized during the computing device described program.
Seventh aspect present invention embodiment proposes a kind of computer-readable recording medium, is stored thereon with computer journey
Sequence, smart machine awakening method as described in relation to the first aspect is realized when the program is executed by processor.
Eighth aspect present invention embodiment proposes a kind of computer-readable recording medium, is stored thereon with computer journey
Sequence, the smart machine awakening method as described in second aspect is realized when the program is executed by processor.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein：
Fig. 1 is the flow chart of the smart machine awakening method of one embodiment of the invention；
Fig. 2 is the flow chart of the smart machine awakening method of another embodiment of the present invention；
Fig. 3 is the signaling interaction diagram of the smart machine awakening method of one embodiment of the invention；
Fig. 4 is the structural representation of the smart machine Rouser of one embodiment of the invention；
Fig. 5 is the structural representation of the smart machine Rouser of another embodiment of the present invention.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
Various embodiments of the present invention are directed to prior art, when being waken up to smart machine, what generally use woke up offline
Mode, using single fixed wake-up word set in advance or several wake-up words of fixation, smart machine is waken up, it is this
Wake-up mode, wake-up word is single, renewal is dumb, it is impossible to meets the individual demand of user, and wakeup process may consume
More hardware performance, the problem of poor user experience, propose a kind of smart machine awakening method.
The voice signal of acquisition can be sent to by smart machine awakening method provided in an embodiment of the present invention, smart machine
Server is identified, so as to which server can be it is determined that recognition result any for waking up word model corresponding with smart machine
When being more than threshold value with degree, wake-up instruction is issued to smart machine, to wake up smart machine.Thus, by using server to language
Sound signal is identified and carries out wake-up control to smart machine, reduces the consumption of hardware performance in wakeup process, and cause
User can utilize customized wake-up word to wake up smart machine, enrich wake-up word, improve the flexibility of wake-up, Ke Yigeng
The good individual demand for meeting user, improve Consumer's Experience.
Below with reference to the accompanying drawings smart machine awakening method, device, server and the smart machine of the embodiment of the present invention are described.
First by taking server side as an example, smart machine awakening method provided in an embodiment of the present invention is described in detail.
Fig. 1 is the flow chart of the smart machine awakening method of one embodiment of the invention.
As shown in figure 1, the smart machine awakening method includes：
Step 101, the voice signal that smart machine is sent is obtained.
Wherein, smart machine awakening method provided in an embodiment of the present invention, can be by intelligence provided in an embodiment of the present invention
Equipment Rouser performs.The smart machine Rouser, can be configured in the clothes being controlled to smart machines such as audio amplifiers
It is engaged in device, to be waken up to smart machine.
Specifically, the voice-input devices such as microphone can be pre-set in smart machine, so as to pass through language in user
When sound wakes up to smart machine, smart machine by voice-input device, can obtain the voice signal of user, then will
Voice signal is sent to server.
Step 102, voice signal is identified, determines recognition result corresponding to voice signal.
Specifically, in the server or in configuration smart machine Rouser in the server voice can be set to know
Other module, so as to which server is after the voice signal of smart machine transmission is got, sound identification module can be utilized, to obtaining
Voice signal carry out speech recognition, to obtain recognition result corresponding to voice signal.
Step 103, it is determined that recognition result any matching degree for waking up word model corresponding with smart machine is more than threshold value
When, issue wake-up instruction to smart machine.
Wherein, threshold value can be arranged as required to.For example fixed value can be set a threshold in advance, such as 80%, 90%
Etc..Or it can be taken according to recognition result each match condition for waking up word model corresponding with smart machine, threshold value
Value.Such as when it is determined that the matching degree of recognition result each wake-up word model corresponding with smart machine is higher, can be by threshold value
It is arranged to higher value；, can when it is determined that the matching degree of recognition result each wake-up word model corresponding with smart machine is relatively low
To set a threshold to relatively low value, etc..
It can be one or multiple it should be noted that waking up word model corresponding to smart machine, herein not
It is restricted.In addition, each wake up the corresponding wake-up word of word model.
Specifically, word model can be waken up so that each wake-up word of training in advance smart machine is corresponding respectively, so as to server
It is identified to voice signal, determines recognition result corresponding to voice signal, and determines characteristic vector corresponding to recognition result
Afterwards, characteristic vector can be inputted to each wake up in word model corresponding with smart machine and carries out verification marking, to determine identification knot
The matching degree of each wake-up word model of fruit and smart machine.If server determines any wake-up word of recognition result and smart machine
The matching degree of model is more than threshold value, then it represents that and the voice signal that smart machine obtains includes waking up word corresponding to smart machine,
Wake-up instruction can be then issued to smart machine, to wake up smart machine.
As an example it is assumed that predetermined threshold value is 90%, the corresponding 3 wake-ups word models of smart machine, respectively with " slowly "
Corresponding wake-up word model A, wake-up word Model B corresponding with " day goblin ", wake-up word MODEL C corresponding with " small degree ".If service
After the voice signal that device is sent to the smart machine of acquisition is identified, determine recognition result as " day goblin ", then can determine " my god
Characteristic vector corresponding to goblin ", and characteristic vector is inputted respectively and waken up in word model A, B, C, to determine recognition result and intelligence
The matching degree of each wake-up word model of equipment.Because " day goblin " and the matching degree of wake-up word Model B are more than threshold value 90%, then service
Device can issue wake-up instruction to smart machine, to wake up smart machine.
Further, it is determined that recognition result any matching degree for waking up word model corresponding with smart machine is more than threshold value
Before, it can also obtain and word model is waken up corresponding to smart machine.That is, before step 103, can also include：
The wake-up word of the smart machine of acquisition is trained, generates wake-up word model corresponding with smart machine.
Wherein, it can be Chinese, English or other any form of wake-up words to wake up word.Smart machine can correspond to one
Or multiple wake-up words, each wake up word, corresponding wake-up word model.
Specifically, server by following various ways, can obtain the wake-up word of smart machine.
Mode one
The voice signal sent to smart machine parses, and determines to wake up word corresponding to smart machine.
Specifically, when user wishes to increase the wake-up word of smart machine, increase can be issued to smart machine by voice
The instruction of word is waken up, or, when user uses smart machine for the first time, whether smart machine can also actively be reported to user and set
The message of word is waken up, so as to which user can be sent including the newly-increased language for waking up word according to the instruction of smart machine to smart machine
Sound.After smart machine gets the voice signal of user, you can voice signal is sent into server, so as to which server can be right
The voice signal of acquisition is parsed, and determines to wake up word corresponding to smart machine.
It should be noted that in embodiments of the present invention, it is believed that it is same wake-up word that pronunciation identical, which wakes up word,.Than
Such as, " slowly ", " mountain mountain ", " China fir China fir " be same wake-up word.
For example, the existing word that wakes up of smart machine be " small degree ", can be with when user wishes that increase wakes up word " it is bewitching "
Smart machine is said by voice " small degree, I will increase name ".After smart machine gets the voice signal of user, Ke Yixiang
User returns to " you want what name increased ", so as to user can say according to the instruction of smart machine to smart machine " my god
Goblin ".After smart machine gets the voice signal for including newly-increased wake-up word of user, you can voice signal is sent into service
Device, the voice signal of acquisition can be parsed so as to server, it is determined that wake up word for " day goblin " or with " day goblin " pronunciation phase
Same wake-up word.
Or user is sent to smart machine when increasing the instruction for waking up word newly, newly-increased call out can also be included in instruction simultaneously
Awake word, such as, " small degree, I will increase name ' day goblin ' ", it is not restricted herein.
It is understood that because the pronunciation of different terms there may be similar situation, such as " slowly " and " glittering ",
" three or three ", then after server gets the voice signal of smart machine transmission, possibly it can not be parsed according to voice signal definitely
Wake-up word.Now, server can send voice signal to smart machine, whether to confirm the wake-up word that parses to user
Accurately.
For example the existing word that wakes up of smart machine is " small degree ", user wishes to increase the wake-up word " slowly " of smart machine
When, smart machine can be said " small degree, I will increase name ' slowly ' ".After smart machine gets the voice signal of user,
Voice signal can be sent to server, so as to which server can parse to the voice signal of acquisition.Due to " slowly "
The pronunciations such as " glittering ", " three or three " are similar, then the wake-up word that server parses may be " slowly ", " glittering " or " three or three ".
Now, server can send voice signal " you want increased name be ' slowly ' " to smart machine, and smart machine is reported
After voice " you want increased name be ' slowly ' ", if getting the voice signal of user's return, user can be returned
Voice signal be sent to server so that the voice signal that server returns according to user, determines to call out corresponding to smart machine
Whether awake word is " slowly " or wakes up word with " slowly " pronunciation identical.
Mode two
The text message inputted in the page is set according to user in wake-up word corresponding with smart machine, determines smart machine
Corresponding wake-up word.
Specifically, can pre-set wake-up word corresponding with smart machine sets the page, user, which needs to increase, wakes up word
When, input increased wake-up word text can be needed in the ad-hoc location for waking up the word page, be called out so as to which server can obtain
The text message that user inputs in the awake word page, and according to text message, determine to wake up word corresponding to smart machine.
It should be noted that waking up the example of word corresponding to above-mentioned determination smart machine, only schematically illustrate, it is impossible to make
For the limitation to technical solution of the present invention, those skilled in the art on this basis, can arbitrarily set determination intelligence as needed
The mode of word is waken up corresponding to energy equipment, this is not construed as limiting herein.
In addition, user need to waken up corresponding to smart machine word modify or delete etc. operate when, can also be to intelligence
Energy equipment sends voice, or is operated in wake-up word corresponding with smart machine sets the page, so as to which server can lead to
The voice signal for sending smart machine is crossed to parse, or the text envelope inputted according to user in the word setting page is waken up
Breath, determine that user needs the wake-up word changed or deleted, to be updated to waking up word corresponding to smart machine.
Specifically, server is obtained after waking up word corresponding to smart machine, you can the wake-up to the smart machine of acquisition
Word is trained, and generates wake-up word model corresponding with smart machine.
During specific implementation, server often obtains a wake-up word of smart machine, you can is called out based on the wake-up word, and with this
The language material that awake word is phonetically alike, train wake-up word model corresponding with the wake-up word.
For example the wake-up word of smart machine that server obtains is " slowly ", then can utilize " slowly " and with " slowly "
" three or three ", " glittering ", " dense " being phonetically alike ' etc. language material, training with " slowly " it is corresponding wake up word model.
It should be noted that in embodiments of the present invention, server determines corresponding with smart machine each in recognition result
When the matching degree of wake-up word model is respectively less than threshold value, recognition result can also be parsed, judge recognition result and each wake-up
The pronunciation similarity of word is waken up corresponding to word model, can be with if the pronunciation similarity that recognition result wakes up word with some is higher
Using recognition result as the training corpus trained when word model is waken up corresponding to the wake-up word, to waking up word corresponding to the wake-up word
Model is further trained, to improve the performance for waking up word model.
Specifically, smart machine awakening method provided in an embodiment of the present invention, is realized to user's by using server
The identification of voice signal and the wake-up control to smart machine, reduce the consumption of hardware performance in wakeup process.And due to clothes
Business device can obtain abundant resource, and word and abundant language material, training life are waken up so as to the smart machine based on acquisition
Into wake-up word model of good performance, user is set to be waken up by customized wake-up word to smart machine.
Smart machine awakening method provided in an embodiment of the present invention, the voice signal that smart machine is sent is obtained first, so
Voice signal is identified afterwards, determines recognition result corresponding to voice signal, it is determined that recognition result is corresponding with smart machine
The matching degree of any wake-up word model when being more than threshold value, issue wake-up instruction to smart machine.Thus, by using server
Voice signal is identified and wake-up control is carried out to smart machine, reduces the consumption of hardware performance in wakeup process, and
Allow user to wake up smart machine using customized wake-up word, enrich wake-up word, improve the flexibility of wake-up, can
To better meet the individual demand of user, improve Consumer's Experience.
Below by taking smart machine side as an example, smart machine awakening method provided in an embodiment of the present invention is carried out specifically
It is bright.
Fig. 2 is the flow chart of the smart machine awakening method of one embodiment of the invention.
As shown in Fig. 2 the smart machine awakening method includes：
Step 201, the voice signal of acquisition is identified, obtains recognition result.
Wherein, smart machine awakening method provided in an embodiment of the present invention, can be by intelligence provided in an embodiment of the present invention
Equipment Rouser performs.The smart machine Rouser, can be configured in the smart machines such as audio amplifier, mobile phone, computer, with
Smart machine is waken up.
Specifically, the voice-input devices such as microphone can be pre-set in smart machine, so as to pass through language in user
When sound wakes up to smart machine, smart machine by voice-input device, can obtain the voice signal of user.
Furthermore it is possible in the smart machine Rouser of smart machine or configuration in smart machine, voice is set to know
Other module, after getting voice signal so as to smart machine, sound identification module can be utilized, the voice signal of acquisition is carried out
Identification, to obtain recognition result corresponding to voice signal.
Step 202, when it is determined that recognition result is respectively less than threshold value with default N number of matching degree for waking up word model, by language
Sound signal is sent to server, so that speech signal is identified server, wherein N is the positive integer more than or equal to 1.
Wherein, default N number of wake-up word model, can be that smart machine is pre-configured in smart machine when dispatching from the factory,
It can also be that smart machine is respectively trained to obtain according to N number of wake-up word of acquisition, can also be that server gets intelligence and set
After standby N number of wake-up word, it is respectively trained what is obtained, is not restricted herein.
Threshold value can be arranged as required to.For example fixed value can be set in advance as, such as 80%, 90%.Or
Can be according to recognition result and default N number of match condition for waking up word model, the value of threshold value.Such as it is determined that knowing
When other result and the higher matching degree of default N number of wake-up word model, higher value can be set a threshold to；It is determined that knowing
When other result and the relatively low matching degree of default N number of wake-up word model, relatively low value, etc. can be set a threshold to.
It is understood that when default N number of wake-up word model is that server trains obtained wake-up word model, server
It can also will wake up word model and be sent to smart machine.That is, before step 202, can also include：
The wake-up word model that the reception server is sent.
Step 203, if getting the wake-up instruction of server return, smart machine is waken up.
Specifically, after smart machine determines the recognition result of voice signal, it may be determined that feature corresponding to recognition result to
Amount, and characteristic vector corresponding to recognition result is inputted in default N number of wake-up word model respectively and carries out verification marking, to determine
The matching degree of recognition result and N number of wake-up word model.If smart machine determines the matching degree of recognition result and N number of wake-up word model
Respectively less than threshold value, then it represents that according to default N number of wake-up word model in smart machine, it is determined that not including in the voice signal obtained
Word is waken up corresponding to smart machine.Because the resource that smart machine obtains is less, therefore voice signal can be sent to service
Device, so that voice signal is identified server.Each word mould is waken up by recognition result is corresponding with smart machine in server
Type is matched, and determines that recognition result any matching degree for waking up word model corresponding with smart machine is more than threshold value, and to intelligence
After energy equipment returns to wake-up instruction, smart machine can instruct according to the wake-up got, wake-up smart machine.
It is understood that if characteristic vector corresponding to recognition result is inputted default N number of wake-up by smart machine respectively
After carrying out verification marking in word model, determine that the matching degree of recognition result and a certain wake-up word model in N number of wake-up word model is big
In threshold value, then it represents that the voice signal that smart machine obtains includes waking up word corresponding to smart machine, so as to directly call out
Awake smart machine.
It should be noted that after smart machine gets voice signal, voice signal can also be sent to server, from
And smart machine voice signal can be identified with server simultaneously, and respectively call out recognition result is corresponding with smart machine
Word model of waking up is matched, with according to matching result, it is determined whether smart machine is waken up.Or smart machine obtains
To after voice signal, voice signal can not also be identified, but voice signal identification is carried out by server, and will identification
As a result each word model that wakes up corresponding with smart machine is matched, with according to matching result, it is determined whether smart machine is entered
Row wakes up.
The smart machine awakening method of the embodiment of the present invention, it is identified in the voice signal to acquisition, obtains identification knot
After fruit, however, it is determined that recognition result is respectively less than threshold value with default N number of matching degree for waking up word model, then is sent to voice signal
Server, so that voice signal is identified server, if getting the wake-up instruction of server return, wakes up intelligence and set
It is standby.Hereby it is achieved that wake-up control is carried out to smart machine by way of waking up offline, and using server to voice signal
It is identified and wake-up control is carried out to smart machine, reduce the consumption of hardware performance in wakeup process, and make it that user can
To wake up smart machine using customized wake-up word, wake-up word is enriched, improves the flexibility of wake-up, can preferably be expired
The individual demand of sufficient user, improve Consumer's Experience.
Fig. 3 is the signaling interaction diagram of the smart machine awakening method of one embodiment of the invention.
As shown in figure 3, the smart machine awakening method has smart machine A and server B to perform, interaction is as follows：
Step 301, the voice signal of acquisition is identified A, obtains recognition result.
Step 302, A is when it is determined that recognition result is respectively less than threshold value with default N number of matching degree for waking up word model, by language
Sound signal is sent to B.
Wherein, N is the positive integer more than or equal to 1.
Step 303, voice signal is identified B, determines recognition result corresponding to voice signal.
Step 304, B is when it is determined that recognition result any matching degree for waking up word model corresponding with A is more than threshold value, to A
Issue wake-up instruction.
Step 305, after A gets the wake-up instruction of B returns, then A is waken up.
Specifically, after the voice signal of acquisition is identified smart machine, however, it is determined that recognition result N number of is called out with default
The matching degree of awake word model is respectively less than threshold value, then voice signal can be sent into server.Server gets voice signal
Afterwards, voice signal can be identified, determines recognition result corresponding to voice signal, however, it is determined that recognition result and smart machine
Corresponding any matching degree for waking up word model is more than threshold value, then is sent to smart machine and wake up instruction.Smart machine is got
After waking up instruction, you can wake up smart machine.
It is understood that after the voice signal of acquisition is identified smart machine, however, it is determined that recognition result is with presetting
N number of wake-up word model in, some wake up word model matching degree be more than threshold value, then can directly wake up smart machine.
By above-mentioned interaction, the voice signal of acquisition can be identified offline for smart machine, and according to identification
As a result with it is default wake-up word model matching degree, it is determined whether wake up smart machine.If it can not be waken up by offline mode
Smart machine, then voice signal can be sent to server, voice signal is identified by server and to smart machine
Carry out wake-up control.
Voice signal is identified by using server and wake-up control is carried out to smart machine, reduces and woke up
The consumption of hardware performance in journey, and allow user to wake up smart machine using customized wake-up word, wake-up word is enriched,
The flexibility of wake-up is improved, the individual demand of user can be better met, improves Consumer's Experience.
Fig. 4 is the structural representation of the smart machine Rouser of one embodiment of the invention.
As shown in figure 4, the smart machine Rouser, including：
First acquisition module 41, for obtaining the voice signal of smart machine transmission；
First determining module 42, for voice signal to be identified, determine recognition result corresponding to voice signal；
First sending module 43, for it is determined that in recognition result it is corresponding with smart machine it is any wake up word model
When being more than threshold value with degree, wake-up instruction is issued to smart machine.
Specifically, the smart machine Rouser that the present embodiment provides, can perform the smart machine shown in Fig. 1 of the present invention
Awakening method.The device can be configured in the server being controlled to audio amplifier etc., to be waken up to smart machine.
In a kind of possible way of realization, the device, it can also include：
Generation module, the wake-up word for the smart machine to acquisition are trained, and generation is corresponding with smart machine to call out
Awake word model.
Second determining module, for being parsed to the voice signal that smart machine is sent, determine corresponding to smart machine
Wake up word；
Or for setting the text message inputted in the page in wake-up word corresponding with smart machine according to user, really
Determine to wake up word corresponding to smart machine.
It should be noted that the explanation of the foregoing smart machine awakening method embodiment to shown in Fig. 1 is also applied for
The smart machine Rouser of the embodiment, here is omitted.
The smart machine Rouser of the embodiment of the present invention, the voice signal that smart machine is sent is obtained first, it is then right
Voice signal is identified, and determines recognition result corresponding to voice signal, it is determined that corresponding with smart machine of recognition result
When the matching degree of one wake-up word model is more than threshold value, wake-up instruction is issued to smart machine.Thus, by using server to language
Sound signal is identified and carries out wake-up control to smart machine, reduces the consumption of hardware performance in wakeup process, and cause
User can utilize customized wake-up word to wake up smart machine, enrich wake-up word, improve the flexibility of wake-up, Ke Yigeng
The good individual demand for meeting user, improve Consumer's Experience.
Fig. 5 is the structural representation of the smart machine Rouser of another embodiment of the present invention.
As shown in figure 5, the smart machine Rouser, including：
Second acquisition module 51, for the voice signal of acquisition to be identified, obtain recognition result；
Second sending module 52, for it is determined that recognition result is respectively less than with default N number of matching degree for waking up word model
During threshold value, voice signal is sent to server, so that speech signal is identified server, wherein N is more than or equal to 1
Positive integer；
Wake module 53, for when getting the wake-up instruction of server return, waking up smart machine.
Specifically, the smart machine Rouser that the present embodiment provides, can perform the smart machine shown in Fig. 2 of the present invention
Awakening method.The device can be configured in the smart machines such as audio amplifier, mobile phone, computer, to be waken up to smart machine.
It should be noted that the explanation of the foregoing smart machine awakening method embodiment to shown in Fig. 2 is also applied for
The smart machine Rouser of the embodiment, here is omitted.
The smart machine Rouser of the embodiment of the present invention, it is identified in the voice signal to acquisition, obtains identification knot
After fruit, however, it is determined that recognition result is respectively less than threshold value with default N number of matching degree for waking up word model, then is sent to voice signal
Server, so that voice signal is identified server, if getting the wake-up instruction of server return, wakes up intelligence and set
It is standby.Hereby it is achieved that wake-up control is carried out to smart machine by way of waking up offline, and using server to voice signal
It is identified and wake-up control is carried out to smart machine, reduce the consumption of hardware performance in wakeup process, and make it that user can
To wake up smart machine using customized wake-up word, wake-up word is enriched, improves the flexibility of wake-up, can preferably be expired
The individual demand of sufficient user, improve Consumer's Experience.
The invention also provides a kind of server, including：
Memory, processor and storage on a memory and the computer program that can run on a processor, the processing
Device realizes the smart machine awakening method as described in first aspect embodiment when performing described program.
The invention also provides a kind of smart machine, including：
Memory, processor and storage on a memory and the computer program that can run on a processor, the processing
Device realizes the smart machine awakening method as described in second aspect embodiment when performing described program.
The invention also provides a kind of computer-readable recording medium, computer program is stored thereon with, when the program quilt
Realized during computing device such as the smart machine awakening method in aforementioned first aspect embodiment.
The invention also provides a kind of computer-readable recording medium, computer program is stored thereon with, when the program quilt
Realized during computing device such as the smart machine awakening method in foregoing second aspect embodiment.
The invention also provides a kind of computer program product, when the instruction in the computer program product is by processor
During execution, perform such as the smart machine awakening method in aforementioned first aspect embodiment.
The invention also provides a kind of computer program product, when the instruction in the computer program product is by processor
During execution, perform such as the smart machine awakening method in foregoing second aspect embodiment.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area
Art personnel can be tied the different embodiments or example and the feature of different embodiments or example described in this specification
Close and combine.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the invention, " multiple " are meant that at least two, such as two, three
It is individual etc., unless otherwise specifically defined.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize custom logic function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress used with reference to these instruction execution systems, device or equipment
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following：Electricity with one or more wiring
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium, which can even is that, to print the paper of described program thereon or other are suitable
Medium, because can then enter edlin, interpretation or if necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although have been shown and retouch above
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (14)
- A kind of 1. smart machine awakening method, it is characterised in that including：Obtain the voice signal that smart machine is sent；The voice signal is identified, determines recognition result corresponding to the voice signal；When it is determined that the recognition result any matching degree for waking up word model corresponding with the smart machine is more than threshold value, to The smart machine issues wake-up instruction.
- 2. the method as described in claim 1, it is characterised in that it is described determine in the recognition result with the smart machine pair The matching degree for any wake-up word model answered is more than before threshold value, in addition to：The wake-up word of the smart machine of acquisition is trained, generates wake-up word model corresponding with the smart machine.
- 3. method as claimed in claim 2, it is characterised in that the wake-up word of the smart machine of described pair of acquisition is instructed Before white silk, in addition to：The voice signal sent to the smart machine parses, and determines to wake up word corresponding to the smart machine；Or the text message inputted in the page is set according to user in wake-up word corresponding with the smart machine, determine institute State and word is waken up corresponding to smart machine.
- A kind of 4. smart machine awakening method, it is characterised in that including：The voice signal of acquisition is identified, obtains recognition result；When it is determined that the recognition result is respectively less than threshold value with default N number of matching degree for waking up word model, the voice is believed Number server is sent to, so that the speech signal is identified the server, wherein N is just whole more than or equal to 1 Number；If getting the wake-up instruction that the server returns, smart machine is waken up.
- 5. method as claimed in claim 4, it is characterised in that described to determine the recognition result and default wake-up word model Matching degree be less than threshold value before, in addition to：Receive the wake-up word model that the server is sent.
- A kind of 6. smart machine Rouser, it is characterised in that including：First acquisition module, for obtaining the voice signal of smart machine transmission；First determining module, for the voice signal to be identified, determine recognition result corresponding to the voice signal；First sending module, for it is determined that corresponding with the smart machine in the recognition result any wake up word model When matching degree is more than threshold value, wake-up instruction is issued to the smart machine.
- 7. device as claimed in claim 6, it is characterised in that also include：Generation module, the wake-up word for the smart machine to acquisition are trained, and generation is corresponding with the smart machine Wake-up word model.
- 8. device as claimed in claim 7, it is characterised in that also include：Second determining module, the voice signal for being sent to the smart machine parse, and determine the smart machine pair The wake-up word answered；Or for setting the text message inputted in the page in wake-up word corresponding with the smart machine according to user, really Word is waken up corresponding to the fixed smart machine.
- A kind of 9. smart machine Rouser, it is characterised in that including：Second acquisition module, for the voice signal of acquisition to be identified, obtain recognition result；Second sending module, for it is determined that the recognition result is respectively less than threshold with default N number of matching degree for waking up word model During value, the voice signal is sent to server, so that the speech signal is identified the server, wherein N is Positive integer more than or equal to 1；Wake module, for when getting the wake-up instruction that the server returns, waking up smart machine.
- 10. device as claimed in claim 9, it is characterised in that also include：Receiving module, the wake-up word model sent for receiving the server.
- 11. a kind of server, including：Memory, processor and the computer program that can be run on the memory and on the processor is stored in, it is special Sign is, the smart machine awakening method as described in any in claim 1-3 is realized during the computing device described program.
- 12. a kind of smart machine, including：Memory, processor and the computer program that can be run on the memory and on the processor is stored in, it is special Sign is, the smart machine awakening method as described in any in claim 4-5 is realized during the computing device described program.
- 13. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that described program is processed The smart machine awakening method as described in any in claim 1-3 is realized when device performs.
- 14. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that described program is processed The smart machine awakening method as described in any in claim 4-5 is realized when device performs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710786739.3A CN107704275B (en) | 2017-09-04 | 2017-09-04 | Intelligent device awakening method and device, server and intelligent device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710786739.3A CN107704275B (en) | 2017-09-04 | 2017-09-04 | Intelligent device awakening method and device, server and intelligent device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107704275A true CN107704275A (en) | 2018-02-16 |
| CN107704275B CN107704275B (en) | 2021-07-23 |
Family
ID=61171966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710786739.3A Active CN107704275B (en) | 2017-09-04 | 2017-09-04 | Intelligent device awakening method and device, server and intelligent device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107704275B (en) |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108494956A (en) * | 2018-03-13 | 2018-09-04 | 广州势必可赢网络科技有限公司 | Intelligent wearable device reminding method and intelligent wearable device |
| CN108538298A (en) * | 2018-04-04 | 2018-09-14 | 科大讯飞股份有限公司 | voice awakening method and device |
| CN108536099A (en) * | 2018-02-26 | 2018-09-14 | 维沃移动通信有限公司 | A kind of information processing method, device and mobile terminal |
| CN108597507A (en) * | 2018-03-14 | 2018-09-28 | 百度在线网络技术（北京）有限公司 | Far field phonetic function implementation method, equipment, system and storage medium |
| CN108646902A (en) * | 2018-05-15 | 2018-10-12 | 广州势必可赢网络科技有限公司 | Control method and device for standby enabling signal |
| CN108665900A (en) * | 2018-04-23 | 2018-10-16 | 百度在线网络技术（北京）有限公司 | High in the clouds awakening method and system, terminal and computer readable storage medium |
| CN108665895A (en) * | 2018-05-03 | 2018-10-16 | 百度在线网络技术（北京）有限公司 | Methods, devices and systems for handling information |
| CN108735210A (en) * | 2018-05-08 | 2018-11-02 | 宇龙计算机通信科技(深圳)有限公司 | A kind of sound control method and terminal |
| CN108737933A (en) * | 2018-05-30 | 2018-11-02 | 上海与德科技有限公司 | A kind of dialogue method, device and electronic equipment based on intelligent sound box |
| CN108962259A (en) * | 2018-07-25 | 2018-12-07 | 联想(北京)有限公司 | Processing method and the first electronic equipment |
| CN109005482A (en) * | 2018-08-14 | 2018-12-14 | 汪俊 | A kind of method and device of the speaker of sound control working condition |
| CN109166571A (en) * | 2018-08-06 | 2019-01-08 | 广东美的厨房电器制造有限公司 | Wake-up word training method, device and the household appliance of household appliance |
| CN109346070A (en) * | 2018-09-17 | 2019-02-15 | 佛吉亚好帮手电子科技有限公司 | A kind of voice based on vehicle device Android system exempts from awakening method |
| CN109471664A (en) * | 2018-10-30 | 2019-03-15 | 南昌努比亚技术有限公司 | Intelligent assistant's management method, terminal and computer readable storage medium |
| CN109686370A (en) * | 2018-12-24 | 2019-04-26 | 苏州思必驰信息科技有限公司 | The method and device of fighting landlord game is carried out based on voice control |
| CN109871238A (en) * | 2019-01-02 | 2019-06-11 | 百度在线网络技术（北京）有限公司 | Voice interactive method, device and storage medium |
| CN109887505A (en) * | 2019-03-11 | 2019-06-14 | 百度在线网络技术（北京）有限公司 | Method and apparatus for wake-up device |
| CN110049395A (en) * | 2019-04-25 | 2019-07-23 | 维沃移动通信有限公司 | Headset control method and ear speaker device |
| CN110119083A (en) * | 2019-04-17 | 2019-08-13 | 惠州市惠泽电器有限公司 | The awakening method of smartwatch |
| CN110211580A (en) * | 2019-05-15 | 2019-09-06 | 海尔优家智能科技（北京）有限公司 | More smart machine answer methods, device, system and storage medium |
| CN110364147A (en) * | 2019-08-29 | 2019-10-22 | 厦门市思芯微科技有限公司 | A kind of wake-up training word acquisition system and method |
| CN110797015A (en) * | 2018-12-17 | 2020-02-14 | 北京嘀嘀无限科技发展有限公司 | Voice wake-up method and device, electronic equipment and storage medium |
| WO2020061787A1 (en) * | 2018-09-26 | 2020-04-02 | 深圳市博电电子技术有限公司 | Intelligent toilet control method and intelligent toilet |
| CN111009246A (en) * | 2020-03-10 | 2020-04-14 | 展讯通信（上海）有限公司 | Intelligent sound box and awakening method thereof, gateway, server and readable storage medium |
| CN111105789A (en) * | 2018-10-25 | 2020-05-05 | 珠海格力电器股份有限公司 | Awakening word obtaining method and device |
| CN111124507A (en) * | 2019-11-18 | 2020-05-08 | 珠海格力电器股份有限公司 | Voice equipment and awakening method, awakening device and storage medium thereof |
| CN111261151A (en) * | 2018-12-03 | 2020-06-09 | 中移（杭州）信息技术有限公司 | Voice processing method and device, electronic equipment and storage medium |
| CN111292726A (en) * | 2020-03-10 | 2020-06-16 | 科通工业技术(深圳)有限公司 | Method and system for changing awakening words offline |
| CN111475206A (en) * | 2019-01-04 | 2020-07-31 | 优奈柯恩(北京)科技有限公司 | Method and apparatus for waking up wearable device |
| CN111508472A (en) * | 2019-01-11 | 2020-08-07 | 华为技术有限公司 | Language switching method and device and storage medium |
| CN112133301A (en) * | 2020-08-21 | 2020-12-25 | 深圳数联天下智能科技有限公司 | Voice recognition method, control device, voice recognition circuit and household equipment |
| US10964317B2 (en) | 2017-07-05 | 2021-03-30 | Baidu Online Network Technology (Beijing) Co., Ltd. | Voice wakeup method, apparatus and system, cloud server and readable medium |
| CN112634897A (en) * | 2020-12-31 | 2021-04-09 | 青岛海尔科技有限公司 | Equipment awakening method and device, storage medium and electronic device |
| CN112820283A (en) * | 2019-11-18 | 2021-05-18 | 阿里巴巴集团控股有限公司 | Voice processing method, device and system |
| CN113012697A (en) * | 2021-03-05 | 2021-06-22 | 北京嘀嘀无限科技发展有限公司 | Information interaction method and device and electronic equipment |
| CN113223529A (en) * | 2021-05-14 | 2021-08-06 | 成都启英泰伦科技有限公司 | Multi-awakening-word anti-error identification method based on multiple single-awakening-word models |
| EP3923275A1 (en) * | 2020-06-12 | 2021-12-15 | Beijing Xiaomi Pinecone Electronics Co., Ltd. | Device wakeup method and apparatus, electronic device, and storage medium |
| CN116030817A (en) * | 2022-07-18 | 2023-04-28 | 荣耀终端有限公司 | Voice wakeup method, equipment and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102693725A (en) * | 2011-03-25 | 2012-09-26 | 通用汽车有限责任公司 | Speech recognition dependent on text message content |
| CN103595869A (en) * | 2013-11-15 | 2014-02-19 | 华为终端有限公司 | Terminal voice control method and device and terminal |
| CN104036170A (en) * | 2014-06-11 | 2014-09-10 | 叶晨光 | Smart glasses and a control method and device of same |
| CN104282307A (en) * | 2014-09-05 | 2015-01-14 | 中兴通讯股份有限公司 | Method, device and terminal for awakening voice control system |
| CN104769668A (en) * | 2012-10-04 | 2015-07-08 | 纽昂斯通讯公司 | Improved hybrid controller for ASR |
| CN105632486A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | Voice wake-up method and device of intelligent hardware |
| CN105654943A (en) * | 2015-10-26 | 2016-06-08 | 乐视致新电子科技（天津）有限公司 | Voice wakeup method, apparatus and system thereof |
| CN105654949A (en) * | 2016-01-07 | 2016-06-08 | 北京云知声信息技术有限公司 | Voice wake-up method and device |
| CN105702253A (en) * | 2016-01-07 | 2016-06-22 | 北京云知声信息技术有限公司 | Voice awakening method and device |
| CN106098059A (en) * | 2016-06-23 | 2016-11-09 | 上海交通大学 | customizable voice awakening method and system |
| CN106233804A (en) * | 2014-04-24 | 2016-12-14 | Lg电子株式会社 | The method and apparatus determining maximum upper limit link transmission power in a wireless communication system |
| CN106653031A (en) * | 2016-10-17 | 2017-05-10 | 海信集团有限公司 | Voice wake-up method and voice interaction device |
-
2017
- 2017-09-04 CN CN201710786739.3A patent/CN107704275B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102693725A (en) * | 2011-03-25 | 2012-09-26 | 通用汽车有限责任公司 | Speech recognition dependent on text message content |
| CN104769668A (en) * | 2012-10-04 | 2015-07-08 | 纽昂斯通讯公司 | Improved hybrid controller for ASR |
| CN103595869A (en) * | 2013-11-15 | 2014-02-19 | 华为终端有限公司 | Terminal voice control method and device and terminal |
| US20150141079A1 (en) * | 2013-11-15 | 2015-05-21 | Huawei Device Co., Ltd. | Terminal voice control method and apparatus, and terminal |
| CN106233804A (en) * | 2014-04-24 | 2016-12-14 | Lg电子株式会社 | The method and apparatus determining maximum upper limit link transmission power in a wireless communication system |
| CN104036170A (en) * | 2014-06-11 | 2014-09-10 | 叶晨光 | Smart glasses and a control method and device of same |
| CN104282307A (en) * | 2014-09-05 | 2015-01-14 | 中兴通讯股份有限公司 | Method, device and terminal for awakening voice control system |
| CN105654943A (en) * | 2015-10-26 | 2016-06-08 | 乐视致新电子科技（天津）有限公司 | Voice wakeup method, apparatus and system thereof |
| CN105632486A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | Voice wake-up method and device of intelligent hardware |
| CN105702253A (en) * | 2016-01-07 | 2016-06-22 | 北京云知声信息技术有限公司 | Voice awakening method and device |
| CN105654949A (en) * | 2016-01-07 | 2016-06-08 | 北京云知声信息技术有限公司 | Voice wake-up method and device |
| CN106098059A (en) * | 2016-06-23 | 2016-11-09 | 上海交通大学 | customizable voice awakening method and system |
| CN106653031A (en) * | 2016-10-17 | 2017-05-10 | 海信集团有限公司 | Voice wake-up method and voice interaction device |
Cited By (49)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10964317B2 (en) | 2017-07-05 | 2021-03-30 | Baidu Online Network Technology (Beijing) Co., Ltd. | Voice wakeup method, apparatus and system, cloud server and readable medium |
| CN108536099A (en) * | 2018-02-26 | 2018-09-14 | 维沃移动通信有限公司 | A kind of information processing method, device and mobile terminal |
| CN108494956A (en) * | 2018-03-13 | 2018-09-04 | 广州势必可赢网络科技有限公司 | Intelligent wearable device reminding method and intelligent wearable device |
| CN108597507A (en) * | 2018-03-14 | 2018-09-28 | 百度在线网络技术（北京）有限公司 | Far field phonetic function implementation method, equipment, system and storage medium |
| US11295760B2 (en) | 2018-03-14 | 2022-04-05 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, apparatus, system and storage medium for implementing a far-field speech function |
| CN108538298A (en) * | 2018-04-04 | 2018-09-14 | 科大讯飞股份有限公司 | voice awakening method and device |
| CN108665900B (en) * | 2018-04-23 | 2020-03-03 | 百度在线网络技术（北京）有限公司 | Cloud wake-up method and system, terminal and computer readable storage medium |
| CN108665900A (en) * | 2018-04-23 | 2018-10-16 | 百度在线网络技术（北京）有限公司 | High in the clouds awakening method and system, terminal and computer readable storage medium |
| US11574632B2 (en) | 2018-04-23 | 2023-02-07 | Baidu Online Network Technology (Beijing) Co., Ltd. | In-cloud wake-up method and system, terminal and computer-readable storage medium |
| CN108665895A (en) * | 2018-05-03 | 2018-10-16 | 百度在线网络技术（北京）有限公司 | Methods, devices and systems for handling information |
| CN108665895B (en) * | 2018-05-03 | 2021-05-25 | 百度在线网络技术（北京）有限公司 | Method, device and system for processing information |
| CN108735210A (en) * | 2018-05-08 | 2018-11-02 | 宇龙计算机通信科技(深圳)有限公司 | A kind of sound control method and terminal |
| CN108646902A (en) * | 2018-05-15 | 2018-10-12 | 广州势必可赢网络科技有限公司 | Control method and device for standby enabling signal |
| CN108737933A (en) * | 2018-05-30 | 2018-11-02 | 上海与德科技有限公司 | A kind of dialogue method, device and electronic equipment based on intelligent sound box |
| CN108962259B (en) * | 2018-07-25 | 2021-06-15 | 联想(北京)有限公司 | Processing method and first electronic device |
| CN108962259A (en) * | 2018-07-25 | 2018-12-07 | 联想(北京)有限公司 | Processing method and the first electronic equipment |
| CN109166571A (en) * | 2018-08-06 | 2019-01-08 | 广东美的厨房电器制造有限公司 | Wake-up word training method, device and the household appliance of household appliance |
| CN109005482A (en) * | 2018-08-14 | 2018-12-14 | 汪俊 | A kind of method and device of the speaker of sound control working condition |
| CN109346070A (en) * | 2018-09-17 | 2019-02-15 | 佛吉亚好帮手电子科技有限公司 | A kind of voice based on vehicle device Android system exempts from awakening method |
| WO2020061787A1 (en) * | 2018-09-26 | 2020-04-02 | 深圳市博电电子技术有限公司 | Intelligent toilet control method and intelligent toilet |
| CN111105789A (en) * | 2018-10-25 | 2020-05-05 | 珠海格力电器股份有限公司 | Awakening word obtaining method and device |
| CN109471664A (en) * | 2018-10-30 | 2019-03-15 | 南昌努比亚技术有限公司 | Intelligent assistant's management method, terminal and computer readable storage medium |
| CN111261151A (en) * | 2018-12-03 | 2020-06-09 | 中移（杭州）信息技术有限公司 | Voice processing method and device, electronic equipment and storage medium |
| CN110797015A (en) * | 2018-12-17 | 2020-02-14 | 北京嘀嘀无限科技发展有限公司 | Voice wake-up method and device, electronic equipment and storage medium |
| CN109686370A (en) * | 2018-12-24 | 2019-04-26 | 苏州思必驰信息科技有限公司 | The method and device of fighting landlord game is carried out based on voice control |
| CN109871238A (en) * | 2019-01-02 | 2019-06-11 | 百度在线网络技术（北京）有限公司 | Voice interactive method, device and storage medium |
| CN111475206A (en) * | 2019-01-04 | 2020-07-31 | 优奈柯恩(北京)科技有限公司 | Method and apparatus for waking up wearable device |
| CN111508472B (en) * | 2019-01-11 | 2023-03-03 | 华为技术有限公司 | Language switching method, device and storage medium |
| CN111508472A (en) * | 2019-01-11 | 2020-08-07 | 华为技术有限公司 | Language switching method and device and storage medium |
| CN109887505A (en) * | 2019-03-11 | 2019-06-14 | 百度在线网络技术（北京）有限公司 | Method and apparatus for wake-up device |
| CN110119083A (en) * | 2019-04-17 | 2019-08-13 | 惠州市惠泽电器有限公司 | The awakening method of smartwatch |
| CN110049395B (en) * | 2019-04-25 | 2020-06-05 | 维沃移动通信有限公司 | Earphone control method and earphone device |
| CN110049395A (en) * | 2019-04-25 | 2019-07-23 | 维沃移动通信有限公司 | Headset control method and ear speaker device |
| CN110211580A (en) * | 2019-05-15 | 2019-09-06 | 海尔优家智能科技（北京）有限公司 | More smart machine answer methods, device, system and storage medium |
| CN110364147B (en) * | 2019-08-29 | 2021-08-20 | 厦门市思芯微科技有限公司 | Awakening training word acquisition system and method |
| CN110364147A (en) * | 2019-08-29 | 2019-10-22 | 厦门市思芯微科技有限公司 | A kind of wake-up training word acquisition system and method |
| CN111124507A (en) * | 2019-11-18 | 2020-05-08 | 珠海格力电器股份有限公司 | Voice equipment and awakening method, awakening device and storage medium thereof |
| CN112820283A (en) * | 2019-11-18 | 2021-05-18 | 阿里巴巴集团控股有限公司 | Voice processing method, device and system |
| CN111292726A (en) * | 2020-03-10 | 2020-06-16 | 科通工业技术(深圳)有限公司 | Method and system for changing awakening words offline |
| CN111009246A (en) * | 2020-03-10 | 2020-04-14 | 展讯通信（上海）有限公司 | Intelligent sound box and awakening method thereof, gateway, server and readable storage medium |
| EP3923275A1 (en) * | 2020-06-12 | 2021-12-15 | Beijing Xiaomi Pinecone Electronics Co., Ltd. | Device wakeup method and apparatus, electronic device, and storage medium |
| US11665644B2 (en) | 2020-06-12 | 2023-05-30 | Beijing Xiaomi Pinecone Electronics Co., Ltd. | Device wakeup method and apparatus, electronic device, and storage medium |
| CN112133301A (en) * | 2020-08-21 | 2020-12-25 | 深圳数联天下智能科技有限公司 | Voice recognition method, control device, voice recognition circuit and household equipment |
| CN112634897B (en) * | 2020-12-31 | 2022-10-28 | 青岛海尔科技有限公司 | Equipment awakening method and device, storage medium and electronic device |
| CN112634897A (en) * | 2020-12-31 | 2021-04-09 | 青岛海尔科技有限公司 | Equipment awakening method and device, storage medium and electronic device |
| CN113012697A (en) * | 2021-03-05 | 2021-06-22 | 北京嘀嘀无限科技发展有限公司 | Information interaction method and device and electronic equipment |
| CN113223529A (en) * | 2021-05-14 | 2021-08-06 | 成都启英泰伦科技有限公司 | Multi-awakening-word anti-error identification method based on multiple single-awakening-word models |
| CN116030817A (en) * | 2022-07-18 | 2023-04-28 | 荣耀终端有限公司 | Voice wakeup method, equipment and storage medium |
| CN116030817B (en) * | 2022-07-18 | 2023-09-19 | 荣耀终端有限公司 | Voice wakeup method, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107704275B (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107704275A (en) | Smart machine awakening method, device, server and smart machine | |
| CN107564518A (en) | Smart machine control method, device and computer equipment | |
| CN106611597B (en) | Voice awakening method and device based on artificial intelligence | |
| CN106653016B (en) | Intelligent interaction method and device | |
| CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
| CN105512105B (en) | Semantic analysis method and device | |
| CN107564531A (en) | Minutes method, apparatus and computer equipment based on vocal print feature | |
| CN107886948A (en) | Voice interactive method and device, terminal, server and readable storage medium storing program for executing | |
| CN109410927A (en) | Offline order word parses the audio recognition method combined, device and system with cloud | |
| CN106502649A (en) | A kind of robot service awakening method and device | |
| CN107610702A (en) | Terminal device standby wakeup method, apparatus and computer equipment | |
| JP7158217B2 (en) | Speech recognition method, device and server | |
| CN106847283A (en) | Intelligent electrical appliance control and device | |
| CN109346069A (en) | A kind of interactive system and device based on artificial intelligence | |
| CN111090728A (en) | Conversation state tracking method and device and computing equipment | |
| CN109065035A (en) | information interaction method and device | |
| CN109036393A (en) | Wake-up word training method, device and the household appliance of household appliance | |
| CN109637551A (en) | Phonetics transfer method, device, equipment and storage medium | |
| CN107545029A (en) | Voice feedback method, equipment and the computer-readable recording medium of smart machine | |
| CN109979443A (en) | Authority management control method and device for robot | |
| CN105244042B (en) | A kind of speech emotional interactive device and method based on finite-state automata | |
| CN109979430A (en) | Robot story telling method and device, robot and storage medium | |
| CN112989800A (en) | Multi-intention identification method and device based on Bert sections and readable storage medium | |
| WO2016203805A1 (en) | Information processing device, information processing system, information processing method, and program | |
| CN109166571A (en) | Wake-up word training method, device and the household appliance of household appliance |
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 |