CN107123421A - Sound control method, device and home appliance - Google Patents
Sound control method, device and home appliance Download PDFInfo
- Publication number
- CN107123421A CN107123421A CN201710233667.XA CN201710233667A CN107123421A CN 107123421 A CN107123421 A CN 107123421A CN 201710233667 A CN201710233667 A CN 201710233667A CN 107123421 A CN107123421 A CN 107123421A
- Authority
- CN
- China
- Prior art keywords
- target
- information
- control instruction
- control
- sound
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000005314 correlation function Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 241000209140 Triticum Species 0.000 claims description 4
- 235000021307 Triticum Nutrition 0.000 claims description 4
- 230000002787 reinforcement Effects 0.000 claims 1
- 238000005728 strengthening Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 11
- 238000004378 air conditioning Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 6
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 241001672694 Citrus reticulata Species 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000032696 parturition Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
The present invention proposes a kind of sound control method, device and home appliance, wherein, method includes:The voice messaging that sound source is sent is gathered based on microphone array;The voice messaging is identified, it is determined that target control corresponding with the voice messaging is instructed;Obtain positional information of the sound source relative to the microphone array;Home appliance is controlled to be run according to target control instruction and the positional information.By this method, the intelligentized control method to home appliance can be realized, user only can control home appliance by sending voice messaging, releases dependence of the user to remote control, lifts Consumer's Experience.
Description
Technical field
The present invention relates to smart home field, more particularly to a kind of sound control method, device and home appliance.
Background technology
Home appliance such as air-conditioning, electric fan etc., as living electric apparatus, are increasingly appearing in daily life
In, the existing control to home appliance is to apply journey by supporting remote control, or by installing in the terminal mostly
What sequence was realized, user can not break away from the dependence to external control devices, and experience sense is poor.
The content of the invention
It is contemplated that at least solving one of technical problem in correlation technique to a certain extent.
Therefore, first purpose of the present invention is to propose a kind of sound control method, to realize intelligentized control method household electrical appliances
Equipment, user can be only controlled by sending voice messaging to home appliance, release dependence of the user to remote control.
Second object of the present invention is to propose a kind of phonetic controller.
Third object of the present invention is to propose a kind of home appliance.
Fourth object of the present invention is to propose a kind of computer program product.
The 5th purpose of the present invention is to propose a kind of non-transitorycomputer readable storage medium.
For up to above-mentioned purpose, first aspect present invention embodiment proposes a kind of sound control method, including:
The voice messaging that sound source is sent is gathered based on microphone array;
The voice messaging is identified, it is determined that target control corresponding with the voice messaging is instructed;
Obtain positional information of the sound source relative to the microphone array;
Home appliance is controlled to be run according to target control instruction and the positional information.
The sound control method of the embodiment of the present invention, by gathering the voice messaging that sound source is sent, is carried out to voice messaging
Identification determines corresponding target control instruction, obtains positional information of the sound source relative to microphone array, and control home appliance is pressed
Run according to target control instruction and positional information.Thereby, it is possible to realize the intelligentized control method to home appliance, user only passes through hair
Go out voice messaging and can control home appliance, relieve dependence of the user to remote control, improve Consumer's Experience.
For up to above-mentioned purpose, second aspect of the present invention embodiment proposes a kind of phonetic controller, including:
Microphone array, for gathering the voice messaging that sound source is sent;
Sound identification module, for the voice messaging to be identified, it is determined that target corresponding with the voice messaging
Control instruction;
Locating module, for obtaining positional information of the sound source relative to the microphone array;
Control module, for controlling home appliance to be run according to target control instruction and the positional information.
The phonetic controller of the embodiment of the present invention, by gathering the voice messaging that sound source is sent, is carried out to voice messaging
Identification determines corresponding target control instruction, obtains positional information of the sound source relative to microphone array, and control home appliance is pressed
Run according to target control instruction and positional information.Thereby, it is possible to realize the intelligentized control method to home appliance, user only passes through hair
Go out voice messaging and can control home appliance, relieve dependence of the user to remote control, improve Consumer's Experience.
For up to above-mentioned purpose, third aspect present invention embodiment proposes a kind of home appliance, including:Language as described above
Sound control device.
The home appliance of the embodiment of the present invention, by gathering the voice messaging that sound source is sent, voice messaging is identified
Corresponding target control instruction is determined, positional information of the sound source relative to microphone array is obtained, control home appliance is according to mesh
Mark control instruction and positional information operation.Thereby, it is possible to realize the intelligentized control method to home appliance, user is only by sending language
The i.e. controllable home appliance of message breath, relieves dependence of the user to remote control, improves Consumer's Experience.
To achieve these goals, fourth aspect present invention embodiment proposes a kind of computer program product, when described
Instruction in computer program product by computing device when, perform the sound control method as described in first aspect embodiment.
To achieve these goals, fifth aspect present invention embodiment proposes a kind of computer-readable storage of non-transitory
Medium, is stored thereon with computer program, can realize that first aspect such as is implemented when the computer program is executed by processor
Sound control method described in example.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and be readily appreciated that, wherein:
The schematic flow sheet for the sound control method that Fig. 1 provides for one embodiment of the invention;
The schematic flow sheet for the sound control method that Fig. 2 provides for another embodiment of the present invention;
The schematic flow sheet for the Voice command algorithm that Fig. 3 provides for further embodiment of this invention;
The schematic flow sheet for the Voice command algorithm that Fig. 4 provides for a further embodiment of the present invention;
Fig. 5 is signal model and Array Model schematic diagram;
The structural representation for the phonetic controller that Fig. 6 provides for one embodiment of the invention;
The structural representation for the phonetic controller that Fig. 7 provides for another embodiment of the present invention;
The structural representation for the phonetic controller that Fig. 8 provides for further embodiment of this invention;
The structural representation for the phonetic controller that Fig. 9 provides for a further embodiment of the present invention;
The structural representation for the phonetic controller that Figure 10 provides for another embodiment of the present invention;And
The structural representation for the home appliance that Figure 11 provides for one embodiment of the invention.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and be not considered as limiting the invention.
Below with reference to the accompanying drawings the sound control method, device and home appliance of the embodiment of the present invention described.
The schematic flow sheet for the sound control method that Fig. 1 provides for one embodiment of the invention.
As shown in figure 1, the sound control method comprises the following steps:
S11, the voice messaging that sound source is sent is gathered based on microphone array.
User using home appliance when, if desired home appliance is controlled, such as control home appliance open or
Close, or control home appliance changes the method for operation, such as changes gear, wind direction of home appliance etc., can be to required control
The home appliance of system sends voice messaging.In the present embodiment, home appliance can include but is not limited to air-conditioning, fan etc..
In the present embodiment, the voice that home appliance can be sent based on built-in microphone array collection sound source (user)
Information.Wherein, microphone array is made up of several separate and characteristic identical microphones, and all microphones are in together
On one straight line, the direction of each microphone is identical, and the interval of any two neighboring microphones is identical, is pre-determined distance.
S12, voice messaging is identified, it is determined that target control corresponding with voice messaging is instructed.
In the present embodiment, after collecting the voice messaging that sound source is sent by microphone array, voice messaging is carried out
Identification, it is determined that target control corresponding with voice messaging is instructed.
In the embodiment of the present invention, voice messaging is identified has two in the way of determining corresponding target control instruction
Kind.As a kind of possible implementation, it can determine that target control is instructed by way of voice inquirement ATL.As another
A kind of possible implementation, it is possible to use speech recognition modeling determines that target control is instructed.Target is determined using two ways
The detailed process of control instruction will be provided in subsequent content, to avoid repeating, not elaborated herein.
S13, obtains positional information of the sound source relative to microphone array.
Wherein, positional information can be angle information and/or range information of the sound source relative to microphone array.
In the present embodiment, after collecting the voice messaging that sound source is sent by microphone array, sound source can also be obtained
Relative to the positional information of microphone array.As a kind of possible implementation, beamforming algorithm acquisition sound can be used
The positional information in source.
It should be noted that in the present embodiment, in no particular order, the two can be same for step S12 and step S13 execution sequence
Shi Zhihang, can also successively be performed, and the present embodiment is only explained so that step S13 is performed after step s 12 as an example, and
It cannot function as limitation of the present invention.
S14, control home appliance is run according to target control instruction and positional information.
In the present embodiment, it is determined that the corresponding target control instruction of voice messaging, and sound source is obtained relative to microphone
After the positional information of array, the control system of home appliance is that controllable home appliance is believed according to target control instruction and position
Breath operation, that is, control the position performance objective control instruction where home appliance towards sound source.
So that home appliance is air-conditioning as an example.When user sends the voice messaging of " wind-force turns a little down ", built in air-conditioning
Microphone array gather the voice messaging, and determine target control instruction corresponding with the voice messaging " to turn wind down
Power ", in addition, the positional information for the sound source that processing unit built in air-conditioning is obtained is 30 ° of angles on the left of relative air-conditioning, then air-conditioning
Built-in control system controls air-conditioning towards the direction blowing of 30 ° of left side, while the wind-force of air conditioning exhausting is reduced.
The sound control method of the present embodiment, by gathering the voice messaging that sound source is sent, voice messaging is identified
Corresponding target control instruction is determined, positional information of the sound source relative to microphone array is obtained, control home appliance is according to mesh
Mark control instruction and positional information operation.Thereby, it is possible to realize the intelligentized control method to home appliance, user is only by sending language
The i.e. controllable home appliance of message breath, relieves dependence of the user to remote control, improves Consumer's Experience.
In order to determine the corresponding target control instruction of voice messaging, it is necessary to which voice messaging is identified.As it was noted above,
The embodiment of the present invention by way of determining target control instruction by the way that voice messaging is identified to have two kinds, and one of which is logical
The mode for crossing voice inquirement ATL determines that target control is instructed, and the implementation process of which is specifically included:Obtain target voice
The object content of information, judges that default sound template storehouse whether there is quasi- control instruction corresponding with object content, if language
There is quasi- control instruction in sound ATL, then instruct quasi- control instruction as target control, so that, as shown in Fig. 2 of the invention
Another sound control method that embodiment is provided may comprise steps of:
S21, the voice messaging that sound source is sent is gathered based on microphone array.
S22, carries out analog-to-digital conversion to voice messaging and obtains digital speech information.
In the present embodiment, home appliance is collected after the voice messaging that sound source is sent by microphone array, can be first right
Voice messaging carries out analog-to-digital conversion, analog voice information is converted into digital speech information, for follow-up speech processes.Make
For a kind of possible implementation, the multi-channel analog that can be gathered using high precision analogue conversion process chip to microphone array
Voice messaging carries out high speed analog-to-digital conversion, obtains digital speech information.
S23, eliminates the interference information in digital speech information, obtains target voice information.
Wherein, interference information includes but is not limited to noise information and echo information.
In the present embodiment, multi-path voice information progress analog-to-digital conversion process is obtained after multi-path digital voice messaging, gone back
Further the multi-path digital voice messaging of gained can be handled, to eliminate the letter of the interference in multi-path digital voice messaging
Breath, such as carry out noise Processing for removing and echo cancellation process to multi-path digital voice messaging, obtain target voice information.As
A kind of possible implementation, can be handled the multi-path digital voice messaging of gained using digital audio processing chip,
To eliminate interference information, target voice information is obtained.
S24, obtains the object content of target voice information.
In the present embodiment, carry out a series of processing in the voice messaging gathered to microphone array and obtain target voice information
Afterwards, the object content in target voice information can also further be obtained.Specifically, can be using related speech recognition skill
Art obtains object content.
Wherein, object content is some conventional control commands, includes but is not limited to turn down, heightens, closes, opening, subtracting
Small, reduction etc..
S25, judges that default sound template storehouse whether there is quasi- control instruction corresponding with object content.
Wherein, quasi- control instruction is the control instruction for exceeding predetermined threshold value with object content matching degree.
In order to perform the control command that user sends, the control that can be recognized can be stored in home appliance in advance
Instruction, after the control command that user sends is received, control command is matched with the control instruction prestored, to perform
The control instruction matched, realizes the control to home appliance.
In the present embodiment, can pre-set be stored with several in sound template storehouse, sound template storehouse can be by family
The control instruction that electric equipment is recognized and performed, the control effect for performing each control instruction realization is entirely different.Obtaining mesh
Mark after the object content in voice messaging, object content is matched with all control instructions in sound template storehouse, with
Judge to whether there is quasi- control instruction corresponding with object content in sound template storehouse.
Specifically, it can judge whether to deposit with the matching degree of control instruction in sound template storehouse by calculating object content
In quasi- control instruction, when the matching degree of object content and control instruction exceedes predetermined threshold value (such as 90%), the control instruction
Be defined control instruction.
It should be noted that the sound template storehouse and predetermined threshold value in the present embodiment can be before home appliance dispatch from the factory by giving birth to
Business men is set.
In the present embodiment, if judging to learn there is quasi- control instruction corresponding with object content in sound template storehouse, perform
Step S26;If judgement, which is learnt, is not present quasi- control instruction corresponding with object content in sound template storehouse, step S29 is performed.
S26, quasi- control instruction is instructed as target control.
In the present embodiment, when learning in default sound template storehouse in the presence of quasi- control instruction corresponding with object content,
Quasi- control instruction is used to control home appliance as target control control instruction.
S27, is handled the progress of target voice information using default beamforming algorithm and obtains positional information.
In the present embodiment, carry out a series of processing in the voice messaging gathered to microphone array and obtain target voice information
Afterwards, target voice information can also be handled using default beamforming algorithm, obtains the positional information of sound source.
Beamforming algorithm is the controllable algorithm based on peak power output, and its basic thought is to gather each array element to come
Signal be weighted summation and form wave beam, the wave beam is guided by searching for the possible position of sound source, modification weights cause wheat
The output signal power of gram wind array is maximum.Beamforming algorithm can be used in time domain, can be used in frequency domain, with compared with
Strong applicability.
It should be noted that step S27 and step S24~S26 execution sequence is in no particular order, the step of positional information is obtained
It is rapid and obtain the step of target control is instructed and can also successively carry out, the present embodiment is only with step S27 in step while carry out
It is explained exemplified by being performed after rapid S26, and cannot function as limitation of the present invention.
S28, control home appliance is run according to target control instruction and positional information.
In the present embodiment, obtain the corresponding target control of voice messaging that the positional information and sound source of sound source sent and refer to
After order, you can control home appliance is run according to target control instruction and positional information.
Specifically, when identify target control instruction be defined control instruction after, further to home appliance export obtain
Positional information, to control home appliance to be run according to target control instruction and positional information.That is, whether will can know
Do not go out target control instruction and be defined control instruction as condition, to decide whether to home appliance output position information.Work as identification
Go out target control instruction be defined control instruction when, just to home appliance output position information, otherwise, without any operation.
By identify target control instruction be defined control instruction when to home appliance output position information to control house
Electric equipment is run according to target control instruction and positional information, it is unidentified go out when without any operation, it is possible to increase language control
The accuracy rate of system, it is to avoid home appliance influences Consumer's Experience because performing unnecessary control instruction.
S29, without any operation.
In the present embodiment, when judging to learn in sound template storehouse in the absence of quasi- control instruction corresponding with object content,
Home appliance no longer carries out any operation, that is, is not responding to the voice messaging that sound source is sent.
The sound control method of the present embodiment, carries out analog-to-digital conversion by the voice messaging gathered to microphone array and obtains
Digital speech information, the interference information eliminated in digital speech information obtains target voice information, can eliminate interference information pair
The interference of target voice information, improves the accuracy rate of subsequent treatment.By using default beamforming algorithm to target voice
Information progress, which is handled, obtains positional information, obtains the object content of target voice information, whether judges default sound template storehouse
In the presence of quasi- control instruction corresponding with object content, quasi- control instruction is referred to as target control when there is quasi- control instruction
Order, and the positional information obtained is exported to home appliance, control home appliance is run according to target control instruction and positional information,
Without any operation when in the absence of quasi- control instruction, it is possible to increase the accuracy rate of language control, it is to avoid home appliance is because holding
The unnecessary control instruction of row and influence Consumer's Experience.
The embodiment of the present invention is described above by the way that voice messaging is identified to determine two kinds of target control instruction
One kind in implementation, is described in detail below another implementation, i.e., determines target control using speech recognition modeling
Instruction.So as to as shown in figure 3, on the basis of embodiment as shown in Figure 2, step S24~S26 could alternatively be following steps:
S31, target voice information is input in speech recognition modeling and judges that the control that whether is defined of target voice information refers to
Order.
Wherein, speech recognition modeling can be obtained by training, and can be obtained using speech recognition modeling can be by household electrical appliances
The control instruction that equipment is recognized and performed.As a kind of possible implementation, when training speech recognition modeling, it can record
The predefined control instruction that different people is sent using mandarin, to obtain voice sample as training sample, is then based on god
Through network model speech recognition modeling is obtained using training sample training.As alternatively possible implementation, in training language
During sound identification model, the predefined control instruction that the people that can record different regions is sent using dialect, to obtain different mouths
The voice sample of sound obtains speech recognition modeling based on neural network model as training sample using training sample training.
In the present embodiment, carry out a series of processing in the voice messaging gathered to microphone array and obtain target voice information
Afterwards, target voice information is input in the good speech recognition modeling of training in advance, speech recognition modeling passes through to target language
Message breath is parsed, and judges whether target voice information is defined control instruction.If target voice information is inputted to speech recognition
Obtain can be by home appliance is recognized and is performed control instruction for parsing in model, then it is assumed that the control that is defined of target voice information refers to
Order;Otherwise it is assumed that target voice information is not quasi- control instruction, any operation is no longer carried out.
Wherein, quasi- control instruction for can by home appliance is recognized and is performed control instruction with target voice information pair
The control instruction answered.
S32, if identifying that target voice information is defined control instruction, and quasi- control instruction is referred to as target control
Order.
In the present embodiment, when speech recognition modeling identify target voice information be defined control instruction when, by quasi- control refer to
Order is instructed as target control.
The sound control method of the present embodiment, by the way that target voice information is input in speech recognition modeling, and in language
Sound identification model identify target voice information be defined control instruction when, quasi- control instruction is instructed as target control, can
Improve the accuracy rate of language control.
Handle in place to the progress of target voice information using default beamforming algorithm in order to illustrate more clearly of above-mentioned
The implementation process of confidence breath, the embodiment of the present invention proposes another sound control method.Fig. 4 is that a further embodiment of the present invention is carried
The schematic flow sheet of the Voice command algorithm of confession.
As shown in figure 4, on the basis of embodiment as shown in Figure 2, step S27 may comprise steps of:
S271, obtains time delay of the target voice information relative to reference microphone in the microphone of microphone array Zhong Ge roads
Value.
Wherein, reference microphone is a microphone in microphone array.
When the voice messaging that sound source is sent reaches microphone array, due to path difference, the signal that each microphone is received
Difference.In order to ensure that the signal that each microphone is obtained is identical, it is necessary to artificially be compensated the information received.
The time delay value that each microphone receives signal is obtained at this point it is possible to calculate, is obtained and reference microphone identical for compensation
Signal.
Assuming that microphone array is made up of M microphone, m is designated as respectively1, m2..., mM, and between neighboring microphones between
It is d every equal.At least there is a sound source in space, be arrowband sound source or simple signal sound source, sound source position is apart from wheat
Gram wind farther out so that the sound wave that the voice messaging that sound source is sent reaches microphone can be approximated to be plane wave, so that each
The deflection for the plane wave that microphone is received i.e. direction of arrival all same, is designated as θ.
By m1As reference microphone, then other microphones receive the time of voice messaging relative to m1In the presence of certain
It is delayed or exceeds the time limit, so that certain phase difference can be produced.I-th of microphone receives voice messaging relative to m1Time delay can be with
Calculated and obtained according to formula (1), formula (1) is expressed as follows:
Wherein, c is the velocity of sound, and M is the number of microphone, and d is the interval between two neighboring microphone.To avoid phase difference
The situation for causing direction fuzzy more than π, generally takesλ is wavelength, i.e. d meets " half-wavelength " principle.
Therefore, in the present embodiment, target voice information in the microphone of microphone array Zhong Ge roads is relative to referring to Mike
The time delay value of wind can also be calculated by formula (1) and obtained.
S272, according to time delay value and default weighting correlation function to the target voice information of each road microphone at
Reason.
In the present embodiment, target voice information in microphone array Zhong Ge roads microphone is obtained is relative to referring to Mike
After the time delay value of wind, the target voice information of each road microphone is handled according to default weighting correlation function, obtained
Hou Ge roads target voice information is handled, w can be expressed asixi(t-τi)。
Wherein, wi, i=1,2 ..., M is the weighting correlation function of the target voice information of each microphone, xi(t-τi),
I=1,2 ..., M is the target voice information after artificial compensation.
S273, will handle the target voice information summation on Hou Ge roads, form the defeated of beam information all the way and beam information
Go out power.
In the present embodiment, the interval between two neighboring microphone is met under conditions of half-wavelength principle, after processing
The target voice information on each road be weighted summation, beam information all the way is obtained, shown in calculation formula such as formula (2).
Based on signal model and Array Model as shown in Figure 5, beam information can be expressed as the arrow as shown in formula (3)
Amount form.
Y (t)=WHx(t) (3)
Wherein, the voice messaging x that x (t) is received by microphone arrayi(t) matrix of composition, W is related comprising weighting
Function wiWith delay value τiMatrix, WHRepresenting matrix W associate matrix, i=1,2 ..., M, i and M be positive integer.
For far field plane wave, W is equal to its array prevalence vector, i.e. W=a (k), and k is the corresponding wave beams of current θ.
In the present embodiment, when calculating the power output of beam information, it is necessary to introduce snap model.Assuming that each microphone
The data of N number of snap are have received, and during N → ∞, the power output of beam information can be calculated by formula (4) to be obtained.
Wherein, the matrix that the voice messaging that x (n) is received by microphone array is constituted.
The weighted value of correlation function is strengthened in S274, adjustment, obtains the maximum object beam signal of power output.
Due to W=a (k), so that, by changing wave beam k, you can change matrix W, and then realize to weighting correlation function
The adjustment of weighted value, forms different wave beams, realizes the scanning to the whole space where point source of sound.
In the present embodiment, strengthen the weighted value of correlation function by changing wave beam k adjustment, obtain the maximum ripple of power output
Beam, as object beam signal.
Can be wheat the whole space where point source of sound equivalent to a spatial filter is given by W=a (k)
Space in front of gram wind array carries out mesh generation, and each mesh point can be calculated successively to the time delay value of each microphone,
The beam signal of each grid and the power output of the beam signal are obtained, so as to realize the scanning to whole space, finally may be used
Therefrom to determine the corresponding beam signal of peak power output.
S275, the spatial point corresponding to search object beam signal, regard the positional information of spatial point as the position of sound source
Information.
In the present embodiment, after the maximum object beam signal of power output is obtained, search object beam signal institute is right
The spatial point answered, the positional information of the spatial point searched is the positional information of sound source.
The sound control method of the present embodiment, by obtaining the target voice information in the microphone of microphone array Zhong Ge roads
Relative to the time delay value of reference microphone, target voice information is handled according to time delay value and default weighting correlation function
Summation forms the power output of beam information and beam information all the way afterwards, and the weighting by adjusting weighting correlation function is worth to defeated
Go out prominent object beam signal, the corresponding spatial point of search object beam signal, can as the positional information of sound source
Improve the accuracy rate of positional information identification.
In order to realize above-described embodiment, the present invention also proposes a kind of speech sounds controller.
The structural representation for the phonetic controller that Fig. 6 provides for one embodiment of the invention.
As shown in fig. 6, the phonetic controller 60 includes:Microphone array 610, sound identification module 620, locating module
630, and control module 640.Wherein,
Microphone array 610, for gathering the voice messaging that sound source is sent.
Sound identification module 620, for voice messaging to be identified, it is determined that target control corresponding with voice messaging refers to
Order.
Alternatively, in a kind of possible implementation of the embodiment of the present invention, as shown in fig. 7, sound identification module 620
It can include:
Contents acquiring unit 62001, the object content for obtaining target voice information.
Judging unit 62002, for judging default sound template storehouse with the presence or absence of quasi- control corresponding with object content
Instruction, wherein, quasi- control instruction is the control instruction for exceeding predetermined threshold value with object content matching degree.
First setting unit 62003, if for there is quasi- control instruction in sound template storehouse, quasi- control instruction made
Instructed for target control.
Alternatively, in a kind of possible implementation of the embodiment of the present invention, as shown in figure 8, sound identification module 620
It can also include:
Model Identification unit 62011, target voice is judged for target voice information to be input in speech recognition modeling
Whether information is defined control instruction.
Second setting unit 62012, if for identifying that target voice information is defined control instruction, quasi- control referred to
Order is instructed as target control.
Locating module 630, for obtaining positional information of the sound source relative to microphone array.
Specifically, locating module 630 is used for, and the progress of target voice information is handled using default beamforming algorithm
To positional information.
Further, in a kind of possible implementation of the embodiment of the present invention, as shown in figure 9, locating module 630 can
With including:
Time delay acquiring unit 6301, for obtain the target voice information in the microphone of microphone array Zhong Ge roads relative to
The time delay value of reference microphone, wherein, reference microphone is a microphone in microphone array.
Processing unit 6302, for using according to the target of time delay value and default weighting correlation function to each road microphone
Voice messaging is handled.
Form of beams unit 6303, for the target voice information for handling Hou Ge roads to be summed, forms wave beam all the way and believes
The power output of breath and beam information.
Adjustment unit 6304, strengthens the weighted value of correlation function for adjusting, and obtains the maximum object beam of power output
Signal.
Search unit 6305, for searching for the spatial point corresponding to object beam signal, the positional information of spatial point is made
For the positional information of sound source.
Control module 640, for controlling home appliance to be run according to target control instruction and positional information.
Specifically, control module 640 is used for, when identify target control instruction be defined control instruction after, to home appliance
Output position information, to control home appliance to be run according to target control instruction and positional information.
Alternatively, in a kind of possible implementation of the embodiment of the present invention, as shown in Figure 10, the phonetic controller 60
It can also include:
Modular converter 650, for voice messaging to be identified in sound identification module 620, it is determined that with voice messaging pair
Before the control instruction answered, analog-to-digital conversion is carried out to voice messaging and obtains digital speech information.
Interference cancellation module 660, for eliminating the interference information in digital speech information, obtains target voice information.
It should be noted that the foregoing explanation to sound control method embodiment is also applied for the voice of the present embodiment
Control device, its realization principle is similar, and here is omitted.
The phonetic controller of the present embodiment, by gathering the voice messaging that sound source is sent, voice messaging is identified
Corresponding target control instruction is determined, positional information of the sound source relative to microphone array is obtained, control home appliance is according to mesh
Mark control instruction and positional information operation.Thereby, it is possible to realize the intelligentized control method to home appliance, user is only by sending language
The i.e. controllable home appliance of message breath, relieves dependence of the user to remote control, improves Consumer's Experience.
In order to realize above-described embodiment, the present invention also proposes a kind of home appliance.
The structural representation for the home appliance that Figure 11 provides for one embodiment of the invention.
As shown in figure 11, the home appliance 110 includes:Phonetic controller 60 as in the foregoing embodiment.
It should be noted that the foregoing explanation to sound control method embodiment is also applied for the household electrical appliances of the present embodiment
Equipment, its realization principle is similar, and here is omitted.
The home appliance of the present embodiment, by gathering the voice messaging that sound source is sent, determination is identified to voice messaging
Corresponding target control instruction, obtains positional information of the sound source relative to microphone array, control home appliance is according to target control
System instruction and positional information operation.Thereby, it is possible to realize the intelligentized control method to home appliance, user is only believed by sending voice
The i.e. controllable home appliance of breath, relieves dependence of the user to remote control, improves Consumer's Experience.
In order to realize above-described embodiment, the present invention also proposes a kind of computer program product, when in computer program product
Instruction by computing device when, perform sound control method as in the foregoing embodiment.
In order to realize above-described embodiment, the present invention also proposes a kind of non-transitorycomputer readable storage medium, deposited thereon
Computer program is contained, Voice command as in the foregoing embodiment can be realized when the computer program is executed by processor
Method.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means to combine specific features, structure, material or the spy that the embodiment or example are described
Point is contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area
Art personnel can be tied the not be the same as Example or the feature of example and non-be the same as Example or example described in this specification
Close and combine.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or implying relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or
Implicitly include at least one this feature.In the description of the invention, " multiple " are meant that at least two, such as two, three
It is individual etc., unless otherwise specifically defined.
Any process described otherwise above or method description are construed as in flow chart or herein, represent to include
Module, fragment or the portion of the code of one or more executable instructions for the step of realizing custom logic function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not be by shown or discussion suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Represent in flow charts or logic and/or step described otherwise above herein, for example, being considered use
In the order list for the executable instruction for realizing logic function, it may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress for combining these instruction execution systems, device or equipment and using
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following:Electricity with one or more wirings
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, can even is that can be in the paper of printing described program thereon or other are suitable for computer-readable medium
Medium, because can then enter edlin, interpretation or if necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, the software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage
Or firmware is realized.Such as, if realized with hardware with another embodiment, following skill well known in the art can be used
Any one of art or their combination are realized:With the logic gates for realizing logic function to data-signal from
Scattered logic circuit, the application specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene can be compiled
Journey gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method is carried
Rapid to can be by program to instruct the hardware of correlation to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.The integrated module is such as
Fruit is realized using in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although having been shown and retouching above
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (17)
1. a kind of sound control method, it is characterised in that including:
The voice messaging that sound source is sent is gathered based on microphone array;
The voice messaging is identified, it is determined that target control corresponding with the voice messaging is instructed;
Obtain positional information of the sound source relative to the microphone array;
Home appliance is controlled to be run according to target control instruction and the positional information.
2. sound control method according to claim 1, it is characterised in that described that the voice messaging is identified,
It is determined that before control instruction corresponding with the voice messaging, in addition to:
Analog-to-digital conversion is carried out to the voice messaging and obtains digital speech information;
The interference information in the digital speech information is eliminated, the target voice information is obtained.
3. sound control method according to claim 2, it is characterised in that described that the voice messaging is identified,
It is determined that target control instruction corresponding with the voice messaging, including:
Obtain the object content of the target voice information;
Judge that default sound template storehouse whether there is quasi- control instruction corresponding with the object content;Wherein, the quasi- control
System instruction is the control instruction for exceeding predetermined threshold value with the object content matching degree;
If there is the quasi- control instruction in the sound template storehouse, the quasi- control instruction is regard as the target control
Instruction.
4. sound control method according to claim 2, it is characterised in that described that the voice messaging is identified,
It is determined that target control instruction corresponding with the voice messaging, including:
The target voice information is input in speech recognition modeling and judges that the target voice information control that whether is defined refers to
Order;
If it is the quasi- control instruction to identify the target voice information, the quasi- control instruction is regard as the target
Control instruction.
5. the sound control method according to claim 3 or 4, it is characterised in that the control home appliance is according to described
Target control is instructed and positional information operation, including:
After it is the quasi- control instruction to identify the target control instruction, exports the position to the home appliance and believe
Breath, to control the home appliance to be run according to target control instruction and the positional information.
6. sound control method according to claim 2, it is characterised in that the acquisition sound source is relative to the wheat
The positional information of gram wind array, including:
The target voice information progress is handled using default beamforming algorithm and obtains the positional information.
7. sound control method according to claim 6, it is characterised in that described to use default beamforming algorithm to institute
State the progress of target voice information and handle and obtain the positional information, including:
Obtain time delay of the target voice information relative to reference microphone in the microphone array Zhong Ge roads microphone
Value;Wherein, the reference microphone is a microphone in the microphone array;
The target voice information of each road microphone is handled according to the time delay value and default weighting correlation function;
The target voice information summation on Hou Ge roads will be handled, form the output of beam information and the beam information all the way
Power;
The adjustment weighted value for strengthening correlation function, obtains the maximum object beam signal of power output;
Search for the spatial point corresponding to the object beam signal, using the positional information of the spatial point as the sound source institute
State positional information.
8. a kind of phonetic controller, it is characterised in that including:
Microphone array, for gathering the voice messaging that sound source is sent;
Sound identification module, for the voice messaging to be identified, it is determined that target control corresponding with the voice messaging
Instruction;
Locating module, for obtaining positional information of the sound source relative to the microphone array;
Control module, for controlling home appliance to be run according to target control instruction and the positional information.
9. phonetic controller according to claim 8, it is characterised in that also include:
Modular converter, for the voice messaging to be identified in the sound identification module, it is determined that with the voice messaging
Before corresponding control instruction, analog-to-digital conversion is carried out to the voice messaging and obtains digital speech information;
Interference cancellation module, for eliminating the interference information in the digital speech information, obtains the target voice information.
10. phonetic controller according to claim 9, it is characterised in that the sound identification module, including:
Contents acquiring unit, the object content for obtaining the target voice information;
Judging unit, for judging that default sound template storehouse whether there is quasi- control instruction corresponding with the object content;
Wherein, the quasi- control instruction is the control instruction for exceeding predetermined threshold value with the object content matching degree;
First setting unit, if for there is the quasi- control instruction in the sound template storehouse, the quasi- control referred to
Order is instructed as the target control.
11. phonetic controller according to claim 9, it is characterised in that the sound identification module, including:
Model Identification unit, the target language message is judged for the target voice information to be input in speech recognition modeling
Cease the control instruction that whether is defined;
Second setting unit, if for identifying that the target voice information is the quasi- control instruction, by the quasi- control
System instruction is instructed as the target control.
12. the phonetic controller according to claim 10 or 11, it is characterised in that the control module, specifically for
After it is the quasi- control instruction to identify the target control instruction, the positional information is exported to the home appliance, with
The home appliance is controlled to be run according to target control instruction and the positional information.
13. phonetic controller according to claim 9, it is characterised in that the locating module, specifically for using pre-
If beamforming algorithm the target voice information progress handled obtain the positional information.
14. phonetic controller according to claim 13, it is characterised in that the locating module, including:
Time delay acquiring unit, for obtain the target voice information in the microphone array Zhong Ge roads microphone relative to
The time delay value of reference microphone;Wherein, the reference microphone is a microphone in the microphone array;
Processing unit, for using according to the target of the time delay value and default weighting correlation function to each road microphone
Voice messaging is handled;
Form of beams unit, for the target voice information for handling Hou Ge roads to be summed, formed beam information all the way and
The power output of the beam information;
Adjustment unit, the weighted value for adjusting the reinforcement correlation function, obtains the maximum object beam signal of power output;
Search unit, for searching for the spatial point corresponding to the object beam signal, the positional information of the spatial point is made
For the positional information of the sound source.
15. a kind of home appliance, it is characterised in that including:Phonetic controller described in the claims any one of 8-14.
16. a kind of computer program product, when the instruction in the computer program product is by computing device, is performed as weighed
Profit requires the sound control method any one of 1-7.
17. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, it is characterised in that the calculating
The sound control method as any one of claim 1-7 is realized when machine program is executed by processor.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710233667.XA CN107123421A (en) | 2017-04-11 | 2017-04-11 | Sound control method, device and home appliance |
PCT/CN2017/104905 WO2018188287A1 (en) | 2017-04-11 | 2017-09-30 | A voice control method and apparatus, and household appliance device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710233667.XA CN107123421A (en) | 2017-04-11 | 2017-04-11 | Sound control method, device and home appliance |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107123421A true CN107123421A (en) | 2017-09-01 |
Family
ID=59726244
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710233667.XA Pending CN107123421A (en) | 2017-04-11 | 2017-04-11 | Sound control method, device and home appliance |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107123421A (en) |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107564522A (en) * | 2017-09-18 | 2018-01-09 | 郑州云海信息技术有限公司 | A kind of intelligent control method and device |
CN107767868A (en) * | 2017-10-23 | 2018-03-06 | 深圳北鱼信息科技有限公司 | Microphone array and speech control system |
CN108231075A (en) * | 2017-12-29 | 2018-06-29 | 北京视觉世界科技有限公司 | Control method, device, equipment and the storage medium of cleaning equipment |
CN108305623A (en) * | 2018-01-15 | 2018-07-20 | 珠海格力电器股份有限公司 | Electric control method and device |
CN108417036A (en) * | 2018-05-07 | 2018-08-17 | 北京中电慧声科技有限公司 | Vehicle whistle sound localization method and device in intelligent transportation system |
CN108628653A (en) * | 2018-03-30 | 2018-10-09 | 上海思愚智能科技有限公司 | Ground cushion management method and terminal |
WO2018188287A1 (en) * | 2017-04-11 | 2018-10-18 | 广东美的制冷设备有限公司 | A voice control method and apparatus, and household appliance device |
CN108834231A (en) * | 2018-03-30 | 2018-11-16 | 上海思愚智能科技有限公司 | Ground pad control method and smart machine |
CN108882103A (en) * | 2018-07-18 | 2018-11-23 | 北京小米移动软件有限公司 | Intelligent sound box, sound collection equipment and intelligent sound box system |
CN108983626A (en) * | 2018-07-24 | 2018-12-11 | 珠海格力电器股份有限公司 | The control method and equipment of equipment, storage medium, electronic device |
CN109309607A (en) * | 2018-10-15 | 2019-02-05 | 珠海格力电器股份有限公司 | Household appliance operation executes method, apparatus, household appliance and readable storage medium storing program for executing |
CN109788382A (en) * | 2019-01-25 | 2019-05-21 | 深圳大学 | A kind of distribution microphone array pickup system and method |
CN109994124A (en) * | 2017-12-29 | 2019-07-09 | 宁波方太厨具有限公司 | A kind of voice screening technique of range hood |
CN109994123A (en) * | 2017-12-29 | 2019-07-09 | 宁波方太厨具有限公司 | A kind of voice screening technique of range hood |
WO2019134473A1 (en) * | 2018-01-08 | 2019-07-11 | 珠海格力电器股份有限公司 | Speech recognition system, method and apparatus |
CN110164443A (en) * | 2019-06-28 | 2019-08-23 | 联想(北京)有限公司 | Method of speech processing, device and electronic equipment for electronic equipment |
CN110412510A (en) * | 2018-04-26 | 2019-11-05 | 苏州触达信息技术有限公司 | Localization method and positioning system in a kind of predetermined two-dimensional space |
CN110517703A (en) * | 2019-08-15 | 2019-11-29 | 北京小米移动软件有限公司 | A kind of sound collection method, device and medium |
CN110708220A (en) * | 2019-09-27 | 2020-01-17 | 恒大智慧科技有限公司 | Intelligent household control method and system and computer readable storage medium |
CN110827811A (en) * | 2018-08-13 | 2020-02-21 | 格力电器(武汉)有限公司 | Voice control method and device for household electrical appliance |
CN110895937A (en) * | 2018-09-13 | 2020-03-20 | 珠海格力电器股份有限公司 | Method and device for acquiring voice control signaling |
CN111103807A (en) * | 2019-12-17 | 2020-05-05 | 青岛海信智慧家居***股份有限公司 | Control method and device for household terminal equipment |
CN111182382A (en) * | 2019-10-22 | 2020-05-19 | 广东小天才科技有限公司 | Audio playing control method based on sound box and sound box |
CN108305615B (en) * | 2017-10-23 | 2020-06-16 | 腾讯科技(深圳)有限公司 | Object identification method and device, storage medium and terminal thereof |
CN111425377A (en) * | 2019-01-09 | 2020-07-17 | 广东美的环境电器制造有限公司 | Fan and control method and device thereof |
CN111833862A (en) * | 2019-04-19 | 2020-10-27 | 佛山市顺德区美的电热电器制造有限公司 | Control method of equipment, control equipment and storage medium |
WO2020252886A1 (en) * | 2019-06-17 | 2020-12-24 | 深圳壹秘科技有限公司 | Directional sound pickup method, recording device and storage medium |
CN112492455A (en) * | 2020-11-27 | 2021-03-12 | 广东美的制冷设备有限公司 | Control method and operation control device of electronic equipment and electronic equipment |
WO2023284562A1 (en) * | 2021-07-14 | 2023-01-19 | 海信视像科技股份有限公司 | Control device, household appliance, and control method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102522082A (en) * | 2011-12-27 | 2012-06-27 | 重庆大学 | Recognizing and locating method for abnormal sound in public places |
CN102707262A (en) * | 2012-06-20 | 2012-10-03 | 太仓博天网络科技有限公司 | Sound localization system based on microphone array |
JP2012211768A (en) * | 2011-03-30 | 2012-11-01 | Advanced Telecommunication Research Institute International | Sound source positioning apparatus |
CN104214890A (en) * | 2014-01-20 | 2014-12-17 | 美的集团股份有限公司 | Air conditioner and method for controlling air supply thereof by voice |
CN105467364A (en) * | 2015-11-20 | 2016-04-06 | 百度在线网络技术(北京)有限公司 | Method and apparatus for localizing target sound source |
-
2017
- 2017-04-11 CN CN201710233667.XA patent/CN107123421A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012211768A (en) * | 2011-03-30 | 2012-11-01 | Advanced Telecommunication Research Institute International | Sound source positioning apparatus |
CN102522082A (en) * | 2011-12-27 | 2012-06-27 | 重庆大学 | Recognizing and locating method for abnormal sound in public places |
CN102707262A (en) * | 2012-06-20 | 2012-10-03 | 太仓博天网络科技有限公司 | Sound localization system based on microphone array |
CN104214890A (en) * | 2014-01-20 | 2014-12-17 | 美的集团股份有限公司 | Air conditioner and method for controlling air supply thereof by voice |
CN105467364A (en) * | 2015-11-20 | 2016-04-06 | 百度在线网络技术(北京)有限公司 | Method and apparatus for localizing target sound source |
Cited By (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018188287A1 (en) * | 2017-04-11 | 2018-10-18 | 广东美的制冷设备有限公司 | A voice control method and apparatus, and household appliance device |
CN107564522A (en) * | 2017-09-18 | 2018-01-09 | 郑州云海信息技术有限公司 | A kind of intelligent control method and device |
CN107767868A (en) * | 2017-10-23 | 2018-03-06 | 深圳北鱼信息科技有限公司 | Microphone array and speech control system |
CN108305615B (en) * | 2017-10-23 | 2020-06-16 | 腾讯科技(深圳)有限公司 | Object identification method and device, storage medium and terminal thereof |
CN109994124A (en) * | 2017-12-29 | 2019-07-09 | 宁波方太厨具有限公司 | A kind of voice screening technique of range hood |
CN108231075A (en) * | 2017-12-29 | 2018-06-29 | 北京视觉世界科技有限公司 | Control method, device, equipment and the storage medium of cleaning equipment |
CN109994123A (en) * | 2017-12-29 | 2019-07-09 | 宁波方太厨具有限公司 | A kind of voice screening technique of range hood |
WO2019134473A1 (en) * | 2018-01-08 | 2019-07-11 | 珠海格力电器股份有限公司 | Speech recognition system, method and apparatus |
CN108305623A (en) * | 2018-01-15 | 2018-07-20 | 珠海格力电器股份有限公司 | Electric control method and device |
CN108628653A (en) * | 2018-03-30 | 2018-10-09 | 上海思愚智能科技有限公司 | Ground cushion management method and terminal |
CN108834231A (en) * | 2018-03-30 | 2018-11-16 | 上海思愚智能科技有限公司 | Ground pad control method and smart machine |
CN110412510A (en) * | 2018-04-26 | 2019-11-05 | 苏州触达信息技术有限公司 | Localization method and positioning system in a kind of predetermined two-dimensional space |
CN108417036A (en) * | 2018-05-07 | 2018-08-17 | 北京中电慧声科技有限公司 | Vehicle whistle sound localization method and device in intelligent transportation system |
CN108882103B (en) * | 2018-07-18 | 2020-01-10 | 北京小米移动软件有限公司 | Intelligent sound box, sound collection equipment and intelligent sound box system |
CN108882103A (en) * | 2018-07-18 | 2018-11-23 | 北京小米移动软件有限公司 | Intelligent sound box, sound collection equipment and intelligent sound box system |
CN108983626A (en) * | 2018-07-24 | 2018-12-11 | 珠海格力电器股份有限公司 | The control method and equipment of equipment, storage medium, electronic device |
CN110827811A (en) * | 2018-08-13 | 2020-02-21 | 格力电器(武汉)有限公司 | Voice control method and device for household electrical appliance |
CN110895937A (en) * | 2018-09-13 | 2020-03-20 | 珠海格力电器股份有限公司 | Method and device for acquiring voice control signaling |
CN109309607A (en) * | 2018-10-15 | 2019-02-05 | 珠海格力电器股份有限公司 | Household appliance operation executes method, apparatus, household appliance and readable storage medium storing program for executing |
CN111425377A (en) * | 2019-01-09 | 2020-07-17 | 广东美的环境电器制造有限公司 | Fan and control method and device thereof |
CN109788382A (en) * | 2019-01-25 | 2019-05-21 | 深圳大学 | A kind of distribution microphone array pickup system and method |
CN111833862B (en) * | 2019-04-19 | 2023-10-20 | 佛山市顺德区美的电热电器制造有限公司 | Control method of equipment, control equipment and storage medium |
CN111833862A (en) * | 2019-04-19 | 2020-10-27 | 佛山市顺德区美的电热电器制造有限公司 | Control method of equipment, control equipment and storage medium |
WO2020252886A1 (en) * | 2019-06-17 | 2020-12-24 | 深圳壹秘科技有限公司 | Directional sound pickup method, recording device and storage medium |
CN110164443A (en) * | 2019-06-28 | 2019-08-23 | 联想(北京)有限公司 | Method of speech processing, device and electronic equipment for electronic equipment |
CN110164443B (en) * | 2019-06-28 | 2021-09-14 | 联想(北京)有限公司 | Voice processing method and device for electronic equipment and electronic equipment |
CN110517703A (en) * | 2019-08-15 | 2019-11-29 | 北京小米移动软件有限公司 | A kind of sound collection method, device and medium |
CN110517703B (en) * | 2019-08-15 | 2021-12-07 | 北京小米移动软件有限公司 | Sound collection method, device and medium |
CN110708220A (en) * | 2019-09-27 | 2020-01-17 | 恒大智慧科技有限公司 | Intelligent household control method and system and computer readable storage medium |
CN111182382A (en) * | 2019-10-22 | 2020-05-19 | 广东小天才科技有限公司 | Audio playing control method based on sound box and sound box |
CN111103807A (en) * | 2019-12-17 | 2020-05-05 | 青岛海信智慧家居***股份有限公司 | Control method and device for household terminal equipment |
CN112492455A (en) * | 2020-11-27 | 2021-03-12 | 广东美的制冷设备有限公司 | Control method and operation control device of electronic equipment and electronic equipment |
WO2023284562A1 (en) * | 2021-07-14 | 2023-01-19 | 海信视像科技股份有限公司 | Control device, household appliance, and control method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107123421A (en) | Sound control method, device and home appliance | |
CN105611477B (en) | The voice enhancement algorithm that depth and range neutral net are combined in digital deaf-aid | |
CN110211580B (en) | Multi-intelligent-device response method, device, system and storage medium | |
CN104810021B (en) | The pre-treating method and device recognized applied to far field | |
Nakamura et al. | Intelligent sound source localization and its application to multimodal human tracking | |
CN106504763A (en) | Based on blind source separating and the microphone array multiple target sound enhancement method of spectrum-subtraction | |
CN105825871B (en) | A kind of end-point detecting method without leading mute section of voice | |
CN108804784A (en) | A kind of instant learning soft-measuring modeling method based on Bayes's gauss hybrid models | |
CN109272989A (en) | Voice awakening method, device and computer readable storage medium | |
CN105409241A (en) | Microphone calibration | |
CN107240395A (en) | A kind of acoustic training model method and apparatus, computer equipment, storage medium | |
CN109767769A (en) | A kind of audio recognition method, device, storage medium and air-conditioning | |
CN107591152A (en) | Sound control method, device and its equipment based on earphone | |
WO2021008000A1 (en) | Voice wakeup method and apparatus, electronic device and storage medium | |
CN109817209A (en) | A kind of intelligent speech interactive system based on two-microphone array | |
CN106057210B (en) | Quick speech blind source separation method based on frequency point selection under binaural distance | |
CN107564539A (en) | Towards the acoustic echo removing method and device of microphone array | |
CN102576543A (en) | Multi-input noise suppresion device, multi-input noise suppression method, program, and integrated circuit | |
CN106971714A (en) | A kind of speech de-noising recognition methods and device applied to robot | |
CN113593548A (en) | Awakening method and device of intelligent equipment, storage medium and electronic device | |
CN113707136B (en) | Audio and video mixed voice front-end processing method for voice interaction of service robot | |
Chan et al. | Speech enhancement strategy for speech recognition microcontroller under noisy environments | |
CN109545210A (en) | A kind of devices and methods therefor promoting speech recognition robustness | |
CN113919945A (en) | Data analysis method, device, equipment and storage medium based on neural network | |
CN117711436A (en) | Far-field sound classification method and device based on multi-sensor fusion |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170901 |
|
RJ01 | Rejection of invention patent application after publication |