Summary of the invention
This application provides a kind of sound control method, device, equipment and storage medium, a kind of meet various make to provideWith the control mode of the smart home of the requirement of habit.
In a first aspect, providing a kind of sound control method, it to be used for smart home system, comprising:
The control command of phonetic order to be collected is exported, the way of output of the control command is that sound exports or picture and text are defeatedOut, the control command is used to control the operating status of one or more smart home devices；
Described instruction audio is associated with preservation with the control command by acquisition instructions audio；
The control audio is carried out waveform with described instruction audio and compared by the acquisition control audio under control model；
If being compared from described instruction audio and obtaining target instruction target word audio, the associated control of the target instruction target word audio is orderedOrder is sent to corresponding smart home device, and the target instruction target word audio and the similarity of the waveform of the control audio reach pre-If targets threshold.
Wherein, before the control command of the output phonetic order to be collected, further includes:
Receive the instruction for entering phonetic order acquisition mode.
Wherein, described instruction audio is associated with preservation with the control command by the acquisition instructions audio, comprising:
Multiple instruction audio is acquired, is acquired prompting before each described instruction audio collection；
Instruction acquisition END instruction is received, the multiple instruction audio is associated with preservation with the control command.
Wherein, described receive enters after the instruction of phonetic order acquisition mode, the output phonetic order to be collectedBefore control command, further includes:
Export the acquisition requirement of described instruction audio.
Wherein, the acquisition requires to include: the prompt before the length restriction of each instruction audio, each instruction audio collectionAt least one of the confirmation operation terminated with instruction acquisition.
Second aspect is used for smart home system using a kind of phonetic controller, comprising:
Order output unit, for exporting the control command of phonetic order to be collected, the way of output of the control commandIt is used to control the operating status of one or more smart home devices for sound output or picture and text output, the control command；
Instruction acquisition unit is used for acquisition instructions audio, described instruction audio is associated with preservation with the control command；
Comparing unit is acquired, for the acquisition control audio under control model, by the control audio and described instruction soundFrequency carries out waveform comparison；
Control response unit refers to the target if obtaining target instruction target word audio for comparing from described instruction audioThe associated control command of audio is enabled to be sent to corresponding smart home device, the target instruction target word audio and the control audioThe similarity of waveform reaches preset targets threshold.
Wherein, the phonetic controller, further includes:
Instruction receiving unit, for receiving the instruction for entering phonetic order acquisition mode.
Wherein, described instruction acquisition unit, comprising:
It acquires reminding module and is acquired prompting before each described instruction audio collection for acquiring multiple instruction audio；
Terminate preserving module, for receiving instruction acquisition END instruction, the multiple instruction audio and the control are orderedAssociation is enabled to save.
Wherein, the phonetic controller, further includes:
It is required that output unit, for exporting the acquisition requirement of described instruction audio.
Wherein, the acquisition requires to include: the prompt before the length restriction of each instruction audio, each instruction audio collectionAt least one of the confirmation operation terminated with instruction acquisition.
The third aspect provides a kind of equipment, comprising: one or more processors；
Memory, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processingDevice realizes the sound control method as described in any in first aspect.
Fourth aspect provides a kind of storage medium comprising computer executable instructions, the computer executable instructionsWhen being executed by computer processor for executing the sound control method as described in any in first aspect.
The embodiment of the present application passes through the control command for exporting phonetic order to be collected, and the way of output of the control command isSound output or picture and text output, the control command are used to control the operating status of one or more smart home devices；AcquisitionAudio is instructed, described instruction audio is associated with preservation with the control command；The acquisition control audio under control model, will be describedControl audio carries out waveform with described instruction audio and compares；It, will if being compared from described instruction audio and obtaining target instruction target word audioThe associated control command of target instruction target word audio is sent to corresponding smart home device, the target instruction target word audio with it is describedThe similarity for controlling the waveform of audio reaches preset targets threshold.Pass through the corresponding audio number of the control command of customized insideThe corresponding control command of confirmation user speech is controlled by acoustic ratio according to when, control, realizes all ages and classes and differenceRegion user facilitates control to smart home device.
Specific embodiment
It is specifically real to the application with reference to the accompanying drawing in order to keep the purposes, technical schemes and advantages of the application clearerExample is applied to be described in further detail.It is understood that specific embodiment described herein is used only for explaining the application,Rather than the restriction to the application.It also should be noted that illustrating only for ease of description, in attached drawing related to the applicationPart rather than full content.It should be mentioned that some exemplary realities before exemplary embodiment is discussed in greater detailIt applies example and is described as the processing or method described as flow chart.Although operations (or step) are described as sequence by flow chartProcessing, but many of these operations can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of operationsIt can be rearranged.The processing can be terminated when its operations are completed, be not included in attached drawing it is also possible to haveAdditional step.The processing can correspond to method, function, regulation, subroutine, subprogram etc..
Fig. 1 is a kind of flow chart of sound control method provided by the embodiments of the present application, voice control provided in this embodimentMethod processed can be executed by phonetic controller, which can be realized by way of hardware and/or software, andIt integrates in a device.Specifically, the equipment in the present embodiment refers to that the control that user is held is whole in Intelligent housing systemEnd can be mobile phone, tablet computer, the laptop etc. for being equipped with control application, be also possible to Intelligent housing systemIncluded controlling terminal.Regardless of the carrier realized, the realization process of specific sound control method is identical.It, should with reference to Fig. 1Sound control method specifically includes:
Step S110: the control command of phonetic order to be collected is exported.
In the control system of smart home, the smart home device controlled is more, needs to Intelligent targetHome equipment carries out accurately control and usually requires certain character learning basis, and for advanced age and low age user, character learningBasis is usually weaker.If existing voice control scheme is typically only capable to identify a few official using voice controlLanguage for users of advanced age that is nonstandard for many mandarins or never speaking standard Chinese pronunciation, can only at most be understood commonWords, but can not accurately say, also result in voice control that can not be accurately controlled substantially.
In the present solution, carrying out voice control otherwise by a kind of non-legible knowledge, it is only necessary to which acquisition is used as referencePhonetic order.Before acquiring phonetic order, current control command to be collected can be exported, can specifically be had to control eventuallyThe control command at end is more the control command to various smart home devices (such as air-conditioning, TV, electric light).It is wherein rightThe control command of controlling terminal mainly chooses some smart home device.The way of output of control command is that sound exports or schemesText output, the control command are used to control the operating status of one or more smart home devices, and output described here isIt is exported to user, rather than as some smart home device exports.Such as user is prompted to say one by way of sound or picture and textDuan Yuyin expression is " choosing air-conditioning " to the order of controlling terminal, then prompts user to say one by way of sound or picture and text againDuan Yuyin indicates it is " temperature is turned up " to the order of air-conditioning.
Step S120: described instruction audio is associated with preservation with the control command by acquisition instructions audio.
The acquisition of audio is instructed to complete by voice capture device, voice capture device such as sound pick-up and microphone.It picks upSound device is integrated with advanced noise processed, echo processing and length away from transmission driving circuit, is verily remembered with the sound quality of high-fidelityRecord and reduction scene.Microphone (referred to as microphone) is a kind of energy converter for converting tones into electronic signal merely, usuallyWhat is oriented is muting sensitive, can just play desired sound collection effect in the generation of close range-aligned.But it can be realSound collection demand needed for now controlling smart home device.
After the completion of instructing audio collection, collected instruction audio is closed in controlling terminal with corresponding control commandUNPROFOR is deposited.Because not being related to the identification from voice to text in this programme, instruction audio can be dialect, it might even be possible to be to be not intended toThe sounding content that the user oneself that justice can still be set remembers.
Step S130: the control audio and described instruction audio are carried out wave by the acquisition control audio under control modelShape compares.
Acquisition control audio can there are many specific operating process under control model, such as choose some intelligence firstThen home equipment acquires specific control audio again to control the smart home device.Instruction corresponding to frontThe collection process of audio chooses the process of smart home device that can also realize by voice control, it is of course also possible to controllingBy manual operation selection target smart home device in terminal, voice control then is carried out to Intelligent target home equipment.OutControl to single intelligentized Furniture equipment, can also be arranged the instruction audio controlled multiple smart home devices, exampleSuch as set an instruction audio for sleep before, can the needs such as disposable closing television, electric light, water heater closed before sleepingSmart home device.The comparison of wave shape of sound is the routine operation in audio data treatment process, and this will not be repeated here.
Step S140: target instruction target word audio is obtained if comparing from described instruction audio, the target instruction target word audio is closedThe control command of connection is sent to corresponding smart home device.
Middle voice control is to go out text from speech recognition compared with the existing technology, is then controlled according to word content.Relatively easy and more effective processing mode is used in this programme, generally speaking, only establishes an instruction audio as referenceBeing associated between control command, but there is no a necessarily relationships between specifying information or content therebetween, are controllingCollected user speech (i.e. control audio), not will do it accurate Text region, as long as confirmation is collected during systemThe similarity of user speech and the waveform of some the instruction audio saved reaches targets threshold, that is, confirms that the user speech is effective,The associated control command of corresponding instruction audio is obtained, then sends corresponding smart home device for the control command, etc.Response to smart home device.Specific targets threshold such as 90%, 95%.
In conclusion control command of the embodiment of the present application by output phonetic order to be collected, the control commandThe way of output is that sound exports or picture and text output, the control command are used to control the operation of one or more smart home devicesState；Described instruction audio is associated with preservation with the control command by acquisition instructions audio；The acquisition control sound under control modelFrequently, the control audio waveform is carried out with described instruction audio to compare；Refer to if being compared from described instruction audio and obtaining targetAudio is enabled, sends corresponding smart home device, the target instruction target word for the associated control command of target instruction target word audioThe similarity of the waveform of audio and the control audio reaches preset targets threshold.Pass through the control command pair of customized insideThe audio data answered controls confirmation user speech corresponding control command by acoustic ratio when control, realizes differenceAge and different geographical user facilitate control to smart home device.
On the basis of the above embodiments, Fig. 2 gives the stream of another sound control method provided by the embodiments of the present applicationCheng Tu.The sound control method is further realized in detail to above-mentioned sound control method.With reference to Fig. 2, the sound control method,Include:
Step S210: the instruction for entering phonetic order acquisition mode is received.
Phonetic order acquisition mode needs to carry out operation realization to controlling terminal, can specifically operate in controlling terminalThe key or key combination set, if it is the controlling terminal with touch display screen, can operation carry out touch control operation intoEnter phonetic order acquisition mode.
Step S220: the acquisition requirement of output described instruction audio.
To guarantee that collected audio data is succinctly effective in specific collection process, needs to remind before being acquiredUser carries out the points for attention before phonetic order setting, such as the length of each instruction audio limits, each instruction audio collectionAt least one of the confirmation operation that preceding prompt and instruction acquisition terminates.Specifically, each instruction audio is limited to be no more thanHow many a words or how long；Multiple instruction audio is acquired if it is a control command, when can be inputted nextInstruct audio；Any operation acknowledgement instruction acquisition terminates (not collecting the end of voice default for a period of time or user is manualConfirmation technology).
Step S230: the control command of phonetic order to be collected is exported.
The way of output of the control command be sound export or picture and text output, the control command for control one orThe operating status of multiple smart home devices.Multiple smart home devices that can be all, such as can control entire intelligent familyThe system of residence is restarted more new system or test network.
Step S240: multiple instruction audio is acquired, is acquired prompting before each described instruction audio collection.
Step S250: instruction acquisition END instruction is received, the multiple instruction audio is associated with guarantor with the control commandIt deposits.
Different users may have different operating habits to the same operation, can save at this time to each control commandMultiple instruction audio.There can be simple onomatopoeia pronunciation to remind (such as " stining ") before each instruction audio collection, be also possible to brightTrue voice reminder (such as " next instruction audio please be input ").
Step S260: the control audio and described instruction audio are carried out wave by the acquisition control audio under control modelShape compares.
Step S270: target instruction target word audio is obtained if comparing from described instruction audio, the target instruction target word audio is closedThe control command of connection is sent to corresponding smart home device.
The similarity of the waveform of the target instruction target word audio and the control audio reaches preset targets threshold.
In the present embodiment, by the further materialization to instruction acquisition process, it is richer to realize instruction acquisition processRich operation can satisfy the demand of the user speech control smart home device of various types and different geographical.
On the basis of the above embodiments, Fig. 3 is that a kind of structure of phonetic controller provided by the embodiments of the present application is shownIt is intended to.With reference to Fig. 3, phonetic controller provided in this embodiment, comprising: order output unit 310, instruction acquisition unit 320,Acquire comparing unit 330 and control response unit 340.Wherein:
Order output unit 310, for exporting the control command of phonetic order to be collected, the output side of the control commandFormula is that sound exports or picture and text output, the control command are used to control the operating status of one or more smart home devices；
Instruction acquisition unit 320 is used for acquisition instructions audio, described instruction audio is associated with guarantor with the control commandIt deposits；
Comparing unit 330 is acquired, for the acquisition control audio under control model, by the control audio and described instructionAudio carries out waveform comparison；
Control response unit 340, if target instruction target word audio is obtained for comparing from described instruction audio, by the targetThe instruction associated control command of audio is sent to corresponding smart home device, the target instruction target word audio and the control audioThe similarity of waveform reach preset targets threshold.
Further, the phonetic controller, further includes:
Instruction receiving unit, for receiving the instruction for entering phonetic order acquisition mode.
Further, described instruction acquisition unit 320, comprising:
It acquires reminding module and is acquired prompting before each described instruction audio collection for acquiring multiple instruction audio；
Terminate preserving module, for receiving instruction acquisition END instruction, the multiple instruction audio and the control are orderedAssociation is enabled to save.
Further, the phonetic controller, further includes:
It is required that output unit, for exporting the acquisition requirement of described instruction audio.
Further, the acquisition requires to include: the length of each instruction audio limits, before each instruction audio collectionAt least one of the confirmation operation that prompt and instruction acquisition terminate.
In conclusion above-mentioned each unit cooperates, by exporting the control command of phonetic order to be collected, the controlThe way of output of order is that sound exports or picture and text output, the control command are used to control one or more smart home devicesOperating status；Described instruction audio is associated with preservation with the control command by acquisition instructions audio；It is acquired under control modelAudio is controlled, the control audio is subjected to waveform with described instruction audio and is compared；It is obtained if being compared from described instruction audioThe associated control command of target instruction target word audio is sent corresponding smart home device, the mesh by target instruction target word audioThe similarity of the waveform of mark instruction audio and the control audio reaches preset targets threshold.Pass through the control of customized insideOrder corresponding audio data, when control controls the corresponding control command of confirmation user speech by acoustic ratio, realizesAll ages and classes and different geographical user to smart home device facilitate control.Meanwhile by instruction acquisition process intoOne step embodies, and realizes the richer operation of instruction acquisition process, can satisfy the use of various types and different geographicalThe demand of family voice control smart home device.
The embodiment of the present application provides a kind of equipment, and voice control dress provided by the embodiments of the present application can be integrated in the equipmentIt sets.Fig. 4 is a kind of structural schematic diagram of equipment provided by the embodiments of the present application.With reference to Fig. 4, the equipment include: processor 410,Memory 420, input unit 430, output device 440 and communication device 450.The quantity of processor 410 can be in the equipmentIt is one or more, in Fig. 4 by taking a processor 410 as an example.In the equipment quantity of memory 420 can be one orIt is multiple, in Fig. 4 by taking a memory 420 as an example.Processor 410, memory 420, input unit 430, the output dress of the equipmentSet 440 and communication device 450 can be connected by bus or other modes, in Fig. 4 for through bus connection.
Memory 420 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computerSequence and module, the corresponding program instruction/module of sound control method as described in the application any embodiment is (for example, voiceOrder output unit 310, instruction acquisition unit 320, acquisition comparing unit 330 and control response unit in control device340).Memory 420 can mainly include storing program area and storage data area, wherein storing program area can storage program area,Application program needed at least one function；Storage data area, which can be stored, uses created data etc. according to equipment.In addition,Memory 420 may include high-speed random access memory, can also include nonvolatile memory, for example, at least a diskMemory device, flush memory device or other non-volatile solid state memory parts.In some instances, memory 420 can be wrapped furtherThe memory remotely located relative to processor 410 is included, these remote memories can pass through network connection to equipment.Above-mentioned netThe example of network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Communication device 450 is for any data communication mode (preferably wirelessly) and other smart home devicesCarry out network connection and data transmission.Communication device 450 is not to refer in particular to a kind of corresponding hardware module of communication mode and its driving,But including can be disposed at communication in equipment, such as Wi F i module, bluetooth module and infrared module etc..
Input unit 430 can be used for receiving the number of input perhaps character information or operational order, in the present solution,It especially include carrying out the operation module and the audio collection module for carrying out sound collection that user manually controls.Output device 440 canTo include loudspeaker, display screen etc..It should be noted that the concrete composition of input unit 430 and output device 440 can basisActual conditions setting, such as it is respectively set to keyboard and display screen, or be wholely set as touch display screen.It is understood thatIt is that in practical application, the equipment is there are also conventional components needed for other realization normal functions, such as power module etc..
Software program, instruction and the module that processor 410 is stored in memory 420 by operation, thereby executing settingStandby various function application and data processing, that is, realize above-mentioned sound control method.
The equipment of above-mentioned offer can be used for executing sound control method provided by the above embodiment, have corresponding function andBeneficial effect.
The embodiment of the present application also provides a kind of storage medium comprising computer executable instructions, and the computer is executableInstruction when being executed by computer processor for executing a kind of sound control method, the sound control method include: output toThe control command of phonetic order is acquired, the way of output of the control command is that sound exports or picture and text output, the control are orderedEnable the operating status for controlling one or more smart home devices；Acquisition instructions audio, by described instruction audio with it is describedControl command association saves；The control audio and described instruction audio are carried out wave by the acquisition control audio under control modelShape compares；If being compared from described instruction audio and obtaining target instruction target word audio, the associated control of the target instruction target word audio is orderedOrder is sent to corresponding smart home device, and the target instruction target word audio and the similarity of the waveform of the control audio reach pre-If targets threshold.
Storage medium --- any various types of memory devices or storage equipment.Term " storage medium " is intended to wrapIt includes: install medium, such as CD-ROM, floppy disk or magnetic tape equipment；Computer system memory or random access memory, such asDRAM, DDR RAM, SRAM, EDO RAM, blue Bath (Rambus) RAM etc.；Nonvolatile memory, such as flash memory, magnetic medium(such as hard disk or optical storage)；Register or the memory component of other similar types etc..Storage medium can further include otherMemory of type or combinations thereof.In addition, storage medium can be located at program in the first computer system being wherein performed,Or can be located in different second computer systems, second computer system is connected to the by network (such as internet)One computer system.Second computer system can provide program instruction to the first computer for executing." storage is situated between termMatter " may include may reside in different location (such as by network connection different computer systems in) two orMore storage mediums.Storage medium can store the program instruction that can be performed by one or more processors and (such as implementFor computer program).
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present applicationVoice provided by the application any embodiment can also be performed in the sound control method that executable instruction is not limited to the described aboveRelevant operation in control method.
The application any embodiment institute can be performed in phonetic controller, storage medium and the equipment provided in above-described embodimentThe sound control method of offer, the not technical detail of detailed description in the above-described embodiments, reference can be made to the application any embodimentProvided sound control method.
Note that above are only the preferred embodiment and institute's application technology principle of the application.It will be appreciated by those skilled in the art thatThe application is not limited to specific embodiment described here, be able to carry out for a person skilled in the art it is various it is apparent variation,The protection scope readjusted and substituted without departing from the application.Therefore, although being carried out by above embodiments to the applicationIt is described in further detail, but the application is not limited only to above embodiments, in the case where not departing from the application design, alsoIt may include more other equivalent embodiments, and scope of the present application is determined by the scope of the appended claims.