The content of the invention
It is an object of the invention to provide a kind of audio control method and device of adaptive external environment, can preferably solveThe problem of audio is certainly controlled according to external environment.
According to an aspect of the invention, there is provided a kind of audio control method of adaptive external environment, including：
Corresponding relation between default phonetic control command and audio frequency control instruction；
During computer system plays audio, phonetic control command is obtained by speech recognition；
According to the corresponding relation between default phonetic control command and audio frequency control instruction, it is determined that resulting voice controlAudio frequency control instruction corresponding to system instruction；
Instructed using identified audio frequency control, the audio played to computer system is controlled.
Preferably, in addition to：
Diverse location on computer surface sets multiple Mikes, and formation can be by Pointing calculation machine outside sound source sideTo microphone array.
Preferably, the step of corresponding relation between the default phonetic control command and audio frequency control instruction includes：
Before computer system plays audio, using the microphone array, user speech stream is obtained；
Speech recognition is carried out to the user speech stream, obtains phonetic control command；
The instruction of resulting phonetic control command and audio frequency control is carried out corresponding, obtain phonetic control command and audio controlCorresponding relation between system instruction.
Preferably, it is described during computer system plays audio, the step of phonetic control command is obtained by speech recognitionSuddenly include：
During computer system plays audio, the audio play data stream of the currently playing audio of computer system is obtained；
Using the microphone array, the mixed audio stream comprising user speech stream and audio play data stream is obtained；
In the mixed audio stream, the audio play data stream is eliminated, obtains user speech stream；
Speech recognition is carried out to the user speech stream, obtains phonetic control command.
Preferably, audio frequency control determined by the utilization instructs, what the audio played to computer system was controlledStep includes：
When the instruction of identified audio frequency control is the instruction for adjusting volume, it is used for adjusting volume according to describedThe instruction of size, the volume that audio is played to computer system are adjusted；
When the instruction of identified audio frequency control be for control it is Jing Yin/release Jing Yin instruction when, be used for controlling according to describedJing Yin/Jing Yin instruction of releasing is made, the volume that audio is played to computer system carries out Jing Yin/Jing Yin control of releasing；
When the instruction of identified audio frequency control is the instruction for suspending/continuing to play, it is used for controlling temporarily according to describedStop/continue the instruction played, control computer system audio, which suspends/continued, to be played.
According to another aspect of the present invention, there is provided a kind of audio control apparatus of adaptive external environment, including：
Setup module, for presetting the corresponding relation between phonetic control command and audio frequency control instruction；
Identification module, for during computer system plays audio, phonetic control command to be obtained by speech recognition；
Determining module, for the corresponding relation between being instructed according to default phonetic control command and audio frequency control, it is determined thatAudio frequency control corresponding to resulting phonetic control command instructs；
Control module, instructed for audio frequency control determined by utilization, the audio played to computer system is controlled.
Preferably, in addition to：
Multiple Mikes of computer surface diverse location are arranged on, formation can be by Pointing calculation machine outside sound source sideTo microphone array.
Preferably, before computer system plays audio, voice that the identification module obtains to the microphone arrayStream carries out speech recognition, obtains phonetic control command, and the setup module is by resulting phonetic control command and audio frequency controlInstruction carries out correspondingly, obtaining the corresponding relation between phonetic control command and audio frequency control instruction.
Preferably, during computer system plays audio, the microphone array obtains and includes user speech stream and audioThe mixed audio stream of play data stream, the identification module obtain the audio played data of the currently playing audio of computer systemStream, and the audio play data stream is eliminated in the mixed audio stream that the microphone array obtains, user speech stream is obtained, it is rightThe user speech stream carries out speech recognition, obtains phonetic control command.
Preferably, the control module identified audio frequency control instruction be the instruction for adjusting volume when,According to the instruction for being used for adjusting volume, the volume that audio is played to computer system is adjusted, identifiedAudio frequency control instruction be for control it is Jing Yin/release Jing Yin instruction when, according to it is described be used for controlling it is Jing Yin/release Jing Yin fingerOrder, the volume that audio is played to computer system carry out Jing Yin/Jing Yin control of releasing, are to use in the instruction of identified audio frequency controlDuring suspending/continue the instruction played, it is used for controlling the instruction for suspending/continuing and play, control computer system sound according to describedFrequency, which suspends/continued, to be played.
Compared with prior art, the beneficial effects of the present invention are：
By the present invention, for user when being conversed, computer particularly notebook computer product can intelligent regulating systemVolume, experienced with this to improve user, improve Consumer's Experience.
Embodiment
Below in conjunction with accompanying drawing to a preferred embodiment of the present invention will be described in detail, it will be appreciated that described below is excellentSelect embodiment to be merely to illustrate and explain the present invention, be not intended to limit the present invention.
Fig. 1 is the audio control method theory diagram of adaptive external environment provided in an embodiment of the present invention, such as Fig. 1 institutesShow, step includes：
Step S101：Corresponding relation between default phonetic control command and audio frequency control instruction.
In step S101, the corresponding relation between phonetic control command and the audio frequency control instruction can be computerIt is being pre-set before product export or be configured as needed by user after dispatching from the factory.
In order to reach more preferable effect, microphone array can be utilized to form a taper narrow beam, receive user speechWhile suppress environment in noise and interference.Specifically, the diverse location on computer surface sets multiple Mikes, is formedCan be by the microphone array in Pointing calculation machine outside sound source direction.For example, it can be set above note-book computer display screenTwo symmetrical Mikes are put, form microphone array, or, in note-book computer display screen marginal position, four symmetrical wheats are setGram, form microphone array, etc..
So, before computer system plays audio, the microphone array can be utilized, acquisition has suppressed ambient noiseWith the user speech stream of interference, speech recognition is carried out to the user speech stream, phonetic control command is obtained, then again by gainedTo the instruction of phonetic control command and audio frequency control carry out it is corresponding, obtain phonetic control command and audio frequency control instruct between pairIt should be related to.
Step S102：During computer system plays audio, phonetic control command is obtained by speech recognition.
Similarly, during computer system plays audio, the microphone array can be utilized, acquisition includes user speechThe mixed audio stream of stream and audio play data stream.For avoid computer itself play audio in occur " Voice command refers toMake " audio frequency control is carried out directly as the control instruction that user assigns, the present invention needs to eliminate the audio that computer itself plays,Therefore, during computer system plays audio, audio play data stream is divided into two-way, loudspeaker is sent into all the way and plays, separatelyIt is used for eliminating the audio play data stream in mixed audio stream all the way.Specifically, the sound of acquired currently playing audio is utilizedFrequency play data stream, the audio play data stream in the mixed audio stream is eliminated, obtains user speech stream.This makes it possible to rightThe user speech stream carries out speech recognition, obtains phonetic control command.
Step S103：According to the corresponding relation between default phonetic control command and audio frequency control instruction, it is determined that gainedAudio frequency control corresponding to the phonetic control command arrived instructs.
Step S104：Instructed using identified audio frequency control, the audio played to computer system is controlled.
Specifically, when the instruction of identified audio frequency control is the instruction for adjusting volume, according to the useTo adjust the instruction of volume, the volume that audio is played to computer system is adjusted；When identified audio frequency control refers toOrder be for control it is Jing Yin/release Jing Yin instruction when, according to it is described be used for controlling it is Jing Yin/release Jing Yin instruction, to calculatingThe volume of machine system plays audio carries out Jing Yin/Jing Yin control of releasing.
For example, phonetic control command can be " feeding ", " Hello ", " hello ", " goodbye " etc., audio frequency control instruction can be withIt is " volume tunes up ", " volume is turned down ", " Jing Yin ", " releasing Jing Yin ", " pause plays ", " continuing to play ", " closing audio " etc.Deng.Such as pre-set phonetic control command " feeding " and audio frequency control instruction " volume is turned down " between corresponding relation, withDuring family plays the audio file such as music, when user receives calls, eliminated by audio play data stream and speech recognition, will" fed " to phonetic control command, now according to default corresponding relation, can determine that audio frequency control instructs " volume is turned down ", and pressAccording to the instruction, music playback volume is turned down.For example pre-set phonetic control command " hello " and instructed " temporarily with audio frequency controlBreak and put " between corresponding relation, during user plays the video file such as film, when user receives calls, broadcast by audioData flow elimination and speech recognition are put, phonetic control command " hello " will be obtained, can be true now according to default corresponding relationAccordatura frequency control instruction " pause plays ", and play the video files such as film according to the instruction, pause.
Fig. 2 is the audio control apparatus block diagram of adaptive external environment provided in an embodiment of the present invention, as shown in Fig. 2 bagInclude setup module 21, identification module 22, determining module 23 and control module 24.
Setup module 21 is used to preset the corresponding relation between phonetic control command and audio frequency control instruction.
Identification module 22 is used to during computer system plays audio, phonetic control command is obtained by speech recognition.
Determining module 23 is used for according to the corresponding relation between default phonetic control command and audio frequency control instruction, it is determined thatAudio frequency control corresponding to resulting phonetic control command instructs.
Control module 24 is used for audio frequency control instruction determined by utilization, and the audio played to computer system is controlledSystem.
Further, in addition to：Microphone array 20, its multiple Mike's shape by being arranged on computer surface diverse locationInto can be by Pointing calculation machine outside sound source direction.
The course of work of described device is as follows：
Before computer system plays audio, microphone array 20 obtains voice flow, and identification module 22 is to Mike's battle arrayThe voice flow that row obtain carries out speech recognition, obtains phonetic control command, and now, setup module 21 is by resulting Voice commandInstruction carried out with audio frequency control instruction it is corresponding, obtain phonetic control command and audio frequency control instruct between corresponding relation.
During computer system plays audio, microphone array 20 obtains and includes user speech stream and audio play data streamMixed audio stream, identification module 22 obtains the audio play data stream of the currently playing audio of computer system, and in the wheatThe audio play data stream is eliminated in the mixed audio stream that gram array 20 obtains, user speech stream is obtained, to user's languageSound stream carries out speech recognition, obtains phonetic control command.The corresponding relation that determining module 23 is pre-set according to setup module 21,The audio frequency control instruction corresponding to the phonetic control command that identification module 22 obtains is determined, so that control module 24 is carried out accordinglyAudio frequency control, such as when the instruction of identified audio frequency control is the instruction for adjusting volume, be used for adjusting according to describedThe instruction of volume is saved, the volume that audio is played to computer system is adjusted；When the instruction of identified audio frequency control isFor control it is Jing Yin/release Jing Yin instruction when, according to it is described be used for controlling it is Jing Yin/release Jing Yin instruction, to department of computer scienceThe volume that system plays audio carries out Jing Yin/Jing Yin control of releasing；When the instruction of identified audio frequency control is for suspending/continuing to broadcastDuring the instruction put, it is used for controlling the instruction for suspending/continuing and play according to described, control computer system audio, which suspends/continued, to be broadcastPut.
Further, the corresponding relation between user speech intensity and volume can also be set, so, in Mike's battle arrayWhile row obtain voice flow, user speech intensity is determined, and is based on user speech intensity, current volume is rationally adjustedSection.
The embodiment provided by Fig. 1 and Fig. 2, the present invention are playing in itself firstly the need of isolation difference computerAudio sound, such as Mp3 music and Movie.If the sound met is occurred in the audio program that computer is playing in itselfInstruction, Hello/ when such as making a phone call feeds/your good usual instructions, then it must be isolated, because this phonetic control command is notIt is the instruction that current user sends.The mode of being specifically isolated is：Utilize echo cancellation technology algorithm (Acoustic echocancelLation, AEC), after Mike collects sound, sound number that the sound that local loudspeaker plays back is gathered from MikeEliminated in so that the sound that Mike records only has local user's one's voice in speech, this function can by software algorithm orCodec chip hardware is realized.Next needs to suppress ambient noise interference, only voice needed for pickup.The present invention utilizes numberBeam forming (Beam forming) technology of word microphone, digital microphone array can be combined as required highly directiveMicrophone, microphone signal control via special circuit or programmed algorithm software, it is pointed to Sounnd source direction and is strengthened audio and adoptCollect effect, only receive the sound of user, while suppress the ambient noise of surrounding environment.For example, if external environment is playingFilm, or the sound for there are other people to answer the call, sound condition can be sized or this environment is shielded by special angleNoise, audio needed for acquisition.Finally, using required audio, speech recognition controlled is carried out.
Fig. 3 is the audio frequency control flow chart of adaptive external environment provided in an embodiment of the present invention, as shown in figure 3, stepIncluding：
Step S301：Start the audio frequency control function of adaptive external environment.
Step S302：Collect phonetic control command.
Step S303：By phonetic control command and the audio frequency control instruction input speech recognition controlled software of corresponding response(ASR) instruction database, is assembled.
Step S304：Typing phonetic control command.
Step 305：The phonetic control command of judgment step S304 typings whether with the voice control in step S303 instruction databasesInstructions match processed, if matching, step S306 is performed, otherwise performs step S307.
Step S306：Logic control is carried out, carries out corresponding response.
Specifically, if the phonetic control command of step S304 typings and the phonetic control command in step S303 instruction databasesMatching, determine that audio frequency control corresponding to the phonetic control command in step S303 instruction databases instructs, and according to the audio frequency controlInstruction, is operated accordingly.
Step S307：It is failure to actuate.
Specifically, if the phonetic control command of step S304 typings and the phonetic control command in step S303 instruction databasesMismatch, then without any response.
It can be seen that the present invention can carry out audio frequency control according to user's service condition, such as user is using notebook computerIn product process, telephone bell sounds, and when Mike's identification meets the audio zone of condition, volume control chip adjusts the sound of loudspeakerAmount, to utilize the communication at family.
Although the present invention is described in detail above, the invention is not restricted to this, those skilled in the art of the present techniqueVarious modifications can be carried out according to the principle of the present invention.Therefore, all modifications made according to the principle of the invention, all should be understood toFall into protection scope of the present invention.