CN107564515A - Sound control method and system, microphone and server based on multi-microphone - Google Patents
Sound control method and system, microphone and server based on multi-microphone Download PDFInfo
- Publication number
- CN107564515A CN107564515A CN201610514013.XA CN201610514013A CN107564515A CN 107564515 A CN107564515 A CN 107564515A CN 201610514013 A CN201610514013 A CN 201610514013A CN 107564515 A CN107564515 A CN 107564515A
- Authority
- CN
- China
- Prior art keywords
- acoustic information
- microphone
- server
- electrical appliance
- information
- 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
Abstract
The invention discloses a kind of sound control method based on multi-microphone and system, microphone and server, the described method comprises the following steps：Server receives the acoustic information in the region that the multiple microphones being arranged at the same area diverse location are collected；Server is parsed to the acoustic information of multiple microphones to extract the phonetic order information of user；Server needs command information corresponding to the household electrical appliance and household electrical appliance of control according to corresponding to determining the phonetic order information of user；Server sends command information corresponding to household electrical appliance to household electrical appliance, to control household electrical appliance to perform respective operations.This method collects the acoustic information in the same area by multiple microphones, and the acoustic information of multiple microphones is parsed to extract effective phonetic order information, so as to effectively suppress interfering noise, improve phonetic recognization rate, and without setting special parameter according to specific environment, greatly reduce later maintenance cost.
Description
Technical field
The present invention relates to field of intelligent control technology, more particularly to a kind of sound control method based on multi-microphone and it is
System, microphone and server.
Background technology
With the development of intelligent artifact industry, phonetic order control is familiar with by people.Phonetic order control can give user
The experience for having more hommization is provided.
The phonetic order control solution of existing intelligent artifact on the market, it is the embedded microphone on intelligent artifact mostly,
Then speech recognition is carried out, the technology typically used is the speech recognition technology near field or far field.But speech recognition is to environment
It is required that higher, echo in ambient noise, regional space etc. can all influence the quality of speech recognition.
In correlation technique, for specific environment, specific parameter is configured, alleviates phonetic recognization rate to a certain extent
The problem of low, but the technical problem of one " environment becomes, and parameter will be with time-varying " is also brought simultaneously, cause later maintenance cost big
It is big to improve.
The content of the invention
It is contemplated that at least solves 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 based on multi-microphone, by more
Individual microphone collects the acoustic information in the same area, and the acoustic information of multiple microphones is parsed to extract effectively
Phonetic order information, so as to effectively suppress interfering noise, phonetic recognization rate is improved, and without setting specific ginseng according to specific environment
Number, greatly reduces later maintenance cost.
Second object of the present invention is to propose a kind of microphone.
Third object of the present invention is to propose a kind of server.
Fourth object of the present invention is to propose a kind of speech control system based on multi-microphone.
To achieve the above object, first aspect present invention embodiment proposes a kind of Voice command side based on multi-microphone
Method, comprise the following steps：Server receives the region that the multiple microphones being arranged at the same area diverse location are collected
Interior acoustic information；The server is parsed to the acoustic information of the multiple microphone to extract the voice of the user
Command information；The server needs the household electrical appliance and family expenses of control according to corresponding to determining the phonetic order information of the user
Command information corresponding to electrical equipment；And the server sends command information corresponding to the household electrical appliance to the household electric
Device, to control the household electrical appliance to perform respective operations.
Sound control method based on multi-microphone according to embodiments of the present invention, server receive and are arranged on the same area
The acoustic information in region that multiple microphones at diverse location are collected, and the acoustic information of multiple microphones is parsed
To extract the phonetic order information of user, then, household electrical appliance and the family of control are needed according to corresponding to determining phonetic order information
Command information corresponding to electrical appliance, and command information corresponding to household electrical appliance is sent to household electrical appliance, to control household electrical appliance
Perform respective operations.This method collects the acoustic information in the same area by multiple microphones, and to the sound of multiple microphones
Message breath is parsed to extract effective phonetic order information, so as to effectively suppress interfering noise, improves phonetic recognization rate, and
Without setting special parameter according to specific environment, later maintenance cost is greatly reduced.
According to one embodiment of present invention, the server parses to the acoustic information of the multiple microphone,
Including：Echo cancellor and noise reduction process are carried out to the acoustic information.
According to one embodiment of present invention, the above-mentioned sound control method based on multi-microphone also includes：It is described more
The decibel and frequency for the acoustic information that each microphone detection in individual microphone is collected into, and judge point of the acoustic information
Whether whether shellfish is more than default decibel, and judge the frequency of the acoustic information in the range of predeterminated frequency；If the sound
The decibel of message breath is more than the frequency of the default decibel and the acoustic information in the preset range, then corresponding Mike
Wind sends the acoustic information to the server.
According to one embodiment of present invention, the multiple microphone is arranged in the household electrical appliance.
To achieve the above object, second aspect of the present invention embodiment proposes a kind of microphone, including：Sound collecting mould
Block, the acoustic information that the sound collecting module is used in collecting zone；Communication module, the communication module is used for and server
Establish communication connection；Judge module, the judge module are connected with the sound collecting module, and the judge module is used to judge
Whether whether the decibel of the acoustic information is more than default decibel, and judge the frequency of the acoustic information in predeterminated frequency scope
It is interior；Sending module, the sending module respectively with the judge module, the communication module and the sound collecting module phase
Even, the sending module is used to more than the frequency of the default decibel and the acoustic information exist in the decibel of the acoustic information
When in the preset range, the acoustic information is sent to the server by the communication module.
Microphone according to embodiments of the present invention, after the acoustic information in sound collecting module collection to region, not
Server is sent directly to, but first passes through judge module and judges whether the decibel of acoustic information is more than default decibel, and is judged
Whether the frequency of acoustic information is in the range of predeterminated frequency, if the decibel of acoustic information is more than default decibel and acoustic information
Within a preset range, then sending module sends acoustic information to server to frequency by communication module, so that microphone is only
More effective part is transmitted, reduces the transmission quantity of data, particularly in multiple microphone simultaneous transmission data to same service
During device, the bandwidth congestion phenomenon caused by mass data simultaneous transmission is avoided, reduces the requirement to transmission bandwidth, and enter
One step reduces processing time and the processing task amount of server, improves the response speed of server.
To achieve the above object, third aspect present invention embodiment proposes a kind of server, including：Receiving module, use
Acoustic information in the region for receiving the multiple microphones collection being arranged at the same area diverse location；Extract mould
Block, for being parsed to the acoustic information of the multiple microphone to extract the phonetic order information of the user；Obtain mould
Block, for according to the phonetic order information of the user determine corresponding to need control household electrical appliance and household electrical appliance corresponding to finger
Make information；And control module, for command information corresponding to the household electrical appliance to be sent to the household electrical appliance, with control
The household electrical appliance perform respective operations.
Server according to embodiments of the present invention, it is arranged on by receiving module reception more at the same area diverse location
The acoustic information in region that individual microphone is collected, then, extraction module the acoustic information of multiple microphones is parsed with
The phonetic order information of user is extracted, acquisition module needs the household electric of control according to corresponding to determining the phonetic order information of user
Command information corresponding to device and household electrical appliance, finally, control module send command information corresponding to household electrical appliance to household electric
Device, to control household electrical appliance to perform respective operations.The server is believed by the sound collected to multiple microphones of the same area
Breath is parsed, and to remove interference noise, is extracted effective phonetic order information, is effectively increased phonetic recognization rate, avoid
In correlation technique, environment becomes, and parameter becomes, then needs manual test to redefine the technical problem of parameter, after greatly reducing
The maintenance cost of phase.
According to one embodiment of present invention, the extraction module solves to the acoustic information of the multiple microphone
Analysis, including：Echo cancellor and noise reduction process are carried out to the acoustic information.
To achieve the above object, fourth aspect present invention embodiment proposes a kind of Voice command system based on multi-microphone
System, including：The multiple microphones being arranged at the same area diverse location, the multiple microphone are used to collect in the region
Acoustic information；Server, the server are used for the acoustic information for receiving the multiple microphone, and to the multiple Mike
The acoustic information of wind is parsed to extract the phonetic order information of the user, and according to the phonetic order information of the user
It is determined that corresponding need command information corresponding to the household electrical appliance and household electrical appliance of control, and will refer to corresponding to the household electrical appliance
Information is made to send to the household electrical appliance, to control the household electrical appliance to perform respective operations.
Speech control system based on multi-microphone according to embodiments of the present invention, server receive and are arranged on the same area
The acoustic information in region that multiple microphones at diverse location are collected, and the acoustic information of multiple microphones is parsed
To extract the phonetic order information of user, then, household electrical appliance and the family of control are needed according to corresponding to determining phonetic order information
Command information corresponding to electrical appliance, and command information corresponding to household electrical appliance is sent to household electrical appliance, to control household electrical appliance
Perform respective operations.The system collects the acoustic information in the same area by multiple microphones, and to the sound of multiple microphones
Message breath is parsed to extract effective phonetic order information, so as to effectively suppress interfering noise, improves phonetic recognization rate, and
Without setting special parameter according to specific environment, later maintenance cost is greatly reduced.
According to one embodiment of present invention, the server parses to the acoustic information of the multiple microphone,
Including：Echo cancellor and noise reduction process are carried out to the acoustic information.
According to one embodiment of present invention, the sound letter that each microphone detection in the multiple microphone is collected into
The decibel and frequency of breath, and judge whether the decibel of the acoustic information is more than default decibel, and judge the acoustic information
Frequency whether within a preset range, wherein, if the decibel of the acoustic information is more than the default decibel and the sound
The frequency of information then sends the acoustic information to the server in the preset range.
According to one embodiment of present invention, the multiple microphone is arranged in the household electrical appliance.
Brief description of the drawings
Fig. 1 is the flow chart of the sound control method according to an embodiment of the invention based on multi-microphone；
Fig. 2 is the microphone schematic layout pattern according to a specific example of the invention；
Fig. 3 is the flow chart of the sound controlling method in accordance with another embodiment of the present invention based on multi-microphone；
Fig. 4 is the structural representation of microphone according to an embodiment of the invention；
Fig. 5 is the structural representation of microphone in accordance with another embodiment of the present invention；
Fig. 6 is the structural representation of server according to an embodiment of the invention；And
Fig. 7 is the block diagram of the speech control system according to an embodiment of the invention based on multi-microphone.
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 is not considered as limiting the invention.
With reference to the accompanying drawings come describe to propose according to embodiments of the present invention sound control method based on multi-microphone and
System, microphone and server.
Fig. 1 is the flow chart of the sound control method according to an embodiment of the invention based on multi-microphone.Such as Fig. 1 institutes
Show, be somebody's turn to do the sound control method based on multi-microphone and comprise the following steps：
S101, server receive the sound in the region that the multiple microphones being arranged at the same area diverse location are collected
Information.
Because requirement of the speech recognition to environment is higher, the meeting such as echo (wall resilience noise) in ambient noise and region
The quality of speech recognition is influenceed, therefore, in an embodiment of the present invention, can be set in the same area according to field condition
More than two microphones, to suppress interference noise.
As a specific example, as shown in Fig. 2 can be using dining room and parlor as the same area A, according to dining room and visitor
The area and structure in the Room can set six microphones；Using the room of lying on one's side in the upper right corner in figure as the same area B, according to room of lying on one's side
Area two microphones can be set；, can according to the area of principal bedroom using the principal bedroom in the lower right corner in figure as the same area C
To set three microphones.Then, the acoustic information in region, bag are obtained by the multiple microphones being arranged in region
Include ambient noise and echo in region etc..
That is, ambient noise and echo etc. are collected respectively using the microphone being arranged at the same area diverse location
Data, and transmit to server.For example, can by all acoustic informations in six microphone collecting zone A in the A of region,
And the acoustic information being collected into is transmitted to server, wherein, in multiple microphones each microphone can have wired function and
Radio function, each microphone can by the server in wired ethernet access to LAN, can also by WIFI, bluetooth,
The wireless way for transmitting such as Zigbee do not limit specifically here to server.
S102, server are parsed to the acoustic information of multiple microphones to extract the phonetic order information of user.
According to one embodiment of present invention, server parses to the acoustic information of multiple microphones, including：To sound
Message breath carries out echo cancellor and noise reduction process.
That is, server after the acoustic information of multiple microphones is received, is made an uproar by a series of algorithm
The separation and elimination of sound, to obtain effective phonetic order information.For example, five microphones in room A can be collected into
Acoustic information is as reference noise, returning in the acoustic information for being then collected into the 6th microphone by sef-adapting filter
Sound and noise etc. are filtered out, to obtain effective phonetic order information；Or first each microphone in room A is collected
After the acoustic information arrived carries out echo cancellor, noise reduction and filtering process, the acoustic information after processing is then subjected to synthesis point
Analyse to obtain effective phonetic order information.It can specifically be handled using algorithm of the prior art, I will not elaborate.
S103, server need the household electrical appliance and household electrical appliance of control according to corresponding to determining the phonetic order information of user
Corresponding command information.
Specifically, server further obtains after effective phonetic order information is obtained according to phonetic order information
Command information corresponding to the title of household electrical appliance and household electrical appliance in phonetic order.
For example, when the phonetic order information that user sends is " opening curtain ", the entitled window of corresponding household electrical appliance
Curtain, corresponding command information are open command；When the phonetic order information that user sends is " closing sound equipment ", corresponding family expenses
The entitled sound equipment of electrical equipment, corresponding command information are out code；When the phonetic order information that user sends is " machine of sweeping the floor
People sweeps the floor " when, the entitled sweeping robot of corresponding household electrical appliance, corresponding command information instructs to start working.
S104, server send command information corresponding to household electrical appliance to household electrical appliance, to control household electrical appliance to perform
Respective operations.
Specifically, the title of household electrical appliance of the server in phonetic order information is got and corresponding command information
Afterwards, command information by wired mode or is sent wirelessly to household electrical appliance, to control corresponding to household electrical appliance execution
Operation, phonetic order control is realized, improve hommization experience.
For example, when the phonetic order information that user sends is " opening curtain ", server will send open command to window
Curtain, to control curtain opening；When the phonetic order information that user sends is " closing sound equipment ", server sends out code extremely
Sound equipment, to control sound equipment to close；When the phonetic order information that user sends is " sweeping robot is swept the floor ", server sends and opened
Beginning work order is to sweeping robot, so that sweeping robot starts to sweep the floor.
Sound control method based on multi-microphone according to embodiments of the present invention, by being arranged on the multiple of the same area
Microphone suppresses interference noise, i.e., all sound in the region are collected by the multiple microphones being arranged in the same area
Information, including ambient noise and wall resilience noise etc., noise separation and elimination are then carried out by series of algorithms, so as to carry
Effective phonetic order information is taken out, and household electrical appliance are controlled according to phonetic order information, can not only be effectively improved
Phonetic recognization rate, and server greatly reduces later maintenance cost without setting special parameter according to specific environment.
In view of in practical application, when multiple microphones while uploading data to server, in fact it could happen that bandwidth congestion is existing
As therefore, in an embodiment of the present invention, the acoustic information that first can be collected into each microphone judges, if sound
Message breath meets certain requirements, then the acoustic information uploads onto the server again, is caused with reducing because uploading more data simultaneously
Bandwidth congestion phenomenon occurs.
It can also include the steps of as shown in figure 3, being somebody's turn to do the sound control method based on multi-microphone：
S301, the decibel and frequency of the acoustic information that each microphone detection in multiple microphones is collected into, and judge
Whether whether the decibel of acoustic information is more than default decibel, and judge the frequency of acoustic information in the range of predeterminated frequency.
S302 is right if the decibel of acoustic information is more than the frequency of default decibel and acoustic information within a preset range
The microphone answered sends acoustic information to server.Wherein, presetting decibel and preset range can be set according to actual conditions
It is fixed.
Specifically, as shown in Fig. 2 when having sound in the A of region, six microphones in the A of region can automatic detection sound
The size (decibel) of sound, and judge the sound whether in the range of voice.If sound is bigger, such as：The decibel of acoustic information
More than default decibel, and the sound is in the range of voice, such as：The frequency of acoustic information within a preset range, then microphone from
It is dynamic that acoustic information uploads onto the server, so that multiple microphones only transmit more effective part, reduce to transmission belt
Wide requirement, reduce the dissection process time of server, improve response speed.
It is understood that in an embodiment of the present invention, multiple microphones can be arranged in household electrical appliance, to increase
The disguise of strong whole equipment group, the aesthetics of interior is improved, improves Consumer's Experience.
Sound control method based on multi-microphone according to embodiments of the present invention, acoustic information is collected into microphone
When, also whether the automatic detection acoustic information meets certain requirements, if it is satisfied, the acoustic information uploads onto the server again,
So that multiple microphones only transmit more effective part, reduce the requirement to transmission bandwidth, reduce server process
Time, improve response speed.Moreover, by the way that multiple microphones are arranged in different household electrical appliance, enhance and entirely set
The disguise of standby group, improves the aesthetics of interior, improves Consumer's Experience.
Fig. 4 is the structural representation of microphone according to an embodiment of the invention.As shown in figure 4, microphone 100 wraps
Include：Sound collecting module 110, communication module 120, judge module 130 and sending module 140.
Wherein, the acoustic information that sound collecting module 110 is used in collecting zone.Communication module 120 is used for and server
Establish communication connection.Judge module 130 is connected with sound collecting module 110, and judge module 130 is used for point for judging acoustic information
Whether whether shellfish is more than default decibel, and judge the frequency of acoustic information in the range of predeterminated frequency.Sending module 140 respectively with
Judge module 130, communication module 120 are connected with sound collecting mould 110, and sending module 140 is big for the decibel in acoustic information
When the frequency of decibel and acoustic information is preset within a preset range, pass through communication module 120 and send acoustic information to server.
Specifically, microphone 100 can not only be collected into the normal one's voice in speech information of people when collecting acoustic information, and
And acoustic information that animal, television set etc. are sent etc. can be collected into, if now directly by the acoustic information being collected into send to
Server is handled, it will the processing task amount of server is greatly increased, especially when multiple microphones send sound simultaneously
Information can not only increase the processing time of server, reduce response speed, and can cause broadband congestion problems to server.
Therefore, in an embodiment of the present invention, after sound collecting module 110 is collected into acoustic information, do not send out directly
The acoustic information of collection is sent to server, but first passes through judge module 130 and judges whether the acoustic information meets certain requirements,
Including judging whether the decibel (size) of the acoustic information is more than default decibel, and judge the acoustic information frequency whether
In preset range.If the acoustic information is met certain requirements, then the acoustic information is sent to clothes by communication module 120
Business device.So that microphone only transmits more effective part, reduce the transmission quantity of data, it is particularly same in multiple microphones
When transferring data to same server, avoid the bandwidth congestion phenomenon caused by mass data simultaneous transmission, reduce pair
The requirement of transmission bandwidth, and processing time and the processing task amount of server are further reduced, improve the sound of server
Answer speed.
It is understood that as shown in figure 5, communication module 120 may include：Wire communication submodule 121 and/or channel radio
Interrogate submodule 122.
Specifically, communication module 120 may include wire communication submodule 121, either wireless telecommunications submodule 122 or
Include wire communication submodule 121 and wireless telecommunications submodule 122 simultaneously.Sending module 140 can pass through wire communication submodule
Server in 121 (such as wired ethernet) access to LAN, wireless telecommunications submodule 122 (such as WIFI, indigo plant can also be passed through
Tooth, Zigbee etc.) send data to server.
Microphone according to embodiments of the present invention, after the acoustic information in sound collecting module collection to region, not
Server is sent directly to, but first passes through judge module and judges whether the decibel of acoustic information is more than default decibel, and is judged
Whether the frequency of acoustic information is in the range of predeterminated frequency, if the decibel of acoustic information is more than default decibel and acoustic information
Frequency within a preset range, then sending module by communication module in a wired fashion or wireless mode send acoustic information to take
Business device, so that microphone only transmits more effective part, reduces the transmission quantity of data, particularly same in multiple microphones
When transferring data to same server, avoid the bandwidth congestion phenomenon caused by mass data simultaneous transmission, reduce pair
The requirement of transmission bandwidth, and processing time and the processing task amount of server are further reduced, improve the sound of server
Answer speed.
Fig. 6 is the structural representation of server according to an embodiment of the invention.As shown in fig. 6, server 200 wraps
Include：Receiving module 210, extraction module 220, acquisition module 230 and control module 240.
Wherein, receiving module 210 is used to receive the area that the multiple microphones being arranged at the same area diverse location are collected
Acoustic information in domain.Extraction module 220 is used to parse to extract the voice of user the acoustic information of multiple microphones
Command information.Acquisition module 230 is used for household electrical appliance and the family that control is needed according to corresponding to determining the phonetic order information of user
Command information corresponding to electrical appliance.Control module 240 is used to send command information corresponding to household electrical appliance to household electrical appliance, with
Household electrical appliance are controlled to perform respective operations.
Specifically, because requirement of the speech recognition to environment is higher, echo in ambient noise and region etc. can influence language
The quality of sound identification, therefore, more than two microphones can be set according to field condition in the same area, to suppress dry
Disturb noise.
As shown in Fig. 2 can be using dining room and parlor as the same area A, can according to the area and structure in dining room and parlor
To set six microphones；Using the room of lying on one's side in the upper right corner in figure as the same area B, two can be set according to the area for room of lying on one's side
Individual microphone；Using the principal bedroom in the lower right corner in figure as the same area C, three Mikes can be set according to the area of principal bedroom
Wind.Then, the acoustic information in region, including the environment in region are obtained by the multiple microphones being arranged in region
Noise and echo etc., and send it to server 200.
Further, according to one embodiment of present invention, extraction module 220 is carried out to the acoustic information of multiple microphones
Parsing, including：Echo cancellor and noise reduction process are carried out to acoustic information.That is, receive multiple wheats in receiving module 210
After the acoustic information of gram wind, extraction module 220 will carry out the separation and elimination of noise by a series of algorithm, to obtain effectively
Phonetic order information, specifically can use algorithm of the prior art carry out noise separation and elimination, I will not elaborate.
After extraction module 220 extracts effective phonetic order information, acquisition module 230 will be according to phonetic order information
Further obtain phonetic order in household electrical appliance title and household electrical appliance corresponding to command information, then, control module 240 will
Command information is by wired mode or is sent wirelessly to household electrical appliance, to control household electrical appliance to perform corresponding operation,
Phonetic order control is realized, improves hommization experience.
For example, when the phonetic order information that user sends is " opening curtain ", acquisition module 230 gets corresponding family
The entitled curtain of electrical appliance, corresponding command information are open command, and control module 240 sends open command to curtain, with
Control curtain opening；When the phonetic order information that user sends is " closing sound equipment ", acquisition module 230 gets corresponding family
The entitled sound equipment of electrical appliance, corresponding command information are out code, and control module 240 sends out code to sound equipment, with
Sound equipment is controlled to close；When the phonetic order information that user sends is " sweeping robot is swept the floor ", acquisition module 230 is got pair
The entitled sweeping robot for the household electrical appliance answered, corresponding command information instruct to start working, and control module 240 sends and opened
Beginning work order is to sweeping robot, so that sweeping robot starts to sweep the floor.
Server according to embodiments of the present invention, it is arranged on by receiving module reception more at the same area diverse location
The acoustic information in region that individual microphone is collected, then, extraction module the acoustic information of multiple microphones is parsed with
The phonetic order information of user is extracted, acquisition module needs the household electric of control according to corresponding to determining the phonetic order information of user
Command information corresponding to device and household electrical appliance, finally, control module send command information corresponding to household electrical appliance to household electric
Device, to control household electrical appliance to perform respective operations.The server is believed by the sound collected to multiple microphones of the same area
Breath is parsed, and to remove interference noise, is extracted effective phonetic order information, is effectively increased phonetic recognization rate, avoid
In correlation technique, environment becomes, and parameter becomes, then needs manual test to redefine the technical problem of parameter, after greatly reducing
The maintenance cost of phase.
Fig. 7 is the block diagram of the speech control system according to an embodiment of the invention based on multi-microphone.Such as
Shown in Fig. 7, the speech control system based on multi-microphone includes：Multiple microphones 100 and server 200.
Specifically, multiple microphones 100 are arranged at the same area diverse location, and multiple microphones 100 are used for collecting region
Acoustic information in domain.
Because requirement of the speech recognition to environment is higher, echo in ambient noise and region etc. can influence speech recognition
Quality, therefore, in an embodiment of the present invention, more than two Mikes can be set according to field condition in the same area
Wind 100, to suppress interference noise.
In actual applications, as shown in Fig. 2 can be using dining room and parlor as the same area A, according to dining room and parlor
Area and structure can set six microphones 100；Using the room of lying on one's side in the upper right corner in figure as the same area B, according to room of lying on one's side
Area two microphones 100 can be set；Using the principal bedroom in the lower right corner in figure as the same area C, according to the face of principal bedroom
Product can set three microphones 100.Then, obtained by the multiple microphones 100 being arranged in region in region
Ambient noise and echo in acoustic information, including region etc., and transmit to server 200.
For example, can be by all acoustic informations in the collecting zone A of six microphones 100 in the A of region, and will be collected into
Acoustic information transmit to server 200, wherein, each microphone 100 can have wired function and nothing in multiple microphones 100
Line function, each microphone 100 can also pass through WIFI, indigo plant by the server 200 in wired ethernet access to LAN
The wireless way for transmitting such as tooth, Zigbee do not limit specifically here to server 200.
Server 200 receives the acoustic information of multiple microphones 100, and the acoustic information of multiple microphones 100 is carried out
Parse to extract the phonetic order information of user, and the household electric of control is needed according to corresponding to determining the phonetic order information of user
Command information corresponding to device 300 and household electrical appliance 300, and command information corresponding to household electrical appliance 300 is sent to household electric
Device 300, to control household electrical appliance 300 to perform respective operations.
According to one embodiment of present invention, server 200 parses to the acoustic information of multiple microphones 100, bag
Include：Echo cancellor and noise reduction process are carried out to acoustic information.That is, server 200 is receiving multiple microphones 100
After acoustic information, the separation and elimination of noise are carried out by a series of algorithm, to obtain effective phonetic order information, specifically
Algorithm of the prior art can be used to carry out the separation and elimination of noise, I will not elaborate.
After server 200 extracts effective phonetic order information, voice is further obtained according to phonetic order information
Command information corresponding to the title of household electrical appliance 300 and household electrical appliance 300 in instruction, then, server 200 leads to command information
Cross wired mode or be sent wirelessly to household electrical appliance 300, to control household electrical appliance 300 to perform corresponding operation, realize
Phonetic order controls, and improves hommization experience.
For example, when the phonetic order information that user sends is " opening curtain ", server 200 gets corresponding family expenses
The entitled curtain of electrical equipment 300, corresponding command information are open command, open command are then sent to curtain, to control window
Curtain is opened；When the phonetic order information that user sends is " closing sound equipment ", server 200 gets corresponding household electrical appliance
300 entitled sound equipment, corresponding command information are out code, out code are then sent to sound equipment, to control sound equipment to close
Close；When the phonetic order information that user sends is " sweeping robot is swept the floor ", server 200 gets corresponding household electrical appliance
300 entitled sweeping robot, corresponding command information instruct to start working, and then send instruction of starting working to sweeping the floor
Robot, so that sweeping robot starts to sweep the floor.
Speech control system based on multi-microphone according to embodiments of the present invention, by being arranged on the multiple of the same area
Microphone suppresses interference noise, i.e., the sound collected by the multiple microphones being arranged in the same area in the region believes
Breath, including ambient noise and wall resilience noise etc., then server noise separation and elimination are carried out by series of algorithms, from
And effective phonetic order information is extracted, and household electrical appliance are controlled according to phonetic order information, not only can be effective
Phonetic recognization rate is improved, and without setting special parameter according to specific environment, greatly reduces later maintenance cost.
In view of in practical application, when multiple microphones 100 while uploading data to server 200, in fact it could happen that bandwidth
Jam, therefore, in an embodiment of the present invention, the acoustic information that first can be collected into each microphone 100 is sentenced
It is disconnected, if acoustic information meets certain requirements, then uploads onto the server 200 by the acoustic information, to reduce because uploading simultaneously
More data cause bandwidth congestion phenomenon to occur.
According to one embodiment of present invention, each microphone 100 in multiple microphones 100 detects the sound being collected into
The decibel and frequency of information, and judge whether the decibel of acoustic information is more than default decibel, and judge the frequency of acoustic information
Whether within a preset range, wherein, if the decibel of acoustic information is more than the frequency of default decibel and acoustic information in default model
In enclosing, then acoustic information is sent to server 200.
Specifically, as shown in Fig. 2 when region A has sound, six microphones 100 in the A of region can automatic detection sound
The size (decibel) of sound, and judge the sound whether in the range of voice.If sound is bigger, such as：The decibel of acoustic information
More than default decibel, and the sound is in the range of voice, such as：The frequency of acoustic information within a preset range, then microphone 100
Automatically acoustic information is uploaded onto the server 200, so that multiple microphones only transmit more effective part, reduced to passing
The requirement of defeated bandwidth, reduce the dissection process time of server, improve response speed.
It is understood that in an embodiment of the present invention, multiple microphones 100 can be arranged on household electrical appliance 300
In, to strengthen the disguise of whole equipment group, the aesthetics of interior is improved, improves Consumer's Experience.
Speech control system based on multi-microphone according to embodiments of the present invention, acoustic information is collected into microphone
When, also whether the automatic detection acoustic information meets certain requirements, if it is satisfied, the acoustic information uploads onto the server again,
So that multiple microphones only transmit more effective part, reduce the requirement to transmission bandwidth, reduce server process
Time, improve response speed.Moreover, by the way that multiple microphones are arranged in different household electrical appliance, enhance and entirely set
The disguise of standby group, improves the aesthetics of interior, improves Consumer's Experience.
In the description of the invention, it is to be understood that term " first ", " second " are only used for describing purpose, and can not
It is interpreted as indicating or implies relative importance or imply the quantity of the technical characteristic indicated by indicating.Thus, define " the
One ", at least one this feature can be expressed or be implicitly included to the feature of " second ".In the description of the invention, " multiple "
It is meant that at least two, such as two, three etc., unless otherwise specifically defined.
In the present invention, unless otherwise clearly defined and limited, term " installation ", " connected ", " connection ", " fixation " etc.
Term should be interpreted broadly, for example, it may be fixedly connected or be detachably connected, or integrally；Can be that machinery connects
Connect or electrically connect；Can be joined directly together, can also be indirectly connected by intermediary, can be in two elements
The connection in portion or the interaction relationship of two elements, limited unless otherwise clear and definite.For one of ordinary skill in the art
For, the concrete meaning of above-mentioned term in the present invention can be understood as the case may be.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.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 different embodiments or example and the feature of different embodiments or example described in this specification
Close and combine.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, changed, replacing and modification.
Claims (11)
1. a kind of sound control method based on multi-microphone, it is characterised in that comprise the following steps：
Server receives the acoustic information in the region that the multiple microphones being arranged at the same area diverse location are collected；
The server is parsed to the acoustic information of the multiple microphone to extract the phonetic order information of the user；
The server needs the household electrical appliance and household electrical appliance of control according to corresponding to determining the phonetic order information of the user
Corresponding command information；And
The server sends command information corresponding to the household electrical appliance to the household electrical appliance, to control the household electric
Device performs respective operations.
2. the sound control method according to claim 1 based on multi-microphone, it is characterised in that the server is to institute
The acoustic information for stating multiple microphones is parsed, including：Echo cancellor and noise reduction process are carried out to the acoustic information.
3. the sound control method according to claim 1 or 2 based on multi-microphone, it is characterised in that also include：
The decibel and frequency for the acoustic information that each microphone detection in the multiple microphone is collected into, and judge the sound
Whether whether the decibel of message breath is more than default decibel, and judge the frequency of the acoustic information in the range of predeterminated frequency；
If the decibel of the acoustic information is more than the frequency of the default decibel and the acoustic information in the preset range
Interior, then corresponding microphone sends the acoustic information to the server.
4. the sound control method according to claim 1 based on multi-microphone, it is characterised in that the multiple microphone
It is arranged in the household electrical appliance.
A kind of 5. microphone, it is characterised in that including：
Sound collecting module, the acoustic information that the sound collecting module is used in collecting zone；
Communication module, the communication module are used to establish communication connection with server；
Judge module, the judge module are connected with the sound collecting module, and the judge module is used to judge the sound
Whether whether the decibel of information is more than default decibel, and judge the frequency of the acoustic information in the range of predeterminated frequency；
Sending module, the sending module respectively with the judge module, the communication module and the sound collecting module phase
Even, the sending module is used to more than the frequency of the default decibel and the acoustic information exist in the decibel of the acoustic information
When in the preset range, the acoustic information is sent to the server by the communication module.
A kind of 6. server, it is characterised in that including：
Receiving module, the sound in the region collected for receiving the multiple microphones being arranged at the same area diverse location
Message ceases；
Extraction module, believed for being parsed to the acoustic information of the multiple microphone with extracting the phonetic order of the user
Breath；
Acquisition module, for needing the household electrical appliance and household electric of control according to corresponding to the determination of the phonetic order information of the user
Command information corresponding to device；And
Control module, for command information corresponding to the household electrical appliance to be sent to the household electrical appliance, to control the family
Electrical appliance performs respective operations.
7. server according to claim 6, it is characterised in that sound of the extraction module to the multiple microphone
Information is parsed, including：Echo cancellor and noise reduction process are carried out to the acoustic information.
A kind of 8. speech control system based on multi-microphone, it is characterised in that including：
The multiple microphones being arranged at the same area diverse location, the multiple microphone are used to collect the sound in the region
Message ceases；
Server, the server are used for the acoustic information for receiving the multiple microphone, and to the sound of the multiple microphone
Message breath is parsed to extract the phonetic order information of the user, and according to the determination pair of the phonetic order information of the user
Command information corresponding to the household electrical appliance and household electrical appliance of the need control answered, and by command information corresponding to the household electrical appliance
Send to the household electrical appliance, to control the household electrical appliance to perform respective operations.
9. the speech control system according to claim 8 based on multi-microphone, it is characterised in that the server is to institute
The acoustic information for stating multiple microphones is parsed, including：Echo cancellor and noise reduction process are carried out to the acoustic information.
10. the speech control system based on multi-microphone according to claim 8 or claim 9, it is characterised in that the multiple wheat
The decibel and frequency for the acoustic information that each microphone detection in gram wind is collected into, and judge that the decibel of the acoustic information is
It is no to be more than default decibel, and whether within a preset range to judge the frequency of the acoustic information, wherein,
If the decibel of the acoustic information is more than the frequency of the default decibel and the acoustic information in the preset range
It is interior, then the acoustic information is sent to the server.
11. the speech control system according to claim 8 based on multi-microphone, it is characterised in that the multiple Mike
Wind is arranged in the household electrical appliance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610514013.XA CN107564515A (en) | 2016-06-30 | 2016-06-30 | Sound control method and system, microphone and server based on multi-microphone |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610514013.XA CN107564515A (en) | 2016-06-30 | 2016-06-30 | Sound control method and system, microphone and server based on multi-microphone |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107564515A true CN107564515A (en) | 2018-01-09 |
Family
ID=60968821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610514013.XA Pending CN107564515A (en) | 2016-06-30 | 2016-06-30 | Sound control method and system, microphone and server based on multi-microphone |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107564515A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108459510A (en) * | 2018-02-08 | 2018-08-28 | 百度在线网络技术（北京）有限公司 | Control method, equipment, system and the computer-readable medium of intelligent appliance |
| CN108461084A (en) * | 2018-03-01 | 2018-08-28 | 广东美的制冷设备有限公司 | Speech recognition system control method, control device and computer readable storage medium |
| CN109243456A (en) * | 2018-11-05 | 2019-01-18 | 珠海格力电器股份有限公司 | A kind of method and apparatus controlling equipment |
| CN109920416A (en) * | 2019-01-29 | 2019-06-21 | 珠海格力电器股份有限公司 | A kind of sound control method, device, storage medium and control system |
| WO2020024546A1 (en) * | 2018-08-01 | 2020-02-06 | 珠海格力电器股份有限公司 | Auxiliary speech control method and device and air conditioner |
| CN111696544A (en) * | 2019-03-14 | 2020-09-22 | 青岛海尔智能技术研发有限公司 | Control method of household appliance, household appliance and control device |
| CN112637208A (en) * | 2020-12-23 | 2021-04-09 | 美的集团股份有限公司 | Method for determining authority of target device, electronic device and computer readable storage medium |
| CN113724706A (en) * | 2021-09-06 | 2021-11-30 | 云知声（上海）智能科技有限公司 | Voice control method and system for multi-level space |
| CN114343483A (en) * | 2020-10-12 | 2022-04-15 | 百度在线网络技术（北京）有限公司 | Method, device and equipment for controlling movable object and storage medium |
| CN114453302A (en) * | 2022-02-10 | 2022-05-10 | 安徽心惢网络科技有限公司 | Intelligent household control system based on voice control |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000194394A (en) * | 1998-12-25 | 2000-07-14 | Kojima Press Co Ltd | Voice recognition controller |
| CN103491488A (en) * | 2013-09-30 | 2014-01-01 | 天脉聚源(北京)传媒科技有限公司 | Echo cancellation method and device for microphone |
| CN105206275A (en) * | 2015-08-31 | 2015-12-30 | 小米科技有限责任公司 | Device control method, apparatus and terminal |
| CN105242556A (en) * | 2015-10-28 | 2016-01-13 | 小米科技有限责任公司 | A speech control method and device of intelligent devices, a control device and the intelligent device |
| CN105427861A (en) * | 2015-11-03 | 2016-03-23 | 胡旻波 | Cooperated microphone voice control system and method of intelligent household |
-
2016
- 2016-06-30 CN CN201610514013.XA patent/CN107564515A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000194394A (en) * | 1998-12-25 | 2000-07-14 | Kojima Press Co Ltd | Voice recognition controller |
| CN103491488A (en) * | 2013-09-30 | 2014-01-01 | 天脉聚源(北京)传媒科技有限公司 | Echo cancellation method and device for microphone |
| CN105206275A (en) * | 2015-08-31 | 2015-12-30 | 小米科技有限责任公司 | Device control method, apparatus and terminal |
| CN105242556A (en) * | 2015-10-28 | 2016-01-13 | 小米科技有限责任公司 | A speech control method and device of intelligent devices, a control device and the intelligent device |
| CN105427861A (en) * | 2015-11-03 | 2016-03-23 | 胡旻波 | Cooperated microphone voice control system and method of intelligent household |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108459510A (en) * | 2018-02-08 | 2018-08-28 | 百度在线网络技术（北京）有限公司 | Control method, equipment, system and the computer-readable medium of intelligent appliance |
| CN108461084A (en) * | 2018-03-01 | 2018-08-28 | 广东美的制冷设备有限公司 | Speech recognition system control method, control device and computer readable storage medium |
| WO2020024546A1 (en) * | 2018-08-01 | 2020-02-06 | 珠海格力电器股份有限公司 | Auxiliary speech control method and device and air conditioner |
| CN109243456A (en) * | 2018-11-05 | 2019-01-18 | 珠海格力电器股份有限公司 | A kind of method and apparatus controlling equipment |
| CN109920416A (en) * | 2019-01-29 | 2019-06-21 | 珠海格力电器股份有限公司 | A kind of sound control method, device, storage medium and control system |
| CN111696544A (en) * | 2019-03-14 | 2020-09-22 | 青岛海尔智能技术研发有限公司 | Control method of household appliance, household appliance and control device |
| CN114343483A (en) * | 2020-10-12 | 2022-04-15 | 百度在线网络技术（北京）有限公司 | Method, device and equipment for controlling movable object and storage medium |
| CN114343483B (en) * | 2020-10-12 | 2023-08-18 | 百度在线网络技术（北京）有限公司 | Control method, device, equipment and storage medium for movable object |
| CN112637208A (en) * | 2020-12-23 | 2021-04-09 | 美的集团股份有限公司 | Method for determining authority of target device, electronic device and computer readable storage medium |
| CN113724706A (en) * | 2021-09-06 | 2021-11-30 | 云知声（上海）智能科技有限公司 | Voice control method and system for multi-level space |
| CN114453302A (en) * | 2022-02-10 | 2022-05-10 | 安徽心惢网络科技有限公司 | Intelligent household control system based on voice control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107564515A (en) | Sound control method and system, microphone and server based on multi-microphone | |
| CN106162436A (en) | Player method based on multi-loudspeaker and system | |
| CN105957519B (en) | Method and system for simultaneously performing voice control on multiple regions, server and microphone | |
| CN104216351B (en) | Household electrical appliance sound control method and system | |
| CN106707788B (en) | A kind of intelligent home voice control identifying system and method | |
| CN106921911B (en) | Voice acquisition method and device | |
| CN107741698A (en) | The inter-linked controlling method of intelligent appliance and access control equipment, device and system | |
| CN104966344A (en) | Security entrance guard system based on video | |
| EP1499085A3 (en) | Method and apparatus for protocol conversion. | |
| CN107249173B (en) | A kind of method for handover control and system of Internet of Things communication pattern | |
| CN106128459A (en) | Phonetic controller and sound control method based on multi-microphone | |
| CN106642547A (en) | Controlling method of air conditioner and air conditioner | |
| CN102710342A (en) | Distributed examination room radio cheating counter measure equipment | |
| CN107845388B (en) | Voice recognition method and device | |
| CN104767960A (en) | WeChat building video intercom system and communication method thereof | |
| CN108986405A (en) | A kind of multi parameters control method based on Zigbee gateway | |
| CN201341189Y (en) | New generation HD web camera, audio/video monitoring system and video conference system | |
| CN109788238A (en) | Empty nestor's safe condition monitors system | |
| CN111541504B (en) | Command communication interference effect evaluation system based on radio station information acquisition terminal | |
| CN206322314U (en) | Intelligent electric appliance control system based on Bluetooth technology | |
| CN110011737A (en) | A kind of wireless screen transmission equipment connection setup interactive mode | |
| CN205721138U (en) | A kind of household electrical appliances volume adjusting apparatus | |
| CN203574778U (en) | Intelligent doorbell and automatic control system for door lock | |
| EP3919831A1 (en) | Air conditioning system | |
| CN104052949B (en) | Volume adjusting method, device and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180109 |