Content of the invention
The embodiment of the present invention provides a kind of control method, for solution because the operability of electronic equipment is poorAnd lead to the relatively low technical problem of the accuracy when line activating is entered to speech recognition engine.
In a first aspect, providing a kind of control method, comprising:
When the voice collecting unit of electronic equipment is in the first working condition, gathered by image acquisition unitsFirst gesture information；Wherein, described first working condition is: described voice collecting forbidden by described electronic equipmentThe state that unit is responded to voice command；
Based on described first gesture information, control the working condition of described voice collecting unit by described firstWorking condition switches to the second working condition；Wherein, described second working condition is: described electronic equipment is permittedPermitted the state that described voice collecting unit is responded to voice command.
Optionally, in the embodiment of the present invention, based on described first gesture information, control described voice collectingThe working condition of unit switches to the second working condition by described first working condition, comprising:
Judge whether described first gesture information is mated with the first default gesture information；
If mating with the described first default gesture information, controlling and described working condition is worked by described firstState switches to described second working condition.
Optionally, in the embodiment of the present invention, controlling, described working condition is cut by described first working conditionAfter being changed to described second working condition, methods described also includes:
Under described second working condition, gathered by described voice collecting unit and obtain voice messaging；
According to described voice messaging, determine corresponding voice control command；
Respond described voice control command, to control described electronic equipment to realize corresponding voice control function.
Optionally, in the embodiment of the present invention, according to described voice messaging, determine corresponding voice control command,Including:
According to described voice messaging, determine at least one voiceprint corresponding with described voice messaging；
Determine the first voiceprint from described at least one voiceprint；Wherein, described first voiceprintIt is the voiceprint matching with default voiceprint；
First voice messaging corresponding with described first voiceprint is determined from described voice messaging；
According to described first voice messaging, determine corresponding voice control command.
Optionally, in the embodiment of the present invention, controlling, described working condition is cut by described first working conditionAfter being changed to described second working condition, methods described also includes:
Determine that the gesture information that described image collecting unit gathers is second by described first gesture information changeGesture information；
Control and described working condition is switched to described first working condition by described second working condition.
Optionally, in the embodiment of the present invention, control described working condition by described second working condition switchingFor described first working condition, comprising:
Optionally, in the embodiment of the present invention, judge whether the described first information meets pre-conditioned, comprising:
Judge whether described second gesture information is matched with the second default gesture information；
If mating with the described second default gesture information, controlling and described working condition is worked by described secondState switches to described first working condition.
Optionally, in the embodiment of the present invention, controlling, described working condition is cut by described first working conditionAfter being changed to described second working condition, methods described also includes:
Determine that described image collecting unit collects threeth gesture informations different from described first gesture information；
Control and described working condition is switched to and described first working condition by described second working condition.
Second aspect, provides the first electronic equipment, comprising:
Voice acquisition device, for gathering voice messaging；
Image collecting device, for gathering image information；
Processor, is connected with described voice acquisition device and described image harvester, respectively for working as voiceWhen harvester is in the first working condition, control described image harvester collection first gesture information；WithAnd it is based on described first gesture information, control the working condition of described voice acquisition device by described first workSwitch to the second working condition as state；Wherein, described first working condition is: described electronic equipment is forbiddenThe state that described voice acquisition device is responded to voice command, described second working condition is: described electricitySub- equipment allows the state that described voice acquisition device is responded to voice command.
Optionally, in the embodiment of the present invention, described processor is used for:
Judge whether described first gesture information is mated with the first default gesture information；
If mating with the described first default gesture information, controlling and described working condition is worked by described firstState switches to described second working condition.
Optionally, in the embodiment of the present invention, described processor is additionally operable to:
Control by described working condition by described first working condition switch to described second working condition itAfterwards, under described second working condition, described voice acquisition device collection is controlled to obtain voice messaging；
According to described voice messaging, determine corresponding voice control command；
Respond described voice control command, to control described electronic equipment to realize corresponding voice control function.
Optionally, in the embodiment of the present invention, described processor is used for:
According to described voice messaging, determine at least one voiceprint corresponding with described voice messaging；
Determine the first voiceprint from described at least one voiceprint；Wherein, described first voiceprintIt is the voiceprint matching with default voiceprint；
First voice messaging corresponding with described first voiceprint is determined from described voice messaging；
According to described first voice messaging, determine corresponding voice control command.
Optionally, in the embodiment of the present invention, described processor is additionally operable to:
Control by described working condition by described first working condition switch to described second working condition itAfterwards, determine that the gesture information that described image harvester gathers is second-hand by described first gesture information changeGesture information；
Control and described working condition is switched to described first working condition by described second working condition.
Optionally, in the embodiment of the present invention, described processor is used for:
Judge whether described second gesture information is matched with the second default gesture information；
If mating with the described second default gesture information, controlling and described working condition is worked by described secondState switches to described first working condition.
Optionally, in the embodiment of the present invention, described processor is additionally operable to:
Control by described working condition by described first working condition switch to described second working condition itAfterwards, determine that described image harvester collects threeth gesture informations different from described first gesture information；
Control and described working condition is switched to and described first working condition by described second working condition.
The third aspect, provides second electronic equipment, comprising:
Acquisition module, for when the voice collecting unit of electronic equipment is in the first working condition, by figureAs collecting unit gathers first gesture information；Wherein, described first working condition is: described electronic equipment is prohibitedThe state that only described voice collecting unit is responded to voice command；
Processing module, for based on described first gesture information, controlling the work of described voice collecting unitState switches to the second working condition by described first working condition；Wherein, described second working condition is:Described electronic equipment allows the state that described voice collecting unit is responded to voice command.
In the embodiment of the present invention, when the voice collecting unit of electronic equipment is in the first working condition, that is, whenWhen voice collecting unit is in backstage listening state, gathered first-hand by the image acquisition units of electronic equipmentGesture information, and then it is based on first gesture information again, control the working condition of voice collecting unit by the first workSwitch to the second working condition as state, that is, control voice collecting unit is switched to by backstage listening state rightThe state that voice command is responded is that is to say, that in the embodiment of the present invention, can be realized by gestureActivation to speech recognition engine, electronic equipment has provided the user a kind of new speech recognition engine activation mouldFormula, enhances electronic equipment operability and multifunctionality, such that it is able to strengthen the experience of user.
Because existing electronic equipment is typically equipped with pixel, higher camera (is equivalent to IMAQ listUnit), it is possible to collecting clearly images of gestures information, i.e. the gesture that electronic equipment is made to userThere is higher identification, then just exactly line activating can be entered to speech recognition engine, such that it is able to carryHigh accuracy, in time speech recognition engine to be entered with line activating, saves the time that is to say, that passing through profitWith hardware configuration existing in electronic equipment, just speech recognition engine accurately and efficiently can be activated,The efficiency that electronic equipment is processed to information can be improved further, strengthen the performance of electronic equipment.
In addition, for a user, carry out that gesture operation is fairly simple, also compare be close to the users using practisingUsed.Meanwhile, user can carry out gesture operation apart from the place of electronic equipment certain distance, as long as imageCollecting unit can collect images of gestures information just can, and without walking close to electronic equipment, user is carried outThe flexibility of gesture operation is larger.And, can also reduce for peripheral hardware hardware device (such as mouse or keyDisk) dependence, enhance the independence of electronic equipment, decrease the step that user is operated manually.
Specific embodiment
The embodiment of the present invention provides a kind of control method, comprising: when the voice collecting unit of electronic equipment is inDuring the first working condition, gather first gesture information by image acquisition units；Wherein, described first workState is: the state that described voice collecting unit is responded forbidden to voice command by described electronic equipment；BaseIn described first gesture information, control the working condition of described voice collecting unit by the described first work shapeState switches to the second working condition；Wherein, described second working condition is: described electronic equipment allows describedThe state that voice collecting unit is responded to voice command.
In the embodiment of the present invention, when the voice collecting unit of electronic equipment is in the first working condition, that is, whenWhen voice collecting unit is in backstage listening state, gathered first-hand by the image acquisition units of electronic equipmentGesture information, and then it is based on first gesture information again, control the working condition of voice collecting unit by the first workSwitch to the second working condition as state, that is, control voice collecting unit is switched to by backstage listening state rightThe state that voice command is responded is that is to say, that in the embodiment of the present invention, can be realized by gestureActivation to speech recognition engine, electronic equipment has provided the user a kind of new speech recognition engine activation mouldFormula, enhances electronic equipment operability and multifunctionality, such that it is able to strengthen the experience of user.
Because existing electronic equipment is typically equipped with pixel, higher camera (is equivalent to IMAQ listUnit), it is possible to collecting clearly images of gestures information, i.e. the gesture that electronic equipment is made to userThere is higher identification, then just exactly line activating can be entered to speech recognition engine, such that it is able to carryHigh accuracy, in time speech recognition engine to be entered with line activating, saves the time that is to say, that passing through profitWith hardware configuration existing in electronic equipment, just speech recognition engine accurately and efficiently can be activated,The efficiency that electronic equipment is processed to information can be improved further, strengthen the performance of electronic equipment.
In addition, for a user, carry out that gesture operation is fairly simple, also compare be close to the users using practisingUsed.Meanwhile, user can carry out gesture operation apart from the place of electronic equipment certain distance, as long as imageCollecting unit can collect images of gestures information just can, and without walking close to electronic equipment, user is carried outThe flexibility of gesture operation is larger.And, can also reduce for peripheral hardware hardware device (such as mouse or keyDisk) dependence, enhance the independence of electronic equipment, decrease the step that user is operated manually.
For making the object, technical solutions and advantages of the present invention become more apparent, real below in conjunction with the present inventionApply the accompanying drawing in example, the technical scheme in the embodiment of the present invention is clearly and completely described it is clear thatDescribed embodiment is only a part of embodiment of the present invention, rather than whole embodiments.Based on thisEmbodiment in bright, the institute that those of ordinary skill in the art are obtained under the premise of not making creative workThere is other embodiment, broadly fall into the scope of protection of the invention.Reality in the case of not conflicting, in the present inventionApply the feature in example and embodiment can mutually be combined.And although show logic in flow chartsSequentially, but in some cases, can be with the step shown or described different from order execution herein.
In the embodiment of the present invention, electronic equipment may refer to mobile phone, pad (panel computer), notebook electricityBrain, pc (personal computer, PC) etc. different electronic equipment, for electronic equipmentSpecifically which type of equipment present invention is not limited, if electronic equipment have simultaneously voice collecting unit andImage acquisition units.
In order to be better understood from technique scheme, below in conjunction with Figure of description and specific embodiment partyFormula is described in detail to technique scheme.
Refer to Fig. 1, the embodiment of the present invention provides a kind of control method, the controlling party in the embodiment of the present inventionMethod can apply to electronic equipment, i.e. in this information processing method, the executive agent of each step can be electronicsEquipment.The main flow of the method is described as follows.
Step 101: when the voice collecting unit of electronic equipment is in the first working condition, adopted by imageCollection unit collection first gesture information；Wherein, the first working condition is: voice collecting list forbidden by electronic equipmentThe state that unit is responded to voice command.
Wherein, voice collecting unit may refer to microphone, such as head microphone or table microphone etc.The external microphone of electronic equipment, or may also mean that the built-in microphone of electronic equipment, voice is adoptedThe particular type of collection unit is not limited, as long as it can gather voice messaging.
Image acquisition units may refer to camera, for example, can be the external camera of electronic equipment, orMay also mean that the camera module of electronic equipment itself, the present invention is not limited, as long as it can gather figureAs information.
In the embodiment of the present invention, the first working condition of voice collecting unit refers to that electronic equipment forbids that voice is adoptedThe state that collection unit is responded to voice command, or it is to be understood that the first working condition is finger speechSound collecting unit processes backstage and monitors but voice command will not be responded state is it can be understood as voiceThe resting state of collecting unit, if necessary to responding to voice command, then need ad hoc fashion pair withThe corresponding speech recognition engine of voice collecting unit enters line activating.
First gesture information, specifically refers to first gesture image information, is first-hand with what user was carried outImage information corresponding to gesture.Because first gesture information is to be gathered by image acquisition units to obtain, so,The gesture ability being only located in the fov (field of view, camera lens field range) of image acquisition unitsCollected by image acquisition units, so, user, when carrying out gesture operation, needs clear and definite IMAQ listThe fov of unit, certainly, for the image acquisition units of distinct electronic apparatuses, corresponding fov is usually notThe same, user may be referred to corresponding operation instructions in actual use.
Step 102: based on first gesture information, control the working condition of voice collecting unit by the first workSwitch to the second working condition as state；Wherein, described second working condition is: electronic equipment allows voiceThe state that collecting unit is responded to voice command.
After collecting first gesture information, electronic equipment can carry out dissection process to first gesture, entersAnd to control the working condition of switching voice collecting unit further according to the first gesture information after dissection process.
Wherein, the second working condition is the state allowing voice collecting unit that voice command is responded, that, the working condition of voice collecting unit is switched to the second working condition by the first working condition, is equivalent toExactly speech recognition engine is entered with line activating process that is to say, that in the embodiment of the present invention, can be according to theOne gesture information enters line activating to control to speech recognition engine, and electronic equipment has provided the user a kind of newThe activation pattern of speech recognition engine, enhances electronic equipment operability and multifunctionality, and then can increaseThe experience of strong user.
Because existing electronic equipment is typically equipped with pixel, higher camera (is equivalent to IMAQ listUnit), it is possible to collecting clearly images of gestures information, i.e. the gesture that electronic equipment is made to userThere is higher identification, then just exactly line activating can be entered to speech recognition engine, such that it is able to carryHigh accuracy, in time speech recognition engine to be entered with line activating, saves the time that is to say, that passing through profitWith hardware configuration existing in electronic equipment, just speech recognition engine accurately and efficiently can be activated,The efficiency that electronic equipment is processed to information can be improved further, strengthen the performance of electronic equipment.
In addition, for a user, carry out that gesture operation is fairly simple, also compare be close to the users using practisingUsed.Meanwhile, user can carry out gesture operation apart from the place of electronic equipment certain distance, as long as imageCollecting unit can collect images of gestures information just can, and without walking close to electronic equipment, user is carried outThe flexibility of gesture operation is larger.And, can also reduce for peripheral hardware hardware device (such as mouse or keyDisk) dependence, enhance the independence of electronic equipment, decrease the step that user is operated manually
In addition, in specific implementation process, user may carry out multiple in the fov of image acquisition unitsGesture, then, in order to avoid electronic equipment that the mistake of gesture is responded as far as possible, according to first gesture information pairBefore speech recognition engine enters line activating, can first first gesture information be judged.That is:
Optionally, in the embodiment of the present invention, based on first gesture information, control the work of voice collecting unitMake state and the second working condition switched to by the first working condition, comprising:
Judge whether first gesture information is mated with the first default gesture information；
If mating with the first default gesture information, controlling and working condition is switched to the by the first working conditionTwo working conditions.
Wherein, the first default gesture information is and the first default corresponding information of gesture, specifically can according toThe different of family require setting, and for example, the first default gesture is " v " type gesture, then, collecting theAfter one gesture information, first gesture information can be judged with whether the first default gesture information mates,Only when first gesture information is matched with the first default gesture information, just can be believed according to first gestureBreath realizes the activation to speech recognition engine, to strengthen the purpose of activation as far as possible.
That is, when determining that first gesture information is mated with the first default gesture information, showing first-handThe certain gestures that gesture sets for user, when user carries out certain gestures, just show that user's expectation is known to voiceOther engine enters line activating, is the reality with user by the response that such mode can ensure electronic equipment as far as possibleBorder use demand is consistent, and avoids responding as far as possible by mistake, is also possible to prevent not know other of certain gestures simultaneouslyUser uses the voice control function of electronic equipment, it is to avoid the information leakage of electronic equipment, strengthens privacy.
Optionally, in the embodiment of the present invention, controlling, working condition is switched to second by the first working conditionAfter working condition, methods described also includes:
In a second operative state, gathered by voice collecting unit and obtain voice messaging；
According to voice messaging, determine corresponding voice control command；
Voice responsive control command, realizes corresponding voice control function with control electronics.
That is, after the working condition of control voice collecting unit switches to the second working condition, that is, show languageSound identification engine has been activated, and voice collecting unit can respond to the real-time voice order of user,To realize voice control function, manually operated such that it is able to be replaced by Voice command, improve operating efficiency,Operation enjoyment can also be improved for user, strengthen the experience of user.
Optionally, in the embodiment of the present invention, according to voice messaging, determine corresponding voice control command, bagInclude:
According to voice messaging, determine at least one voiceprint corresponding with voice messaging；
The first voiceprint is determined from least one voiceprint；Wherein, the first voiceprint is and presetsThe voiceprint that voiceprint matches；
First voice messaging corresponding with the first voiceprint is determined from voice messaging；
According to the first voice messaging, determine corresponding voice control command.
Embodiment of the present invention master it is noted that during user carries out Voice command, if there is languageHow sound interference specifically should be processed.
Such as, when the voice that the owner user a of electronic equipment says is " opening word ", that is, show to useFamily a is expected that by Voice command electronic equipment and opens word application, and meanwhile, near user aUser b also said the voice of " opening notepad ", due to " opening word " with " open noteThing this " all within the acquisition range of voice collecting unit, then voice collecting unit will collect includingThe message breath of above-mentioned two voices, then, it is control according to the voice messaging that voice collecting unit collects actuallyWord application opened by electronic equipment processed or control electronics open notepad appli-cation？
In specific implementation process, the voice messaging collecting can be parsed, to determine this voiceAt least one voiceprint that information includes, certainly, because everyone voiceprint is different, works as collectionArrived a few individual voice when, electronic equipment is assured that out several voiceprints.Further, then willAt least one voiceprint determined carries out coupling with default voiceprint and compares, for example, determine at least oneThe first voiceprint in bar voiceprint is mated with default voiceprint.In specific implementation process, presetVoiceprint can be gathered in advance by electronic equipment, and is the actual user of the electronic equipment gathering in advanceVoiceprint, then, in actual speech control process, just can extract from voice messaging and theCorresponding first voice messaging of one voiceprint is as real control voice, and then believes further according to the first voiceCease and to realize corresponding voice control function.
That is, by the scheme in the embodiment of the present invention, because user a is the owner of electronic equipment, then,Just default voiceprint can be set to the voiceprint of user a, collect at the same time including user a" opening word " and user b the voice messaging of " opening notepad " when it may be determined that user aVoiceprint mate with default voiceprint, then, electronic equipment will be from the voice messaging collectingThe voice of " opening word " extracting user a is as control voice, and then control electronics are openedWord applies, so that user carries out follow-up operation by word application.
That is, by the technical scheme in the embodiment of the present invention, can use up in the presence of interferenceAmount improves voice-operated accuracy, is consistent with the actual demand of real user as far as possible.
In control method in FIG, first gesture information as activation speech recognition engine trigger condition,So, after according to first gesture information activation speech recognition engine, when user is no longer necessary to use voiceDuring control function, in order to reduce powder consumption of electronic equipment as far as possible, and also to avoid responding, electronics as far as possible by mistakeWhen equipment should interrupt the identification of speech recognition engine that is to say, that how control voice identification is drawnHold up and terminate the voice command of user is carried out responding？
In specific implementation process, in order to solve the above problems, two kinds of possible modes presented below.That is:
First kind of way:
Optionally, in the embodiment of the present invention, controlling, working condition is switched to second by the first working conditionAfter working condition, methods described also includes:
Determine that the gesture information that image acquisition units gather is second gesture information by first gesture information change；
Control and working condition is switched to the first working condition by the second working condition.
In the embodiment of the present invention, after according to first gesture information activation speech recognition engine, enter in userDuring row phonetic entry, user can persistently carry out first gesture, i.e. only enters in first gestureInput voice in the process of row could realize corresponding function as control voice with control electronics,That is, in embodiments of the present invention, first gesture information serves not only as activating the triggering of speech recognition engineCondition, also as the control condition of phonetic entry, so so that speech recognition engine is clear and definite should actuallyObtained which section Instant audio messages, user just can carry out first-hand when being desired with voice control functionGesture, can improve voice-operated accuracy as far as possible, and specific aim is stronger, can largely meetThe real-time requirement of user.
In first kind of way, during Voice command is carried out by first gesture information, as long as onceFirst gesture information change is detected is the second gesture information different from first gesture information, and electronic equipment is justCan control at once and the working condition of voice collecting unit is switched to the first working condition by the second working condition,That is, control voice identifies that engine interrupts the identification to voice at once, to meet the actual demand of user as far as possible,The power consumption of electronic equipment can also be reduced as far as possible.
Optionally, in the embodiment of the present invention, control and working condition is switched to the first work by the second working conditionMake state, comprising:
Judge whether second gesture information is matched with the second default gesture information；
If mating with the second default gesture information, controlling and working condition is switched to the by the second working conditionOne working condition.
Further, second gesture information is detected it is also possible to judge second gesture be whether user in advanceThe certain gestures setting, so can avoid because user carries out first gesture for a long time as far as possible and lead to gestureSlightly deform, and then accuracy can be improved, only just interrupt in the predetermined certain gestures of userThe identification of speech recognition engine, is consistent with the actually used demand of user.
The second way:
Optionally, in the embodiment of the present invention, controlling, working condition is switched to second by the first working conditionAfter working condition, methods described also includes:
Determine that image acquisition units collect threeth gesture informations different from first gesture information；
Control and working condition is switched to and the first working condition by the second working condition.
In the embodiment of the present invention, after according to first gesture information activation speech recognition engine, user is permissiblePersistently carry out phonetic entry control, i.e. first gesture information is as just the triggering of activation speech recognition engineCondition, and when user expects to close voice control function, another spies different from first gesture will be carried outDetermine gesture (i.e. the 3rd gesture), wherein, the 3rd gesture information can be identical with second gesture information, also may be usedWith difference, i.e. the 3rd gesture can be identical gesture or different gestures from second gesture.
Image acquisition units after collecting the 3rd gesture information, that is, determine that Voice command is closed in user's expectationFunction, will control at once and for the working condition of voice collecting unit switch to the first work by the second working conditionMake state, i.e. control voice identifies that engine interrupts the identification to voice, to meet the reality of user as far as possible at onceBorder demand, can also reduce the power consumption of electronic equipment as far as possible.
For example, first gesture is " v " type gesture, and the 3rd gesture is that (i.e. user vertically eats " 1 " word gestureRefer to and gesture that other fingers are clenched fist), when user expects activation speech recognition engine, " v " will be madeType gesture, after figure collecting unit collects gesture information corresponding with " v " type gesture, will controlThe working condition of voice collecting unit is switched to the second working condition by the first working condition, that is, activates voiceIdentification engine, such as user is " v " the type gesture carrying out in 13:30, is carrying out once " v " type gestureAfterwards, user can put down the hand carrying out gesture, then realizes voice by phonetic entry come control electronicsControl function.In 13:50, user intends to go out, and in order to save the power consumption of electronic equipment, is also simultaneouslyPrevent the other users using the voice control function of electronic equipment in order to avoid causing information leakage, now user canTo control the identification interrupting speech recognition engine to carry out " 1 " word gesture.
That is, within 13:30-13:50 this period, electronic equipment is for whole voices lives of userOrder all can be responded, and only after user has carried out " 1 " word gesture, interruption voice just can be controlled to knowThe identification of other engine, such speech recognition engine can be carried out to the voice command of user in a long time in real timeResponse, and carry out other unnecessary operations without user, more convenient, practicality is stronger.
It is enumerated above the knowledge of two kinds of interruption speech recognition engines otherwise, in specific implementation process, whenOther modes so can also be had to interrupt the identification of speech recognition engine, just differ one schematically illustrates herein.
Refer to Fig. 2, based on same inventive concept, the embodiment of the present invention provides the first electronic equipment 200,Electronic equipment 200 includes:
Voice acquisition device 201, for gathering voice messaging；
Image collecting device 202, for gathering image information；
Processor 203, is connected with voice acquisition device 201 and image collecting device 202 respectively, for working asWhen voice acquisition device 201 is in the first working condition, control image collecting device 202 collection first gestureInformation；And it is based on first gesture information, control the working condition of voice acquisition device 201 by the first workSwitch to the second working condition as state；Wherein, the first working condition is: voice forbidden by electronic equipment 200The state that harvester 201 is responded to voice command, the second working condition is: electronic equipment 200 is permittedPermitted the state that voice acquisition device 201 is responded to voice command.
Specifically, voice acquisition device 201 may refer to microphone, such as head microphone or desktopThe external microphone of the electronic equipments such as microphone 200, or may also mean that the built-in wheat of electronic equipment 200Gram wind, etc., the particular type for voice acquisition device 201 is not limited, as long as voice acquisition device201 can gather voice messaging.
Image collecting device 202 may refer to camera, can be the external camera of electronic equipment 200,Or may also mean that electronic equipment 200 camera module of itself, the present invention is not limited.
Processor 203 can be specifically general cpu (central processing unit), or can be specific asic(application specific integrated circuit, application integrated circuit), or can be one or manyThe individual integrated circuit for control program execution.
Can pass through even respectively between processor 203 and voice acquisition device 201 and image collecting device 202Wiring is attached, and this connecting line has the effect of signal transmission, i.e. processor 203 and voice collecting dressPut and can keep between 201 and image collecting device 202 being electrically connected with, for voice acquisition device 201The voice messaging of collection and the image information that image collecting device 202 is gathered are processed.
Further, electronic equipment 200 can also include memory, the quantity of memory can be one orMultiple.Memory can include rom (read only memory, read-only storage), ram (randomAccess memory, random access memory) or magnetic disc store.
Optionally, in the embodiment of the present invention, processor 203 is used for:
Judge whether first gesture information is mated with the first default gesture information；
If mating with the first default gesture information, controlling and working condition is switched to the by the first working conditionTwo working conditions.
Optionally, in the embodiment of the present invention, processor 203 is additionally operable to:
After working condition is switched to the second working condition by the first working condition by control, in the second workUnder state, control voice harvester 201 collection obtains voice messaging；
According to voice messaging, determine corresponding voice control command；
Voice responsive control command, realizes corresponding voice control function with control electronics 200.
Optionally, in the embodiment of the present invention, processor 203 is used for:
According to voice messaging, determine at least one voiceprint corresponding with voice messaging；
The first voiceprint is determined from least one voiceprint；Wherein, the first voiceprint is and presetsThe voiceprint that voiceprint matches；
First voice messaging corresponding with the first voiceprint is determined from voice messaging；
According to the first voice messaging, determine corresponding voice control command.
Optionally, in the embodiment of the present invention, processor 203 is additionally operable to:
After working condition is switched to the second working condition by the first working condition by control, determine that image is adoptedThe gesture information of acquisition means 202 collection is second gesture information by first gesture information change；
Control and working condition is switched to the first working condition by the second working condition.
Optionally, in the embodiment of the present invention, processor 203 is used for:
Judge whether second gesture information is matched with the second default gesture information；
If mating with the second default gesture information, controlling and working condition is switched to the by the second working conditionOne working condition.
Optionally, in the embodiment of the present invention, processor 203 is additionally operable to:
After working condition is switched to the second working condition by the first working condition by control, determine that image is adoptedAcquisition means 202 collect threeth gesture informations different from first gesture information；
Control and working condition is switched to and the first working condition by the second working condition.
Principle due to the control method solve problem in the electronic equipment 200 and Fig. 1 in the embodiment of the present inventionSimilar, therefore in the embodiment of the present invention, the enforcement of electronic equipment 200 may refer to the reality of control method in Fig. 1Apply, will not be described here.
Refer to Fig. 3, based on same inventive concept, the embodiment of the present invention also provides second electronic equipment,This electronic equipment includes the first acquisition module 301 and the first control module 302.
First acquisition module 301, for when the voice collecting unit of electronic equipment is in the first working condition,Gather first gesture information by image acquisition units；Wherein, the first working condition is: electronic equipment is forbiddenThe state that voice collecting unit is responded to voice command；
First control module 302, for based on first gesture information, controlling the work of voice collecting unitState switches to the second working condition by the first working condition；Wherein, the second working condition is: electronic equipmentAllow the state that voice collecting unit is responded to voice command.
Optionally, in the embodiment of the present invention, the first control module 302 is used for:
Judge whether first gesture information is mated with the first default gesture information；
If mating with the first default gesture information, controlling and working condition is switched to the by the first working conditionTwo working conditions.
Optionally, in the embodiment of the present invention, electronic equipment also includes the second acquisition module, the first determining moduleWith the second control module.
Working condition is worked by first by the second acquisition module for being used for controlling in the first control module 302After state switches to the second working condition, in a second operative state, obtained by the collection of voice collecting unitObtain voice messaging；
First determining module, for according to voice messaging, determining corresponding voice control command；
Second control module, for voice responsive control command, realizes corresponding voice with control electronicsControl function.
Optionally, in the embodiment of the present invention, the first determining module is used for:
According to voice messaging, determine at least one voiceprint corresponding with voice messaging；
The first voiceprint is determined from least one voiceprint；Wherein, the first voiceprint is and presetsThe voiceprint that voiceprint matches；
First voice messaging corresponding with the first voiceprint is determined from voice messaging；
According to the first voice messaging, determine corresponding voice control command.
Optionally, in the embodiment of the present invention,
Electronic equipment also includes the second determining module, for being used for controlling work in the first control module 302After state switches to the second working condition by the first working condition, determine the gesture of image acquisition units collectionInformation is second gesture information by first gesture information change；
First control module 302 is additionally operable to: controls and for working condition to switch to the first work by the second working conditionMake state.
Optionally, in the embodiment of the present invention, the first control module 302 is used for:
Judge whether second gesture information is matched with the second default gesture information；
If mating with the second default gesture information, controlling and working condition is switched to the by the second working conditionOne working condition.
Optionally, in the embodiment of the present invention,
Second determining module is additionally operable to: is used for controlling working condition by the first work in the first control module 302After state switches to the second working condition, determine that image acquisition units collect with first gesture information notThe 3rd same gesture information；
First control module 302 is additionally operable to: controls and is switched to and first working condition by the second working conditionWorking condition.
Principle phase due to the control method solve problem in the electronic equipment in the embodiment of the present invention and Fig. 1Seemingly, therefore in the embodiment of the present invention, the enforcement of electronic equipment may refer to the enforcement of the control method in Fig. 1,Will not be described here.
In the embodiment of the present invention, when the voice collecting unit of electronic equipment is in the first working condition, that is, whenWhen voice collecting unit is in backstage listening state, gathered first-hand by the image acquisition units of electronic equipmentGesture information, and then it is based on first gesture information again, control the working condition of voice collecting unit by the first workSwitch to the second working condition as state, that is, control voice collecting unit is switched to by backstage listening state rightThe state that voice command is responded is that is to say, that in the embodiment of the present invention, can be realized by gestureActivation to speech recognition engine, electronic equipment has provided the user a kind of new speech recognition engine activation mouldFormula, enhances electronic equipment operability and multifunctionality, such that it is able to strengthen the experience of user.
Because existing electronic equipment is typically equipped with pixel, higher camera (is equivalent to IMAQ listUnit), it is possible to collecting clearly images of gestures information, i.e. the gesture that electronic equipment is made to userThere is higher identification, then just exactly line activating can be entered to speech recognition engine, such that it is able to carryHigh accuracy, in time speech recognition engine to be entered with line activating, saves the time that is to say, that passing through profitWith hardware configuration existing in electronic equipment, just speech recognition engine accurately and efficiently can be activated,The efficiency that electronic equipment is processed to information can be improved further, strengthen the performance of electronic equipment.
In addition, for a user, carry out that gesture operation is fairly simple, also compare be close to the users using practisingUsed.Meanwhile, user can carry out gesture operation apart from the place of electronic equipment certain distance, as long as imageCollecting unit can collect images of gestures information just can, and without walking close to electronic equipment, user is carried outThe flexibility of gesture operation is larger.And, can also reduce for peripheral hardware hardware device (such as mouse or keyDisk) dependence, enhance the independence of electronic equipment, decrease the step that user is operated manually.
Those skilled in the art can be understood that, for convenience and simplicity of description, only with above-mentionedThe division of each functional module is illustrated, and in practical application, can divide above-mentioned functions as desiredJoin and completed by different functional units, the internal structure of device will be divided into different functional units, with completeBecome all or part of function described above.The specific works mistake of the system, apparatus, and unit of foregoing descriptionJourney, may be referred to the corresponding process in preceding method embodiment, will not be described here.
It should be understood that disclosed system, device and side in several embodiments provided by the present inventionMethod, can realize by another way.For example, device embodiment described above is only schematically, for example, the division of described module or unit, only a kind of division of logic function, actual can when realizingThere to be other dividing mode, for example multiple units or assembly can in conjunction with or be desirably integrated into another and beUnite, or some features can be ignored, or do not execute.Another, shown or discussed coupling each otherClose or direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING of device or unit or communicationConnect, can be electrical, mechanical or other forms.
The described unit illustrating as separating component can be or may not be physically separate, asThe part that unit shows can be or may not be physical location, you can with positioned at a place, orCan also be distributed on multiple NEs.Can select therein some or all of according to the actual needsUnit is realizing the purpose of this embodiment scheme.
In addition, can be integrated in a processing unit in each functional unit in each embodiment of the present invention,Can also be that unit is individually physically present it is also possible to two or more units are integrated in a unitIn.Above-mentioned integrated unit both can be to be realized in the form of hardware, it would however also be possible to employ SFU software functional unitForm is realized.
If described integrated unit is realized and as independent production marketing using in the form of SFU software functional unitOr when using, can be stored in a computer read/write memory medium.Based on such understanding, thisPart that bright technical scheme substantially contributes to prior art in other words or this technical scheme completePortion or partly can be embodied in the form of software product, this computer software product is stored in a storageIn medium, including some instructions with so that computer equipment (can be personal computer, server,Or network equipment etc.) or processor (processor) execute each embodiment methods described of the present invention completePortion or part steps.And aforesaid storage medium includes: u disk, portable hard drive, rom (read-onlyMemory, read-only storage), ram (random access memory, random access memory),Magnetic disc or CD etc. are various can be with the medium of store program codes.
Specifically, the corresponding computer program instructions of one of embodiment of the present invention control method can be byIt is stored in CD, hard disk, on the storage medium such as u disk, when corresponding with a kind of control method in storage mediumComputer program instructions when being read or be performed by an electronic equipment, comprise the steps:
When the voice collecting unit of electronic equipment is in the first working condition, gathered by image acquisition unitsFirst gesture information；Wherein, the first working condition is: electronic equipment forbids that voice collecting unit is ordered to voiceMake the state being responded；
Based on first gesture information, control and the working condition of voice collecting unit is switched by the first working conditionFor the second working condition；Wherein, the second working condition is: electronic equipment allows voice collecting unit to voiceOrder the state being responded.
Optionally, in storage medium storage and step: based on first gesture information, control voice collectingThe working condition of unit switches to the second working condition by the first working condition, and corresponding computer instruction is in quiltAmong the process of execution, comprising:
Judge whether first gesture information is mated with the first default gesture information；
If mating with the first default gesture information, controlling and working condition is switched to the by the first working conditionTwo working conditions.
Optionally, in storage medium storage and step: control working condition is switched by the first working conditionFor the second working condition, corresponding computer instruction, after being performed, also includes:
In a second operative state, gathered by voice collecting unit and obtain voice messaging；
According to voice messaging, determine corresponding voice control command；
Voice responsive control command, realizes corresponding voice control function with control electronics.
Optionally, in storage medium storage and step: according to described voice messaging, determine corresponding voiceControl command, corresponding computer instruction is among the process being performed, comprising:
According to voice messaging, determine at least one voiceprint corresponding with voice messaging；
The first voiceprint is determined from least one voiceprint；Wherein, the first voiceprint is and presetsThe voiceprint that voiceprint matches；
First voice messaging corresponding with the first voiceprint is determined from voice messaging；
According to the first voice messaging, determine corresponding voice control command.
Optionally, in storage medium storage and step: control working condition is switched by the first working conditionFor the second working condition, corresponding computer instruction, after being performed, also includes:
Determine that the gesture information that image acquisition units gather is second gesture information by first gesture information change；
Control and working condition is switched to the first working condition by the second working condition.
Optionally, in storage medium storage and step: control working condition is switched by the second working conditionFor the first working condition, corresponding computer instruction is among the process being performed, comprising:
Judge whether second gesture information is matched with the second default gesture information；
If mating with the second default gesture information, controlling and working condition is switched to the by the second working conditionOne working condition.
Optionally, in storage medium storage and step: control by described working condition by described first workSwitch to described second working condition as state, corresponding computer instruction, after being performed, also includes:
Determine that image acquisition units collect threeth gesture informations different from first gesture information；
Control and working condition is switched to and the first working condition by the second working condition.
The above, above example only in order to be described in detail to technical scheme, but withThe explanation of upper embodiment is only intended to help and understands the method for the present invention and its core concept, and it is right to should not be construed asThe restriction of the present invention.Those skilled in the art the invention discloses technical scope in, can think easilyThe change or replacement arrived, all should be included within the scope of the present invention.