CN102842306B - Sound control method and device, voice response method and device - Google Patents
Sound control method and device, voice response method and device Download PDFInfo
- Publication number
- CN102842306B CN102842306B CN201210319278.6A CN201210319278A CN102842306B CN 102842306 B CN102842306 B CN 102842306B CN 201210319278 A CN201210319278 A CN 201210319278A CN 102842306 B CN102842306 B CN 102842306B
- Authority
- CN
- China
- Prior art keywords
- voice
- user
- control
- operational order
- recording
- 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.)
- Active
Links
Abstract
The present invention discloses a kind of sound control method, comprising: record the control voice of user's input, extract the also voice feature data of record controls voice; Record the operational order of the corresponding control of user voice or reply voice; Voice feature data be set with operational order or reply the associated of voice, for the voice operating control instruction of User Defined electronic equipment. Voice response method and device that the present invention also discloses a kind of phonetic controller and responds controlling voice. The present invention is by recording the control voice of user's input, extract and the voice feature data of record controls voice, the method recording the operational order of these control voice or reply voice, voice feature data and operational order be set or reply the associated of voice and these control voice are responded, there is the beneficial effect that user can customize speech recognition controlled and can exchange with TV, make TV have the function of study, improve TV performance, promoted user's experience.<!--1-->
Description
Technical field
The present invention relates to intelligent television speech recognition controlled technical field, relate in particular to a kind of voice controlMethod, device and television set.
Background technology
The TV(Television of prior art, television set) only have indivedual application programs passable on platformUse voice control function, and voice control must just can play work under some special scenesWith, such as entering certain application interface, phonetic entry just has effect. Prior artThe thing that voice control can complete is too simple, single, and can only complete while dispatching from the factory and establish in advanceIndivedual operations of reserving, such as switching channels simply, open network address, weather forecast etc., user can not add new voice control function, can not delete user self and think it unnecessary to wantVoice control function; If software is not set up voice sign and corresponding operating in advance while dispatching from the factoryCorresponding relation, cannot realize voice control; User's spoken language varies, prior artScheme is often because fixing speech recognition mode causes the heavy voice of None-identified accent. At presentThe function application of TV system is many, if only have indivedual application just can make term in TV systemSound control system, voice control function will be very restricted so, make the correlation function of TV systemCan not be fully utilized, cause the waste of resource.
Summary of the invention
Main purpose of the present invention is to provide a kind of sound control method, device and television set, is intended to buildVertical user-defined voice identification control function, makes TV have the function of study.
The invention discloses a kind of sound control method, comprise the following steps:
Record the control voice of user's input, extract the also voice feature data of record controls voice;
Record the operational order of the corresponding described control voice of user or reply voice;
Described voice feature data be set with described operational order or reply the associated of voice, for user certainlyThe voice operating control instruction of definition electronic equipment.
Preferably, described in, record the control voice that user inputs, the voice of extraction record controls voiceSpecialThe step of levying data specifically comprises:
Described control voice are uploaded to cloud server and identify, extract described voice feature data；
Receive and be converted to readable phonetic characters according to described voice feature data;
Show described phonetic characters, confirm that user described phonetic characters records described voice word when errorlessSymbol or source characteristic.
Preferably, described in, record the operational order of the corresponding described control voice of user or reply the step of voiceSuddenly specifically comprise:
When being judged as while recording described operational order,
Display application program listing, the application program of selecting according to user, follows the tracks of and records remote keyingThe operation corresponding teleswitch value of overall process and application index;
When being judged as while replying voice described in recording,
When recorded speech answer-mode, obtain the speech data of replying of user's input, and generation is repliedVoice data file.
Preferably, the described pass that described voice feature data and described operational order is set or replys voiceThe step of connection specifically comprises:
According to the described operational order of recording, set up described application index, described teleswitch value withThe corresponding relation of described phonetic characters is also stored in database;
Or
Described in recording, reply voice, set up described phonetic characters or characteristic and described answeringAnswer the corresponding relation of voice, and be stored in database.
Preferably, described database comprises that operational order replys sound bank, and described operational order is replied languageSound storehouse comprises multiple voice documents, the associated corresponding described voice operating control of described voice documentInstruction and application index.
The present invention also discloses a kind of phonetic controller, comprising:
First records module, for recording the control voice of user's input, extracts and record controls voiceVoice feature data;
Second records module, for recording the operational order of the corresponding described control voice of user or replying languageSound;
Association arranges module, for described voice feature data and described operational order being set or replying languageThe association of sound, for the voice operating control instruction of User Defined electronic equipment.
Preferably, described first record module and specifically comprise:
Characteristic extraction unit, identifies for described control voice are uploaded to cloud server, extract described voice feature data;
Phonetic characters acquiring unit, is converted to readable for receiving according to described voice feature dataPhonetic characters;
Record cell, for showing described phonetic characters, in the time that user confirms that described phonetic characters is errorlessRecord described phonetic characters or source characteristic.
Preferably, described second record module and specifically comprise:
Operational order recording elements, for being judged as while recording described operational order,
Display application program listing, the application program of selecting according to user, follows the tracks of and records remote keyingThe operation corresponding teleswitch value of overall process and application index;
Reply voice recording unit, for being judged as while replying voice described in recording,
When recorded speech answer-mode, obtain the speech data of replying of user's input, and generation is repliedVoice data file.
Preferably, described association arranges module and specifically comprises:
Operational order setting unit, for according to the described operational order of recording, sets up described application journeyThe corresponding relation of sequence index, described teleswitch value and described phonetic characters is also stored in database；
Reply voice setting unit, for reply voice described in recording, set up described voice wordSymbol or characteristic and described in reply the corresponding relation of voice, and be stored in database.
Preferably, described database comprises that operational order replys sound bank, and described operational order is replied languageSound storehouse comprises multiple voice documents, the associated corresponding described voice operating control of described voice documentInstruction and application index.
The present invention also discloses a kind of voice response method, and described response method comprises described voice controlThe method that control voice in method processed respond, described response method comprises the following steps:
Obtain the control voice of user's input, and extract and control voice feature data;
Retrieval phonetic characters database, judges in described database, whether to find described voice spyLevy response mode corresponding to data;
If so, reply according to described response mode;
If not, switch to described in study and work pattern carries out corresponding operating or prompting user re-entersLanguageSound instruction.
Preferably, described step of replying according to described response mode specifically comprises:
Judge the corresponding action type of described response mode;
In the time that described response mode is operation acknowledge, carry out application program that described operation acknowledge specifies and/ or corresponding control instruction;
In the time that described response mode is voice answer-back, play corresponding voice document.
The present invention also discloses a kind of voice response device, and described responding device comprises described voice controlDevice processed is controlled, and described responding device comprises:
Control voice acquisition module, for obtaining the control voice of user's input, and extract and control voiceCharacteristic;
Response mode acquisition module, for retrieving phonetic characters database, judges in described databaseWhether can find the response mode that described voice feature data is corresponding;
The first responder module, for finding described voice feature data correspondence at described databaseResponse mode time, reply according to described response mode;
The second responder module, for not finding described voice feature data correspondence at described databaseResponse mode time, switch to study and work pattern carry out corresponding operating or prompting user again defeatedEnter described phonetic order.
Preferably, described the first responder module specifically comprises:
Acknowledgement type acquiring unit, for judging the corresponding action type of described response mode;
Operation acknowledge unit, in the time that described response mode is operation acknowledge, carrying out described operation shouldAnswer application program and/or the corresponding control instruction of specifying;
Voice responding unit, in the time that described response mode is voice answer-back, plays corresponding voiceFile.
The present invention, by recording the control voice of user's input, extracts the also voice spy of record controls voiceLevy data, record the operational order of these control voice or reply voice, voice feature data is setWith operational order or the method for replying the associated of voice and these control voice being responded, haveThe beneficial effect that user can customize speech recognition controlled and can exchange with TV, makes TVHave the function of study, improved TV performance, promoted user's experience.
Brief description of the drawings
Fig. 1 is sound control method one embodiment schematic flow sheet of the present invention;
Fig. 2 is speech recognition one example structure block diagram in Fig. 1;
Fig. 3 is the control voice of recording user's input in Fig. 1, extracts the also voice spy of record controls voiceLevy data one embodiment schematic flow sheet;
Fig. 4 records the operational order of the corresponding described control voice of user or replys voice one enforcement in Fig. 1Example schematic flow sheet;
Fig. 5 is phonetic controller one example structure schematic diagram of the present invention;
Fig. 6 is that in Fig. 5, association arranges module one example structure schematic diagram;
Fig. 7 first records module one example structure schematic diagram in Fig. 5;
Fig. 8 second records module one example structure schematic diagram in Fig. 5;
Fig. 9 is voice response method one embodiment schematic flow sheet of the present invention;
Figure 10 replys an embodiment schematic flow sheet according to response mode in Fig. 9;
Figure 11 is voice response device one example structure schematic diagram of the present invention;
Figure 12 is the first responder module one example structure schematic diagram in Figure 11.
Realization, functional characteristics and the advantage of the object of the invention, in connection with embodiment, are done into one with reference to accompanying drawingStep explanation.
Detailed description of the invention
Further illustrate technical scheme of the present invention below in conjunction with Figure of description and specific embodiment. ShouldWork as understanding, specific embodiment described herein is only in order to explain the present invention, and is not used in limitDetermine the present invention.
With reference to Fig. 1, Fig. 1 is sound control method one embodiment schematic flow sheet of the present invention; As shown in Figure 1, sound control method of the present invention comprises the following steps:
Step S01, record the control voice of user input, extract and the phonetic feature of record controls voiceData;
In a preferred embodiment, in TV main program, be provided with speech controling switch, default situationsLower voice control is inoperative, and after TV main program is opened this voice control function, TV just starts languageSound control system, phonetic function enters dialogue mode of operation after starting. Under dialogue mode, record useThe control voice that family is inputted by voice-input devices such as microphone, voice remote controller or mobile phones,Extract simultaneously and record this controlThe voice feature data that voice are corresponding. In a preferred embodiment, TV is by the control of user's inputVoice processed are uploaded to cloud server and identify, and extract voice feature data; With reference to Fig. 2, figureSpeech recognition one example structure block diagram in the 2nd, Fig. 1; As shown in Figure 2, TV is by the language of user's inputSound is uploaded to high in the clouds speech recognition server after recording, this high in the clouds speech recognition server pairVoice are converted to the phonetic characters that can be identified by TV after identifying, TV is logical by this phonetic charactersCross OSD(OnScreenDisplay, screen menu type shows) or other display modesShow and check confirmation for user, after user's confirmation, TV record this phonetic characters orSource characteristic; In the present embodiment, described characteristic comprises described phonetic characters.
Step S02, record the operational order of the corresponding described control voice of user or reply voice;
Extract after the corresponding voice feature data of control voice of also recording user input, TV also needs recordMake the corresponding operational order of these control voice or reply voice; Particularly, preferred real oneExecute in example, first television set judges the voice control type that user selects; If the control that user selectsType processed is when " speaking ", and the voice that television set storage user inputs, set up the language of these voiceCorresponding relation between sound path and corresponding phonetic characters is also stored to described database. If userWhen the control type of selecting is " working ", the program listing of television set display application, according to userThe application program of selecting, follows the tracks of and records the corresponding teleswitch value of remote keying operation overall processAnd application index; And set up between application index, teleswitch value and phonetic charactersCorresponding relation is also stored to described database.
Step S03, described voice feature data be set with described operational order or reply the associated of voice,For the voice operating control instruction of User Defined electronic equipment.
In order to realize the voice operating control instruction of User Defined electronic equipment, phonetic feature number is setAccording to being specially with the associated of operational order: according to the operational order of recording, set up application program ropeDraw, the corresponding relation of teleswitch value and phonetic characters being stored in database; Voice spy is setLevy data and reply the associated of voice and be specially: according to the voice of replying of recording, set up voice wordSymbol or characteristic and reply the corresponding relation of voice, and be stored in database.
In a preferred embodiment, database storage is also retrieved the phonetic characters that high in the clouds is returned, and comparesMemory scan speech audio file is more simple, accurate. Certainly, described database is stored in cloudEnd server, data volume is little, and therefore the expense of local hardware is also little, can more accurately retrieve audio frequencyFile or phonetic characters, be not restricted here.
The specific implementation process of sound control method of the present invention is described with specific embodiment below.
Such as realizing the voice control of " opening USB flash disk movie ". First user enters mode of learning，The instruction that study receives. TV can be pointed out user input voice instruction, and user passes through microphoneThe phonetic entry that to " turn on USB flash disk movie " is to TV, and TV is processed and is converted to by high in the cloudsAlphabetic character, and taking the mode of OSD prompting feed back to user " your input whether as ' opening UDish movie '? " User selects "Yes", then just enters the second step of study, OSD further points out " study is spoken or handled affairs? " user selects " working ", has OSD to continueContinuous prompting user, " application that please select you to open ". Then user selects " USB application ", after program enters USB application, ensuing all remote controller keys will be by record one by one,User just can simulate and enter after USB application, how to select step by step to play with remote controllerFilm and realize play. User just completes and oneself wants, after the arranging of function, to select to exitThe button of habit pattern. Preserve the content of study according to prompting, as " opening USB flash disk movie "Alphabetic character and a series of remote keyings such as index and up/down/left/right of USB application programKey assignments. In addition can also go to speak by " religion " TV by said method, such as user enters,Enter the voice of one section of typing after mode of learning oneself, and the voice of typing are associated with phonetic charactersBe stored in database, TV speaking as just can " repeating the words of others like a parrot ", also can intelligenceCan reply.
The present embodiment, by recording the control voice of user's input, extracts the also voice of record controls voiceCharacteristic, record the operational order of these control voice or reply voice, phonetic feature number is setAccording to operational order or the method for replying the associated of voice and these control voice being responded, toolThe beneficial effect that has user to can customize speech recognition controlled and can exchange with TV, makes electricityDepending on having the function of study, improve TV performance, promote user's experience.
With reference to Fig. 3, Fig. 3 is the control voice of recording user's input in Fig. 1, extracts and record controls voiceVoice feature data one embodiment schematic flow sheet; The present embodiment is only done further step S01Describe, other related steps of sound control method of the present invention please refer to the tool of related embodimentVolume description, does not repeat them here.
As shown in Figure 3, in sound control method of the present invention, step S01, record the control of user inputVoice, extract the also step of the voice feature data of record controls voice and specifically comprise:
Step S11, described control voice are uploaded to cloud server identify, extract described voiceCharacteristic;
Step S12, reception are converted to displayable alphabetic character according to described voice feature data,Phonetic characters;
Step S13, show described phonetic characters, confirm that user described phonetic characters records institute when errorlessStatePhonetic characters or source characteristic.
TV is uploaded to cloud server by the control voice of user's input and identifies, and extracts phonetic featureData; TV is uploaded to high in the clouds speech recognition server after the voice of user's input are recorded, this high in the clouds speech recognition server is converted to the language that can be identified by TV after voice are identifiedSound character, TV by this phonetic characters by OSD or by other display modes show forConfirmation is checked at family, and after user's confirmation, TV records this phonetic characters or source characteristic;In the present embodiment, described characteristic comprises described phonetic characters. Above-mentioned specific implementation process pleaseWith reference to the specific descriptions of embodiment described in Fig. 2, do not repeat them here.
The present embodiment, by recording the control voice of user's input, extracts the also voice of record controls voiceThe method of characteristic, has user more accurately and can customize the beneficial effect that has of speech recognition controlledReally.
With reference to Fig. 4, Fig. 4 records the operational order of the corresponding control of user voice or replys voice one in Fig. 1Embodiment schematic flow sheet; The present embodiment is only further described step S02, voice of the present inventionOther related steps of control method please refer to the specific descriptions of related embodiment, at this no longerRepeat.
As shown in Figure 4, in sound control method of the present invention, step S02, record the corresponding described control of userThe operational order of voice processed or the step of replying voice specifically comprise:
Step S21, judgement institute's operational order of recording or reply voice; If operational order, holdsRow step S22; If reply voice, perform step S23;
Step S22, display application program listing, the application program of selecting according to user, follows the tracks of and recordThe remote keying operation corresponding teleswitch value of overall process and application index;
In the time being judged as recording operation instruction, the program listing of TV display application, that selects according to user shouldBy program, follow the tracks of and record the remote keying operation corresponding teleswitch value of overall process and application journeySequence index. Particularly, in a preferred embodiment, when judging user, TV selects " working "While being recording operation instruction, there is OSD to continue prompting the user, " application that please select you to open". Then user selects " USB application ", when program enters after USB application, and ensuing instituteHave the remote controller key will be by record one by one, user just can simulate and enter after USB application, asWhat is selected step by step the film that will play and realizes and playing with remote controller. User just completes oneselfWant, after the arranging of function, to select to exit the button of mode of learning. Learn according to prompting preservationContent, as the index of the alphabetic character of " opening USB flash disk movie " and USB application program withAnd the key assignments of a series of remote keyings such as up/down/left/right.
When step S23, recorded speech answer-mode, obtain the speech data of replying of user's input, andRawBecome to reply voice data file.
Record while replying voice being judged as, TV by recorded speech answer-mode time, obtains userInput reply speech data, and generate and reply voice data file. Particularly, preferred oneEmbodiment in, after user enters mode of learning, when the voice of one section of typing oneself, TV will useThe voice of family typing are stored in database associatedly with phonetic characters, and TV just can " parrotMechanically repeat other people's words " as spoken. Certainly described replys voice as long as have logical relation with control voice, can realize intelligent response. For example, controlling voice is " where remote controller is put ", replys languageSound can be " under cabinet for TV in drawer ". Like this when other kinsfolks to TV ask "Where remote controller is put " time, intelligent television energy intelligent response " under cabinet for TV in drawer "。
The present embodiment is by recording the operational order of the corresponding described control voice of user or replying the side of voiceMethod, has the beneficial effect that user can exchange with TV, makes TV have more intellectuality and peopleProperty.
With reference to Fig. 5, Fig. 5 is phonetic controller one example structure schematic diagram of the present invention; As shown in Figure 5, phonetic controller of the present invention specifically comprises:
First records module 01, for recording the control voice of user's input, extracts and record controls languageThe voice feature data of sound;
In a preferred embodiment, in TV main program, be provided with speech controling switch, default situationsLower voice control is inoperative, and after TV main program is opened this voice control function, TV just starts languageSound control system, phonetic function enters dialogue mode of operation after starting. Under dialogue mode, the first recordIt is defeated by voice-input devices such as microphone, voice remote controller or mobile phones that molding piece 01 is recorded userThe control voice that enter, extract simultaneously and record the voice feature data that these control voice are corresponding. ?In one preferred embodiment, first records module 01 is uploaded to cloud by the control voice of user's inputEnd server is identified, and extracts voice feature data; Particularly, first record module 01 generalThe voice of user's input are uploaded to high in the clouds speech recognition server, these high in the clouds voice after recordingIdentified server is converted to the phonetic characters that can be identified by TV, first after voice are identifiedRecord module 01 this phonetic characters is shown to the core for user by OSD or other display modesTo confirming, after user's confirmation, first records module 01 records this phonetic characters or source spyLevy data; In the present embodiment, described characteristic comprises described phonetic characters. Above-mentioned enforcementJourney please refer to the specific descriptions of embodiment described in Fig. 2, does not repeat them here.
Second records module 02, for recording the operational order of the corresponding described control voice of user or replyingVoice;
First records the corresponding phonetic feature number of control voice that module 01 is extracted and recording user is inputtedAccording to rear, second records module 02 also needs to record the corresponding operational order of these control voice or replysVoice; Particularly, in a preferred embodiment, first second records module 02 judges userThe voice control type of selecting; If when the control type that user selects is " speaking ", the second recordMolding piece 02 is stored the voice of user's input, sets up voice path and the corresponding voice word of these voiceCorresponding relation between symbol is also stored to described database. If user select control type be "Handle affairs " time, second records module 02 display application program listing, the application of selecting according to userProgram, follows the tracks of and records the remote keying operation corresponding teleswitch value of overall process and application programIndex; And set up corresponding relation also between application index, teleswitch value and phonetic charactersBe stored to described database.
Association arranges module 03, for described voice feature data and described operational order being set or replyingThe association of voice, for the voice operating control instruction of User Defined electronic equipment.
In order to realize the voice operating control instruction of User Defined electronic equipment, need association that mould is setPiece 03 arranges voice feature data with operational order or replys the associated of voice. With reference to Fig. 6, Fig. 6That in Fig. 5, association arranges module one example structure schematic diagram; As shown in Figure 6, association arranges mouldPiece 03 specifically comprises:
Operational order setting unit 031, for according to the described operational order of recording, sets up described applicationThe corresponding relation of procedure index, described teleswitch value and described phonetic characters is also stored to databaseIn;
Reply voice setting unit 032, for reply voice described in recording, set up described voiceCharacter or characteristic and described in reply the corresponding relation of voice, and be stored in database.
Association arranges module 03 and voice feature data is set is specially with the associated of operational order:
If the associated of described voice feature data and operational order is set, operational order setting unit 031 according to the operational order of recording, and sets up the right of application index, teleswitch value and phonetic charactersShould be related to and be stored in database;
If voice feature data be set and reply the associated of voice, replying voice setting unit 032 basisThat records replys voice, sets up phonetic characters or characteristic and replys the corresponding relation of voice, and be stored in database.
In a preferred embodiment, database storage is also retrieved the phonetic characters that high in the clouds is returned, and comparesMemory scan speech audio file is more simple, accurate. Certainly, described database is stored in cloudEnd server, data volume is little, and therefore the expense of local hardware is also little, can more accurately retrieve audio frequencyFile or phonetic characters, be not restricted here.
Describing phonetic controller of the present invention with specific embodiment below carries out voice-operated concreteRealExecute process.
Such as realizing the voice control of " opening USB flash disk movie ". First user enters mode of learning, the instruction that study receives. TV can be pointed out user input voice instruction, and user passes through MikeThe phonetic entry that wind will " be turned on USB flash disk movie " is to TV, and the phonetic controller of TV is logicalCross high in the clouds processing and be converted to alphabetic character, and " you input to feed back to user in the mode of OSD promptingBe ' opening USB flash disk movie '? " User selects "Yes", then just entersThe second step of practising, OSD further points out " study is spoken or handled affairs? " user selects " to handle affairs", there is OSD to continue prompting user, " application that please select you to open ". Then user's choosingSelect " USB application ", when program enters after USB application, ensuing all remote controller keys willCan be by record one by one, after user just can simulate and enter USB and apply, how to use remote controller one stepStep is selected the film that will play and is realized and playing. User just completes the setting of oneself wanting functionAfter, the button of mode of learning is exited in selection. In phonetic controller prompting preservation studyHold, as the index of the alphabetic character of " opening USB flash disk movie " and USB application program andThe key assignments of a series of remote keyings such as up/down/left/right. In addition, phonetic controller is by above-mentionedMethod can also be gone to speak by " religion " TV, such as user enter after mode of learning one section of typing fromOneself voice, and be stored in database associated with phonetic characters the voice of typing, electricDepending on just can " repeating the words of others like a parrot ", having spoken as intelligent response.
The present embodiment, by recording the control voice of user's input, extracts the also voice of record controls voiceCharacteristic, record the operational order of these control voice or reply voice, phonetic feature number is setAccording to operational order or reply the associated of voice and these control voice are responded, there is userThe beneficial effect that can customize speech recognition controlled and can exchange with TV, has TVThe function of study, has improved TV performance, has promoted user's experience.
With reference to Fig. 7, Fig. 7 first records module one example structure schematic diagram in Fig. 5; The present embodiment onlyRecord module 01 to first and be further described, other that phonetic controller of the present invention is relatedModule please refer to the specific descriptions of related embodiment, does not repeat them here.
As shown in Figure 7, in phonetic controller of the present invention, first records module 01 specifically comprises:
Characteristic extraction unit 011, knows for described control voice are uploaded to cloud server, do not extract described voice feature data;
Phonetic characters acquiring unit 012, is converted to and can shows according to described voice feature data for receivingThe alphabetic character showing, hereinafter to be referred as phonetic characters;
Record cell 013, for showing described phonetic characters, confirms that user described phonetic characters is errorlessPhonetic characters or source characteristic described in Shi Jilu.
The characteristic extraction unit 011 of TV is uploaded to cloud server by the control voice of user's input and entersRow identification, extracts voice feature data; Characteristic extraction unit 011 is by the voice of user's inputAfter recording, be uploaded to high in the clouds speech recognition server, this high in the clouds speech recognition server is to languageSound is converted to the phonetic characters that can be identified by TV, phonetic characters acquiring unit 01 after identifying2 obtain this phonetic characters, and record cell 013 shows this phonetic characters by OSD or by otherThe mode of showing shows for user and checks confirmation, after user's confirmation, and record cell 013 recordThis phonetic characters or source characteristic; In the present embodiment, described characteristic comprises institute's predicateSound character. Above-mentioned specific implementation process please refer to the specific descriptions of embodiment described in Fig. 2, at this notRepeat again.
The present embodiment, by recording the control voice of user's input, extracts the also voice of record controls voiceCharacteristic, has user and can customize the beneficial effect of speech recognition controlled.
With reference to Fig. 8, Fig. 8 second records module one example structure schematic diagram in Fig. 5; The present embodiment onlyRecord module 02 to second and be further described, other that phonetic controller of the present invention is relatedModule please refer to the specific descriptions of related embodiment, does not repeat them here.
As shown in Figure 8, in phonetic controller of the present invention, second records module 02 specifically comprises:
Operational order recording elements 021, for being judged as while recording described operational order, display applicationProgram listing, the application program of selecting according to user, follows the tracks of and records remote keying and operate full mistakeThe corresponding teleswitch value of journey and application index;
In the time being judged as recording operation instruction, the 021 display application program listing of operational order recording elements,The application program of selecting according to user, follows the tracks of and records remote keying operation overall process correspondingTeleswitch value and application index. Particularly, in a preferred embodiment, when TV judgementWhen user selects " working " to be recording operation instruction, there is OSD to continue prompting user, " please selectSelect the application that you will open ". Then user selects " USB application ", answers when program enters USBWith rear, ensuing all remote controller keys will be by record one by one, and user just can simulateEnter after USB application, how select step by step the film that will play and realize broadcasting with remote controller. User just completes and oneself wants, after the arranging of function, to select to exit the button of mode of learning. RootPreserve the content of study according to 021 prompting of operational order recording elements, as " opened USB flash disk and play electricityShadow " alphabetic character and a series of remote controls such as index and up/down/left/right of USB application programThe key assignments of button.
Reply voice recording unit 022, for being judged as while replying voice described in recording, recorded speechWhen answer-mode, obtain the speech data of replying of user's input, and speech data is replied in generationFile.
Record while replying voice being judged as, reply voice recording unit 022 by recorded speech answer-modeTime, obtain the speech data of replying of user's input, and voice data file is replied in generation.Particularly, in a preferred embodiment, one section of typing oneself after user enters mode of learningVoice time, reply voice recording unit 022 by associated with phonetic characters the voice of user's typing groundBe stored in database, TV having spoken as just can " repeating the words of others like a parrot ". Certainly describedReply voice as long as have logical relation with control voice, can realize intelligent response. For example, controlVoice processed are " where remote controller is put ", reply voice and can be " under cabinet for TV in drawer ". Like this in the time that other kinsfolks ask " where remote controller is put " to TV, Intelligent electricDepending on can intelligent response " under cabinet for TV in drawer ".
The present embodiment is by recording the operational order of the corresponding described control voice of user or replying voice, toolThe beneficial effect that has user to exchange with TV, makes TV have more intellectuality and hommization.
With reference to Fig. 9, Fig. 9 is voice response method one embodiment schematic flow sheet of the present invention; Language of the present inventionSound equipment induction method comprises the method that the control voice in above-mentioned sound control method are responded,As shown in Figure 9, voice response method of the present invention comprises the following steps:
Step S101, obtain the control voice of user input, and extract and control voice feature data;
Under dialogue mode, user is by voice-input devices such as microphone, voice remote controller or mobile phonesInput voice information, TV obtains the control voice of user input, and it is right to extract this control voice instituteThe control voice feature data of answering; Particularly, in a preferred embodiment, user's inputAfter the speech recognition system identification of voice messaging by cloud server, by this voice document conversionFor phonetic characters, described phonetic characters comprises all characters that can be identified by TV such as alphabetic character; Described control voice feature data comprises described phonetic characters. Above-mentioned specific implementation process please be joinedAccording to the specific descriptions of embodiment described in Fig. 2, do not repeat them here.
Whether step S102, retrieval phonetic characters database, judge in described database and can findThe response mode that described voice feature data is corresponding; If so, perform step S103; If not,Perform step S104;
Step S103, reply according to described response mode;
Step S104, switch to study and work pattern carry out corresponding operating or prompting user re-enter instituteState phonetic order.
The index of setting up according to phonetic characters, retrieval phonetic characters database, it is right in database, to findThe response mode of answering. If can find the response mode of this phonetic characters in database,Reply according to this response mode. If operation so just enters its specified applicationProgram completes associative operation; If voice answer-back is play corresponding voice document. IfIn database, do not find the response mode of this phonetic characters, on OSD, point out user's retryOr enter mode of learning.
Particularly, the mode of operation of TV acquiescence is dialogue mode, under dialogue mode, passes through MikeWind is said " opening USB flash disk movie " to TV, and television set can pass through cloud by the voice of input automaticallyEnd speech recognition is corresponding alphabetic character, and then to search in local data base, " opening USB flash disk playsFilm " character, if find relative recording, carry out the operation that matches with it as startedUSB(UniversalSerialBus, USB) application program send and beRow key assignments message, to TV, so just can realize the desired function of user. If databaseIn do not find relevant character, explanation is not set up this language control function or speech recognition hasMistake, points out user to re-enter or enter mode of learning.
Sound control method of the present invention can travel through all application programs, and with remote controller simulate intoEnter the operation of application program inside, therefore user can also simulate more operation such as editorProgram, preserved program, volume plus-minus, change channel, timing shutdown, check the sky in certain cityGas forecasts, logs in certain website etc. User carries out relative set to TV according to the method described above," church " TV has been done.
The present embodiment enters dialogue mode of operation by starting phonetic function, confirms errorless postscript userThe phonetic characters that record obtains after being changed by the phonetic order of inputting is looked in phonetic characters databaseWhile arriving the response mode of this phonetic characters, reply according to this response mode, do not findingTime, switch to study and work pattern and carry out corresponding operating or point out user to re-enter these voice referring toThe method of order, having user can self-defined speech recognition controlled also can exchange with TVBeneficial effect, make TV have the function of study, improved TV performance, promoted userExperience.
With reference to Figure 10, Figure 10 replys an embodiment schematic flow sheet according to response mode in Fig. 9;The present embodiment is only described specifically step S103, its that voice response method of the present invention is relatedHis step, please refer to the specific descriptions of related embodiment, does not repeat them here.
As shown in figure 10, in voice response method of the present invention, step S103, according to described response modeReply specifically and comprise:
Step S31, judge the corresponding action type of described response mode; Be behaviour in described response modeWhile responsing, execution step S32; In the time that described response mode is voice answer-back, execution step S33；
Step S32, the application program of carrying out described operation acknowledge appointment and/or corresponding control command;
Step S33, play corresponding voice document.
If can find the response mode of this phonetic characters in database, according to this response modeReply. If i.e. " working " of operation so just enters its specified application programComplete associative operation; If i.e. " the speaking " of voice answer-back play corresponding voice document. Particularly, such as, if this operation acknowledge is " opening USB flash disk movie ", television set is justCarry out the application program that this replys appointment, television set is opened USB flash disk automatically, and movie; IfBe voice answer-back, television set is play corresponding language according to the voice path of this phonetic characters associationSound, as play the voice " you are really very good " of the prior typing of user.
The present embodiment is by judging that the corresponding action type of response mode is operation or voice rootCarry out the corresponding method of replying according to response mode, have the beneficial effect of TV set intelligent。
With reference to Figure 11, Figure 11 is voice response device one example structure schematic diagram of the present invention; This enforcementThe described voice response device of example comprises to be controlled above-mentioned phonetic controller, as Figure 11 instituteShow, voice response device of the present invention comprises:
Control voice acquisition module 10, for obtaining the control voice of user's input, and extract and control languageSound characteristic;
Under dialogue mode, user is by voice-input devices such as microphone, voice remote controller or mobile phonesInput voice information, the control voice acquisition module 10 of TV obtains the control voice of user's input,And extract the corresponding control voice feature data of these control voice; Particularly, preferred oneIn embodiment, the voice messaging of user's input is by the speech recognition system identification of cloud serverAfter, this voice document is converted to phonetic characters, described phonetic characters comprises alphabetic character etc.Cut the character that can be identified by TV; Described control voice feature data comprises described phonetic characters.Above-mentioned specific implementation process please refer to the specific descriptions of embodiment described in Fig. 2, does not repeat them here.
Response mode acquisition module 20, for retrieving phonetic characters database, judges at described databaseIn whether can find the corresponding response mode of described voice feature data;
The first responder module 30, for finding described voice feature data pair at described databaseAnswer response mode time, reply according to described response mode;
The second responder module 40, for not finding described voice feature data pair at described databaseAnswer response mode time, switch to study and work pattern carry out corresponding operating or prompting user againDescribed in inputPhonetic order.
The index of setting up according to phonetic characters, response mode acquisition module 20 is retrieved phonetic characters database, in database, find corresponding response mode. If response mode acquisition module 20 can beIn database, find the response mode of this phonetic characters, the first responder module 30 is replied according to thisMode is replied. If operation, the first responder module 30 just enters that it is specified soApplication program completes associative operation; If voice answer-back, the first responder module 30 play rightThe voice document of answering. If response mode acquisition module 20 does not find these voice in databaseThe response mode of character is pointed out user's retry or is switched by the second responder module 40 on OSDEnter mode of learning.
Particularly, the mode of operation of TV acquiescence is dialogue mode, under dialogue mode, passes through MikeWind is said " opening USB flash disk movie " to TV, and television set can pass through cloud by the voice of input automaticallyEnd speech recognition is corresponding phonetic characters, controls voice acquisition module 10 and records this phonetic characters,Then in local data base, search for " opening USB flash disk movie " by response mode acquisition module 20Character, if response mode acquisition module 20 finds relative recording, the first responder module 30Carry out the operation matching with it as started USB application program and sending a series of key assignments message to electricityDepending on, so just can realize the desired function of user. If response mode acquisition module 20 existsIn database, do not find relevant character, this language control function or voice are not set up in explanationIdentify wrongly, point out user to re-enter or switch and enter study mould by the second responder module 40Formula.
Phonetic controller of the present invention can travel through all application programs by above-mentioned sound control method, and simulate the operation that enters application program inside with remote controller, therefore user can also simulateGo out more operation such as editing program, preserved program, volume plus-minus, change channel, regularlyShutdown, check certain city weather forecast, log in certain website etc. User is right according to the method described aboveTV carries out relative set, can do by " church " TV.
The present embodiment enters dialogue mode of operation by starting phonetic function, confirms errorless postscript userThe phonetic characters that record obtains after being changed by the phonetic order of inputting is looked in phonetic characters databaseWhile arriving the response mode of this phonetic characters, reply according to this response mode, do not findingTime, switch to study and work pattern and carry out corresponding operating or point out user to re-enter these voice referring toOrder, have user can self-defined speech recognition controlled and can exchange with TV usefulEffect, makes TV have the function of study, has improved TV performance, has promoted user's experience.
With reference to Figure 12, Figure 12 talks with operational module one example structure schematic diagram in Figure 11; This enforcementExampleOnly the first responder module 30 is further described to its that phonetic controller of the present invention is relatedHis module please refer to the specific descriptions of related embodiment, does not repeat them here.
As shown in figure 12, in phonetic controller of the present invention, the first responder module 30 specifically comprises:
Acknowledgement type acquiring unit 301, for judging the corresponding action type of described response mode;
Operation acknowledge unit 302, in the time that described response mode is operation acknowledge, carries out described operationReply application program and/or the corresponding control instruction of appointment;
Voice responding unit 303, in the time that described response mode is voice answer-back, plays corresponding languageSound file.
If response mode acquisition module 20 can find the response mode of this phonetic characters in database, acknowledgement type acquiring unit 301 judges that the corresponding action type of this response mode basis shouldResponse mode is replied. If acknowledgement type acquiring unit 301 judges that this response mode is for operationReply i.e. " working ", it is complete that operation acknowledge unit 302 just enters its specified application program soBecome associative operation; If it is that voice answer-back is that acknowledgement type acquiring unit 301 judges this response mode" speak ", voice responding unit 303 is play corresponding voice document. Particularly, such as,If acknowledgement type acquiring unit 301 judges that this operation acknowledge is for " opening USB flash disk movie ",This is just carried out and replys the application program of appointment in the operation acknowledge unit 302 of television set, television set fromMoving USB flash disk the movie opened; If acknowledgement type acquiring unit 301 judges this operation acknowledge and isVoice answer-back, the voice responding unit 303 of television set is according to the voice road of this phonetic characters associationCorresponding voice are play in footpath, as play the voice " you are really very good " of the prior typing of user.
The present embodiment is by judging that the corresponding action type of response mode is operation or voice rootCarry out corresponding replying according to response mode, have the beneficial effect of TV set intelligent.
The foregoing is only the preferred embodiments of the present invention, not thereby limit its scope of the claims, everyThe equivalent structure or the conversion of equivalent flow process that utilize description of the present invention and accompanying drawing content to do, directlyOr be indirectly used in other relevant technical fields, be all in like manner included in patent protection of the present inventionIn scope.
Claims (14)
1. a sound control method, is characterized in that, comprises the following steps:
Record the control voice of user's input, extract and record the voice feature data of described control voice;
Record the operational order of the corresponding described control voice of user or reply voice;
Described voice feature data be set with described operational order or reply the associated of voice, making by oneself for userThe voice operating control instruction of justice electronic equipment;
Wherein, the step of recording the operational order of the corresponding described control voice of user or replying voice comprises:When being judged as while recording described operational order,
Display application program listing, the application program of selecting according to user, follows the tracks of and records remote keying behaviourMake the corresponding teleswitch value of overall process and application index.
2. the method for claim 1, is characterized in that, described in record the control language of user inputSound, extracts the also step of the voice feature data of record controls voice and specifically comprises:
Described control voice are uploaded to cloud server and identify, extract described voice feature data;
Receive and be converted to readable phonetic characters according to described voice feature data;
Show described phonetic characters, confirm that user described phonetic characters records described phonetic characters when errorlessOr source characteristic.
3. the method for claim 1, is characterized in that, described in record the corresponding described control of userThe operational order of voice or the step of replying voice also comprise:
When being judged as while replying voice described in recording,
When recorded speech answer-mode, obtain the speech data of replying of user's input, and language is replied in generationSound data file.
4. method as claimed in claim 2, is characterized in that, described described voice feature data is setSpecifically comprise with described operational order or the associated step of replying voice:
According to the described operational order of recording, set up described application index, described teleswitch value and instituteState the corresponding relation of phonetic characters and be stored in database;
Or,
Described in recording, reply voice, set up described phonetic characters or characteristic and described in replyThe corresponding relation of voice, and be stored in database.
5. method as claimed in claim 4, is characterized in that, described database comprises that operational order shouldAnswer sound bank, described operational order is replied sound bank and is comprised multiple voice documents, described voice document associationCorresponding described voice operating control instruction and application index.
6. a phonetic controller, is characterized in that, comprising:
First records module, for recording the control voice of user's input, extracts and record described control languageThe voice feature data of sound;
Second records module, for recording the operational order of the corresponding described control voice of user or replying voice;
Association arranges module, for described voice feature data and described operational order being set or replying voiceAssociation, for the voice operating control instruction of User Defined electronic equipment;
Described second records module comprises:
Operational order recording elements, for being judged as while recording described operational order,
Display application program listing, the application program of selecting according to user, follows the tracks of and records remote keying behaviourMake the corresponding teleswitch value of overall process and application index.
7. device as claimed in claim 6, is characterized in that, described first records module specifically comprises:
Characteristic extraction unit, identifies for described control voice are uploaded to cloud server,Extract described voice feature data;
Phonetic characters acquiring unit, is converted to readable language for receiving according to described voice feature dataSound character;
Record cell, for showing described phonetic characters, note in the time that user confirms that described phonetic characters is errorlessRecord described phonetic characters or source characteristic.
8. device as claimed in claim 6, is characterized in that, described second records module also comprises:
Reply voice recording unit, for being judged as while replying voice described in recording, recorded speech is repliedWhen pattern, obtain the speech data of replying of user's input, and voice data file is replied in generation.
9. device as claimed in claim 7, is characterized in that, described association arranges module and specifically comprises:
Operational order setting unit, for according to the described operational order of recording, sets up described application programThe corresponding relation of index, described teleswitch value and described phonetic characters is also stored in database;
Reply voice setting unit, for reply voice described in recording, set up described phonetic charactersOr characteristic and described in reply the corresponding relation of voice, and be stored in database.
10. device as claimed in claim 9, is characterized in that, described database comprises that operational order shouldAnswer sound bank, described operational order is replied sound bank and is comprised multiple voice documents, described voice document associationCorresponding described voice operating control instruction and application index.
11. 1 kinds of voice response methods, described response method comprises voice control as claimed in claim 1The method that control voice in method processed respond, is characterized in that, described response method comprises followingStep:
Obtain the control voice of user's input, and extract and control voice feature data;
Retrieval phonetic characters database, judges in described database whether can find described phonetic featureThe response mode that data are corresponding;
If so, reply according to described response mode;
If not, switching to study and work pattern carries out corresponding operating or points out user to re-enter voice referring toOrder;
Described step of replying according to described response mode comprises:
Judge the corresponding action type of described response mode;
In the time that described response mode is operation acknowledge, carry out application program that described operation acknowledge specifies and/orCorresponding control instruction.
12. response methods as claimed in claim 11, is characterized in that, described according to described answer partyThe step that formula is replied also comprises:
In the time that described response mode is voice answer-back, play corresponding voice document.
13. 1 kinds of voice response devices, described responding device comprises voice control as claimed in claim 6Device processed is controlled, and it is characterized in that, described responding device comprises:
Control voice acquisition module, for obtaining the control voice of user's input, and extract and control voice spyLevy data;
Response mode acquisition module, for retrieving phonetic characters database, judges in described database to beNoly can find the response mode that described voice feature data is corresponding;
The first responder module, for finding described voice feature data corresponding at described databaseWhen response mode, reply according to described response mode;
The second responder module, for not finding described voice feature data corresponding at described databaseWhen response mode, switch to study and work pattern and carry out corresponding operating or point out user to re-enter voice referring toOrder;
Described the first responder module comprises:
Acknowledgement type acquiring unit, for judging the corresponding action type of described response mode;
Operation acknowledge unit, in the time that described response mode is operation acknowledge, carries out described operation acknowledgeThe application program of specifying and/or corresponding control instruction.
14. devices as claimed in claim 13, is characterized in that, described the first responder module also comprises:
Voice responding unit, in the time that described response mode is voice answer-back, plays corresponding voice literary compositionPart.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210319278.6A CN102842306B (en) | 2012-08-31 | 2012-08-31 | Sound control method and device, voice response method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210319278.6A CN102842306B (en) | 2012-08-31 | 2012-08-31 | Sound control method and device, voice response method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102842306A CN102842306A (en) | 2012-12-26 |
| CN102842306B true CN102842306B (en) | 2016-05-04 |
Family
ID=47369592
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210319278.6A Active CN102842306B (en) | 2012-08-31 | 2012-08-31 | Sound control method and device, voice response method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102842306B (en) |
Families Citing this family (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9443522B2 (en) | 2013-11-18 | 2016-09-13 | Beijing Lenovo Software Ltd. | Voice recognition method, voice controlling method, information processing method, and electronic apparatus |
| CN103646646B (en) * | 2013-11-27 | 2018-08-31 | 联想(北京)有限公司 | A kind of sound control method and electronic equipment |
| CN103793641B (en) * | 2014-02-27 | 2021-07-16 | 联想(北京)有限公司 | Information processing method and device and electronic equipment |
| CN103945152A (en) * | 2014-03-14 | 2014-07-23 | 京东方科技集团股份有限公司 | Television set and method for voice control over television set |
| TWI561052B (en) * | 2014-07-08 | 2016-12-01 | Hooloop Corp | Methods and systems for voice message association and playback, and related computer program products |
| CN105653229A (en) * | 2014-11-14 | 2016-06-08 | 中兴通讯股份有限公司 | Method and device for implementing voice control |
| CN105739940A (en) * | 2014-12-08 | 2016-07-06 | 中兴通讯股份有限公司 | Storage method and device |
| CN105810207A (en) * | 2014-12-30 | 2016-07-27 | 富泰华工业（深圳）有限公司 | Meeting recording device and method thereof for automatically generating meeting record |
| CN105845136A (en) * | 2015-01-13 | 2016-08-10 | 中兴通讯股份有限公司 | Voice control method and device, and terminal |
| CN104837010B (en) * | 2015-04-24 | 2017-04-12 | 青岛海信电器股份有限公司 | Voice remote control testing method, device and system |
| CN104992709B (en) * | 2015-06-25 | 2019-06-11 | 广州视源电子科技股份有限公司 | A kind of the execution method and speech recognition apparatus of phonetic order |
| CN105245913B (en) * | 2015-09-25 | 2019-02-22 | 小米科技有限责任公司 | Information acquisition method and device |
| CN105355200B (en) * | 2015-11-20 | 2020-02-07 | 深圳狗尾草智能科技有限公司 | System and method for directly training and modifying robot interactive content |
| CN105546724B (en) * | 2015-12-16 | 2018-08-14 | 芜湖美智空调设备有限公司 | Sound control method and system, client, control device |
| CN105897686A (en) * | 2015-12-21 | 2016-08-24 | 乐视致新电子科技（天津）有限公司 | Smart television user account speech management method and smart television |
| CN105744326A (en) * | 2016-02-03 | 2016-07-06 | 广东长虹电子有限公司 | Editable voice intelligent control method and system for television |
| CN106205614A (en) * | 2016-07-27 | 2016-12-07 | 太仓世源金属制品有限公司 | The remote control unit of a kind of speech-controlled electric bed and remote control system |
| CN106331874A (en) * | 2016-08-31 | 2017-01-11 | 浙江创佳数字技术有限公司 | Set top box control method and devices |
| CN106952646A (en) * | 2017-02-27 | 2017-07-14 | 深圳市朗空亿科科技有限公司 | A kind of robot interactive method and system based on natural language |
| CN106971009B (en) * | 2017-05-11 | 2020-05-22 | 网易（杭州）网络有限公司 | Voice database generation method and device, storage medium and electronic equipment |
| CN109089140A (en) * | 2017-06-14 | 2018-12-25 | 北京优朋普乐科技有限公司 | A kind of sound control method and device |
| CN107454508B (en) * | 2017-08-23 | 2020-07-14 | 深圳创维－Rgb电子有限公司 | TV set and TV system of microphone array |
| CN110322876A (en) * | 2018-03-30 | 2019-10-11 | 中华映管股份有限公司 | Voice application system and its method |
| CN108717853B (en) * | 2018-05-09 | 2020-11-20 | 深圳艾比仿生机器人科技有限公司 | Man-machine voice interaction method, device and storage medium |
| CN110544473B (en) * | 2018-05-28 | 2022-11-08 | 百度在线网络技术（北京）有限公司 | Voice interaction method and device |
| CN108632653B (en) * | 2018-05-30 | 2022-04-19 | 腾讯科技（深圳）有限公司 | Voice control method, smart television and computer readable storage medium |
| CN108831469B (en) * | 2018-08-06 | 2021-02-12 | 珠海格力电器股份有限公司 | Voice command customizing method, device and equipment and computer storage medium |
| CN109471931A (en) * | 2018-11-22 | 2019-03-15 | 平安科技（深圳）有限公司 | Corpus collection method, device, computer equipment and storage medium |
| CN112153213A (en) * | 2019-06-28 | 2020-12-29 | 青岛海信移动通信技术股份有限公司 | Method and equipment for determining voice information |
| CN111128136A (en) * | 2019-11-28 | 2020-05-08 | 星络智能科技有限公司 | User-defined voice control method, computer equipment and readable storage medium |
| CN111221282A (en) * | 2019-12-27 | 2020-06-02 | 深圳世纪扬凡数码科技有限公司 | Intelligent voice switch and setting method thereof |
| CN111327935B (en) * | 2020-03-02 | 2021-12-24 | 彩迅工业(深圳)有限公司 | Information interaction platform based on artificial intelligence TV set |
| CN111757195B (en) * | 2020-06-09 | 2022-10-21 | 北京未来居科技有限公司 | Information output method and device based on intelligent sound box |
| CN111934959A (en) * | 2020-08-11 | 2020-11-13 | 广东好太太科技集团股份有限公司 | Intelligent clothes airing machine and voice control system and method thereof |
| CN112309373A (en) * | 2020-09-28 | 2021-02-02 | 惠州市德赛西威汽车电子股份有限公司 | System and method for self-defining vehicle-mounted voice technology |
| CN112399222A (en) * | 2020-11-10 | 2021-02-23 | 深圳创维－Rgb电子有限公司 | Voice instruction learning method and device for smart television, smart television and medium |
| CN112735387A (en) * | 2020-12-25 | 2021-04-30 | 惠州市德赛西威汽车电子股份有限公司 | User-defined vehicle-mounted voice skill system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075433A (en) * | 2007-04-18 | 2007-11-21 | 上海山思智能科技有限公司 | Artificial intelligent controlling method for discriminating robot speech |
| CN201514761U (en) * | 2009-09-23 | 2010-06-23 | 上海大屯能源股份有限公司 | Household voice controller |
| CN101794126A (en) * | 2009-12-15 | 2010-08-04 | 广东工业大学 | Wireless intelligent home appliance voice control system |
| CN101938391A (en) * | 2010-08-31 | 2011-01-05 | 中山大学 | Voice processing method, system, remote controller, set-top box and cloud server |
| CN102036033A (en) * | 2010-12-31 | 2011-04-27 | Tcl集团股份有限公司 | Method for remotely controlling television with voice and remote voice control |
-
2012
- 2012-08-31 CN CN201210319278.6A patent/CN102842306B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075433A (en) * | 2007-04-18 | 2007-11-21 | 上海山思智能科技有限公司 | Artificial intelligent controlling method for discriminating robot speech |
| CN201514761U (en) * | 2009-09-23 | 2010-06-23 | 上海大屯能源股份有限公司 | Household voice controller |
| CN101794126A (en) * | 2009-12-15 | 2010-08-04 | 广东工业大学 | Wireless intelligent home appliance voice control system |
| CN101938391A (en) * | 2010-08-31 | 2011-01-05 | 中山大学 | Voice processing method, system, remote controller, set-top box and cloud server |
| CN102036033A (en) * | 2010-12-31 | 2011-04-27 | Tcl集团股份有限公司 | Method for remotely controlling television with voice and remote voice control |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102842306A (en) | 2012-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102842306B (en) | Sound control method and device, voice response method and device | |
| JP6613347B2 (en) | Method and apparatus for pushing information | |
| US11100934B2 (en) | Method and apparatus for voiceprint creation and registration | |
| CN106663430B (en) | Keyword detection for speaker-independent keyword models using user-specified keywords | |
| CN108470566B (en) | Application operation method and device | |
| EP2747389B1 (en) | Mobile terminal having auto answering function and auto answering method for use in the mobile terminal | |
| CN109101545A (en) | Natural language processing method, apparatus, equipment and medium based on human-computer interaction | |
| CN110020010A (en) | Data processing method, device and electronic equipment | |
| EP3611724A1 (en) | Voice response method and device, and smart device | |
| CN108172223A (en) | Voice instruction recognition method, device and server and computer readable storage medium | |
| US10191716B2 (en) | Method and apparatus for recognizing voice in portable device | |
| CN103078995A (en) | Customizable individualized response method and system used in mobile terminal | |
| WO2018099000A1 (en) | Voice input processing method, terminal and network server | |
| CN102568478A (en) | Video play control method and system based on voice recognition | |
| CN106570100A (en) | Information search method and device | |
| CN107655154A (en) | Terminal control method, air conditioner and computer-readable recording medium | |
| CN103888581A (en) | Communication terminal and method for recording communication information thereof | |
| CN104252464A (en) | Information processing method and information processing device | |
| WO2020038145A1 (en) | Service data processing method and apparatus, and related device | |
| CN107479400A (en) | Control method, device, home appliance and the readable storage medium storing program for executing of home appliance | |
| CN106782604A (en) | The processing method of speech message, device and its electronic equipment | |
| CN104468941A (en) | Information display method and device | |
| CN103425668A (en) | Information search method and electronic equipment | |
| CN105100672A (en) | Display apparatus and method for performing videotelephony using the same | |
| CN102847325A (en) | Toy control method and system based on voice interaction of mobile communication terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |