CN207676649U - A kind of voice processing apparatus and smart machine based on 4 microphone linear array - Google Patents
A kind of voice processing apparatus and smart machine based on 4 microphone linear array Download PDFInfo
- Publication number
- CN207676649U CN207676649U CN201721053970.3U CN201721053970U CN207676649U CN 207676649 U CN207676649 U CN 207676649U CN 201721053970 U CN201721053970 U CN 201721053970U CN 207676649 U CN207676649 U CN 207676649U
- Authority
- CN
- China
- Prior art keywords
- signal
- voice
- module
- control instruction
- output
- 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.)
- Active
Links
Landscapes
- Circuit For Audible Band Transducer (AREA)
Abstract
The utility model embodiment provides a kind of voice processing apparatus and smart machine based on 4 microphone linear array, the voice processing apparatus is applied to smart machine, specifically include 4 microphones at the distribution of line shape, audio collection module, reference audio receiving module, control instruction receiving module, processor, voice output module and wake-up command output module.Wherein, audio collection module is connected with 4 microphones respectively, processor then respectively with audio collection module, reference audio receiving module, control instruction receiving module, voice output module is connected, for being handled the collected multipath audio signal of audio collection module according to the control instruction and reference audio signal that receive, it can be exported to smart machine and wake up control signal, it can also access and export clearly voice signal to smart machine, it can solve the problems, such as that it can not understand when apart from user farther out when being applied on smart machine and obtain the sent out voice of user.
Description
Technical field
The utility model is related to audio signal processing technique fields, more particularly to a kind of language based on 4 microphone linear array
Sound processor and smart machine.
Background technology
Now, various smart machines are increasingly entering in our life, study and work, including domestic appliance
People, smart television, intelligent sound box, intelligent refrigerator, intelligent air condition, intelligent vehicle device etc., have brought great convenience.These
Smart machine also has interactive function substantially, and user only needs that the control to smart machine can be realized by voice.
Realize that carrying out voice control to smart machine needs clearly to collect the voice that user is sent out, then to language
Sound is parsed and is handled, and is instructed accordingly, is then controlled smart machine according to instruction, to realize user
The purpose that smart machine is controlled with voice.However, current smart machine on pair and its closer sent out language of user of distance
The acquisition of sound is more clear, is not so problem for smart mobile phone and tablet computer, however for generally apart from user compared with
For remote intelligent appliance, because voice decaying is larger, lead to not clearly get the sent out voice of user, to make intelligence
Equipment can not accordingly be operated according to the voice of user, and voice control is caused to fail.
Utility model content
In view of this, the utility model provides a kind of voice processing apparatus and intelligence based on 4 microphone linear array
Equipment obtains the sent out voice of user to solve the problems, such as that smart machine can not understand when apart from user farther out.
To solve the above-mentioned problems, the utility model discloses a kind of, and the speech processes based on 4 microphone linear array fill
It sets, is applied to smart machine, the speech processing module includes 4 microphones at the distribution of line shape, audio collection module, reference
Audio receiving module, control instruction receiving module, processor, voice output module and wake-up command output module, wherein：
The audio collection module is connected with 4 microphones respectively, defeated for acquiring each microphone institute
The audio signal gone out, and pass through its signal output end output multi-channel audio signal；
The reference audio receiving module exports the ginseng for receiving reference audio signal, and by its signal output end
Examine audio signal；
The control instruction receiving module exports the control by its instruction output end and refers to for receiving control instruction
It enables；
The processor is provided with first input end, the second input terminal and third input terminal；
The first input end is connected with the signal output end of the audio collection module, for receiving the multichannel sound
Frequency signal, second input terminal is connected with the signal output end of the reference audio signal input module, for receiving
Reference audio signal is stated, the third input terminal is connected with the signal output end of the control instruction receiving module, for connecing
Receive the control instruction；
The processor is additionally provided with the first output end and second output terminal；
First output end is configured to according to the control instruction, the reference audio signal and the MCVF multichannel voice frequency
Signal output wakes up control signal；
The second output terminal is configured to be believed according to reference audio signal described in the control instruction and the MCVF multichannel voice frequency
Number output is by default treated voice signal；
The wake-up output module is connected with first output end, for according to wake-ups control signal to described
The wake-up module of smart machine exports predetermined level signal；
The voice output module is connected with the second output terminal, for receiving the voice signal, and will be described
Voice signal is output to the phonetic incepting equipment of the smart machine.
Optionally, 4 eolian horizontal linears of Mike are uniformly distributed.
Optionally, the distance between two neighboring described microphone is 35mm.
Optionally, the reference audio signal is 1 tunnel reference audio signal or 2 tunnel reference audio signals.
Optionally, the control instruction be wake up control instruction, echo cancellor control instruction, beam forming control instruction and
Some or all of in noise reduction control instruction.
Optionally, the voice signal is analog voice signal or audio digital signals.
In addition, the utility model additionally provides a kind of smart machine, it is provided with voice processing apparatus as described above.
It can be seen from the above technical proposal that the utility model provides a kind of voice based on 4 microphone linear array
Processing unit and smart machine, the voice processing apparatus are applied to smart machine, specifically include 4 Mikes at the distribution of line shape
Wind, audio collection module, reference audio receiving module, control instruction receiving module, processor, voice output module and wake-up refer to
Enable output module.Wherein, audio collection module is connected with 4 microphones respectively, processor then respectively with audio collection module,
Reference audio receiving module, control instruction receiving module, voice output module are connected, for according to the control instruction received
The collected multipath audio signal of audio collection module is handled with reference audio signal, can export and call out to smart machine
It wakes up and controls signal, additionally it is possible to the voice signal for obtaining and passing through to smart machine output default processing, since the utility model is adopted
With 4 microphones, 4 microphones can voice sent out to user in different directions be acquired, and area between signal
It can refer to not and mutually, can be obtained clearly voice signal after treatment, can be solved when being applied on smart machine
Certainly it can not understand the problem of obtaining user's sent out voice when apart from user farther out.
Description of the drawings
In order to illustrate the embodiment of the utility model or the technical proposal in the existing technology more clearly, below will be to embodiment
Or attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
It is some embodiments of the utility model, for those of ordinary skill in the art, in the premise not made the creative labor
Under, other drawings may also be obtained based on these drawings.
Fig. 1 is a kind of structural frames of voice processing apparatus embodiment based on 4 microphone linear array of the utility model
Figure.
Specific implementation mode
The following will be combined with the drawings in the embodiments of the present invention, carries out the technical scheme in the embodiment of the utility model
Clearly and completely describe, it is clear that the described embodiments are only a part of the embodiments of the utility model, rather than whole
Embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are without making creative work
The every other embodiment obtained, shall fall within the protection scope of the present invention.
Embodiment one
Fig. 1 is a kind of structural frames of the voice processing apparatus embodiment based on 4 microphone linear arrays provided by the invention
Figure.
Voice processing apparatus shown in referring to Fig.1 is applied to the smart machines such as smart mobile phone, intelligent appliance, intelligent vehicle device
On, the voice for being sent out in medium and long distance acquisition user, the device is provided with the linear array of 4 microphones composition, the dress
It sets and specifically includes 4 into the microphone 10 of linear branch, audio collection module 20, reference audio receiving module 30, control instruction
Receiving module 40, processor 50, voice output module 60 and wake-up command output module 70.
Above-mentioned processor occupy center, is provided with first input end 51, the second input terminal 52, third input terminal 53,
One output end 54 and second output terminal.First input end is connected with the signal output end of audio collection module, the second input terminal
It is connected with the signal output end of reference audio receiving module, third input terminal is then inputted with the signal of control instruction receiving module
End is connected；First output end is then connected with wake-up command output module, and second output terminal is then connected with voice output module
It connects.
The eolian linear branch of 4 Mikes, the horizontal linear constituted, the practical sound for 4 microphones of above-mentioned straight line
The central point of frequency input part is constituted；Plane at the straight line is horizontality, and two microphones of arbitrary neighborhood it
Between distance be identical, apart from preferred 35mm.And 4 microphones generate multipath audio signal at work.
Audio collection module is connected with 4 microphones respectively, for acquiring MCVF multichannel voice frequency caused by this 4 microphones
Signal, and be output to by its signal output end the first input end of processor, that is, it is output to the processor.
Reference audio receiving module is used to receive the reference audio signal of the acoustic component output of smart machine, called reference
Audio signal refers to that smart machine yearns for the sound sent in the course of work, so that processor can be according to the reference audio signal
Back elimination processing is carried out to microphone the received audio signal, itself is played to eliminate ambient noise, smart machine
Sound and smart machine play sound caused by echo.Reference audio receiving module is receiving reference audio signal
The second input terminal of processor is output to by gas signal output end afterwards.In addition, the reference that the reference audio receiving module receives
Audio signal can be 1 tunnel reference audio signal, can also be 2 tunnel reference audio signals.
Control instruction receiving module is used to receive its control instruction exported from the master control system of smart machine, and passes through it
Signal output end is output to the third input terminal of processor.Control instruction include wake up control instruction, echo cancellor control instruction,
Beam forming control instruction or noise reduction control instruction；Can also be one such, a variety of or whole, or even including other
The control instruction that utility model is not mentioned.
Processor by its first input end, the second input terminal and third input terminal receive respectively multipath audio signal,
Reference audio signal and one or more control instructions.After receiving above-mentioned signal or instruction according to corresponding control instruction and
Reference audio signal handles above-mentioned multipath audio signal.Processing procedure believes MCVF multichannel voice frequency including the use of preset algorithm
Elimination noise number is carried out, echo is eliminated, eliminates the processing such as the sound that smart machine itself is sent out, to obtain after treatment
Voice signal.In addition, smart machine is determining the position for the person of issuing an order according to multipath audio signal and is sending out wave beam to the present apparatus
After shaping control instruction, processor forms enhancing wave beam to sounder direction, and inhibits the sound other than wave beam.
In addition, processor is additionally operable to according to above-mentioned wake-up control instruction and reference audio signal to above-mentioned multipath audio signal
Handled, obtain waking up control signal, wake-up control signal be used to make the wake-up module of smart machine to smart machine into
Row wake operation.
Algorithm that the above processor is handled multipath audio signal according to control instruction and reference audio signal, program
It is the prior art with processing procedure, those skilled in the art can be according to above-metioned instruction, audio without making creative work
Signal obtains above-mentioned corresponding voice signal, and therefore, scheme provided herein is not the improvement made to computer program,
Its protection domain complies fully with the regulation of Patent Law and detailed rules for the implementation to utility model.
First output end of processor is used to, to the above-mentioned wake-up control signal of command output module output is waken up, wake up instruction
Output module is connected in actual embodiment with the wake-up module of smart machine, and after receiving wake-up control signal
The wake-up signal of predetermined level, such as output high level or low level are exported to wake-up module, specific choice needs basis to call out
Depending on the specific operation level of module of waking up.The purpose of voice wake-up smart machine can be utilized thereby using family.
The second output terminal of processor is used to export the voice signal obtained by above-mentioned processing to voice output module.It should
Voice signal can be analog voice signal, can also be audio digital signals, when selecting audio digital signals, can utilize
The IIS way of outputs are output to the smart machine.
Find out in terms of above-mentioned technical proposal, present embodiments provides a kind of speech processes based on 4 microphone linear array
Device, the voice processing apparatus are applied to smart machine, specifically include 4 microphones at the distribution of line shape, audio collection module,
Reference audio receiving module, control instruction receiving module, processor, voice output module and wake-up command output module.Wherein,
Audio collection module is connected with 4 microphones respectively, and processor then receives mould with audio collection module, reference audio respectively
Block, control instruction receiving module, voice output module are connected, for according to the control instruction and reference audio signal received
The collected multipath audio signal of audio collection module is handled, can be exported to smart machine and wake up control signal, also
It can obtain and the voice signal to smart machine output by default processing, since the utility model uses 4 microphones, 4
A microphone can voice sent out to user in different directions be acquired, and different from and can mutually join between signal
It examines, can be obtained clearly voice signal after treatment, it can be solved when being applied on smart machine and is used in distance
Family farther out when can not understand the problem of obtaining user's sent out voice.
Embodiment two
A kind of smart machine is present embodiments provided, which can be smart mobile phone, tablet computer, intelligent vehicle device
Equal mobile terminal devices can also be the intelligence such as smart television, domestic robot, intelligent air condition, intelligent refrigerator, intelligent washing machine
Household appliance.The smart machine is provided with the speech processes dress based on 4 microphone linear array that an embodiment as above is provided
It sets.The size of the module is long 32mm, and wide 24mm, high 3mm are convenient to be integrated into smart machine.
The device includes 4 microphones at the distribution of line shape, and audio collection module, reference audio receiving module, control refer to
It enables receiving module, processor, voice output module and wakes up command output module.Audio collection module respectively with 4 microphones
It is connected, the multipath audio signal exported for acquiring microphone, and by its signal output end to processor output multi-channel
Audio signal.
Reference audio receiving module is output to processor for receiving reference audio signal；Control instruction receiving module
For receiving control instruction input by user, and it is output to processor.Processor is used for according to control instruction, states reference audio letter
Number and multipath audio signal to wake up output module output wake up control signal；Processor is additionally operable to according to control instruction, reference
Audio signal and multipath audio signal output are by default treated voice signal.4 microphones can be in different directions
Voice sent out to user is acquired, and different from and can mutually be referred between signal, and it is clear to can be obtained after treatment
Voice signal so that this smart machine can solve it and when apart from user farther out can not understand to obtain user sent out voice
Problem.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiment, the same or similar parts between the embodiments can be referred to each other.
Although having been described that the preferred embodiment of the utility model embodiment, those skilled in the art are once learnt
Basic creative concept, then additional changes and modifications can be made to these embodiments.So appended claims are intended to solve
It is interpreted as including preferred embodiment and falling into all change and modification of the utility model embodiment range.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also include other elements that are not explicitly listed, or further include for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device including the element.
Technical solution provided by the utility model is described in detail above, specific case pair used herein
The principles of the present invention and embodiment are expounded, and the explanation of above example is only intended to help to understand that this practicality is new
The method and its core concept of type；Meanwhile having according to the thought of the utility model for those of ordinary skill in the art
There will be changes in body embodiment and application range, in conclusion the content of the present specification should not be construed as to this practicality
Novel limitation.
Claims (7)
1. a kind of voice processing apparatus based on 4 microphone linear arrays is applied to smart machine, which is characterized in that institute's predicate
Sound processing module includes the microphone of 4 linear distributions, and audio collection module, reference audio receiving module, control instruction connect
It receives module, processor, voice output module and wakes up command output module, wherein：
The audio collection module is connected with 4 microphones respectively, is exported for acquiring each microphone
Audio signal, and pass through its signal output end output multi-channel audio signal；
The reference audio receiving module refers to sound for receiving reference audio signal, and by the way that the output of its signal output end is described
Frequency signal；
The control instruction receiving module exports the control instruction for receiving control instruction, and by its instruction output end；
The processor is provided with first input end, the second input terminal and third input terminal；
The first input end is connected with the signal output end of the audio collection module, for receiving the MCVF multichannel voice frequency letter
Number, second input terminal is connected with the signal output end of the reference audio signal input module, for receiving the ginseng
Audio signal is examined, the third input terminal is connected with the signal output end of the control instruction receiving module, for receiving
State control instruction；
The processor is additionally provided with the first output end and second output terminal；
First output end is configured to according to the control instruction, the reference audio signal and the multipath audio signal
Output wakes up control signal；
The second output terminal is configured to defeated according to reference audio signal described in the control instruction and the multipath audio signal
Go out by default treated voice signal；
The wake-up output module is connected with first output end, for controlling signal to the intelligence according to the wake-up
The wake-up module of equipment exports predetermined level signal；
The voice output module is connected with the second output terminal, for receiving the voice signal, and by the voice
Signal is output to the phonetic incepting equipment of the smart machine.
2. voice processing apparatus as described in claim 1, which is characterized in that 4 eolian horizontal linears of Mike uniformly divide
Cloth.
3. voice processing apparatus as claimed in claim 2, which is characterized in that the distance between two neighboring described microphone is
35mm。
4. voice processing apparatus as described in claim 1, which is characterized in that the reference audio signal is 1 tunnel reference audio
Signal or 2 tunnel reference audio signals.
5. voice processing apparatus as described in claim 1, which is characterized in that the control instruction is to wake up control instruction, return
Some or all of in sound elimination control instruction, beam forming control instruction and noise reduction control instruction.
6. voice processing apparatus as described in claim 1, which is characterized in that the voice signal is analog voice signal or number
Word voice signal.
7. a kind of smart machine, which is characterized in that be arranged just like claim 1~6 any one of them voice processing apparatus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721053970.3U CN207676649U (en) | 2017-08-22 | 2017-08-22 | A kind of voice processing apparatus and smart machine based on 4 microphone linear array |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721053970.3U CN207676649U (en) | 2017-08-22 | 2017-08-22 | A kind of voice processing apparatus and smart machine based on 4 microphone linear array |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN207676649U true CN207676649U (en) | 2018-07-31 |
Family
ID=62952925
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201721053970.3U Active CN207676649U (en) | 2017-08-22 | 2017-08-22 | A kind of voice processing apparatus and smart machine based on 4 microphone linear array |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN207676649U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109147787A (en) * | 2018-09-30 | 2019-01-04 | 深圳北极鸥半导体有限公司 | A kind of smart television acoustic control identifying system and its recognition methods |
-
2017
- 2017-08-22 CN CN201721053970.3U patent/CN207676649U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109147787A (en) * | 2018-09-30 | 2019-01-04 | 深圳北极鸥半导体有限公司 | A kind of smart television acoustic control identifying system and its recognition methods |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN207676650U (en) | A kind of voice processing apparatus and smart machine based on 6 microphone annular arrays | |
| CN106792415B (en) | A kind of test method and device for digital microphone array | |
| WO2019134473A1 (en) | Speech recognition system, method and apparatus | |
| CN105225681B (en) | Speech playing method and system | |
| US10785559B2 (en) | Method and device for switching play modes of wireless speaker, and wireless speaker | |
| CN108174320B (en) | A kind of adaptive ear canal active noise reduction earphone and adaptive ear canal active denoising method | |
| CN106775553A (en) | Sound-volume control system and method for controlling volume | |
| CN106020765B (en) | A kind of effect adjusting method and device | |
| CN109308908A (en) | A kind of voice interactive method and device | |
| CN103714847A (en) | DSP (digital signal processing)-based multi-channel digital audio processor | |
| CN108401204A (en) | A kind of novel active noise reduction earphone | |
| CN110505547A (en) | A kind of earphone wearing state detection method and earphone | |
| CN103702258A (en) | Microphone device and microphone setting method for eliminating interference of near-field sound source | |
| CN207676649U (en) | A kind of voice processing apparatus and smart machine based on 4 microphone linear array | |
| CN207676651U (en) | A kind of voice processing apparatus and smart machine based on 2 microphone linear array | |
| CN103916810B (en) | A kind of time domain acoustic energy compared with control method and system | |
| CN104850278B (en) | A kind of all-in-one and its control method of non-tactile control | |
| CN205620939U (en) | Wearable equipment of intelligence | |
| CN113096677B (en) | Intelligent noise reduction method and related equipment | |
| CN207947879U (en) | A kind of voice processing apparatus and smart machine based on 4 microphone annular arrays | |
| CN108432216A (en) | The method, apparatus and electronic equipment of volume adjustment | |
| CN110010117A (en) | A kind of method and device of voice active noise reduction | |
| CN205510340U (en) | Noise reduction earphone | |
| CN205584467U (en) | Microphone and linear audio input's compatible circuit | |
| CN105227151B (en) | Speech playing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP02 | Change in the address of a patent holder |
Address after: Building 2102, building 1, Haidian District, Beijing Patentee after: BEIJING SINOVOICE TECHNOLOGY Co.,Ltd. Address before: 100193 room 2101, 1f, building a, Zhongguancun Software Park, No. 8, Dongbeiwang West Road, Haidian District, Beijing Patentee before: BEIJING SINOVOICE TECHNOLOGY Co.,Ltd. |
|
| CP02 | Change in the address of a patent holder |