CN207473563U - A kind of speech processes mouse - Google Patents
A kind of speech processes mouse Download PDFInfo
- Publication number
- CN207473563U CN207473563U CN201721628253.9U CN201721628253U CN207473563U CN 207473563 U CN207473563 U CN 207473563U CN 201721628253 U CN201721628253 U CN 201721628253U CN 207473563 U CN207473563 U CN 207473563U
- Authority
- CN
- China
- Prior art keywords
- voice
- speech
- noise reduction
- signal
- speech processes
- 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 discloses a kind of speech processes mouse, including：Microphone and voice de-noising processing circuit；The microphone is connected with the voice de-noising processing circuit, for receiving externally input primary speech signal, and the primary speech signal is exported to the voice de-noising processing circuit；The voice de-noising processing circuit is used to carry out noise reduction process to the primary speech signal, obtains the voice signal after noise reduction, and the voice signal after the noise reduction is exported.The utility model embodiment carries out noise reduction process by voice de-noising processing circuit to the primary speech signal that microphone receives, the preferable voice signal of voice quality can be exported, the phonetic recognization rate under noise circumstance is improved, meets the voice record demand under adverse noise environment.
Description
Technical field
The utility model embodiment is related to voice processing technology field, and in particular to a kind of speech processes mouse.
Background technology
At present under severe noise circumstance, the mode major way of information record has hand-written record or mouse and keyboard knot
Close typing；Hand-written record needs special stenographer, and record efficiency is too low, also there is the problems such as misremembering or failing to record, and follow-up
It is difficult discs reduction scene；Although mouse, which is combined record with keyboard, can improve record efficiency, record efficiency is still inadequate
It is preferable；For having the function of the mouse of voice record, there are problems that shaking under environment is difficult typing, is identified in a noisy environment
Rate can not meet the voice record demand under adverse noise environment than relatively low.
Utility model content
Due to problem of the existing technology, the utility model embodiment proposes a kind of speech processes mouse.
The utility model embodiment proposes a kind of speech processes mouse, including：Microphone and voice de-noising processing circuit；
The microphone is connected with the voice de-noising processing circuit, for receiving externally input primary speech signal,
And the primary speech signal is exported to the voice de-noising processing circuit；
The voice de-noising processing circuit is used to carry out noise reduction process to the primary speech signal, obtains the language after noise reduction
Sound signal, and the voice signal after the noise reduction is exported.
Optionally, it further includes：Speech recognition button；
The speech recognition button is set on the outer surface of the speech processes mouse；
If the speech recognition button is triggered, starts microphone and receive primary speech signal.
Optionally, it further includes：Analog-to-digital conversion adc circuit；
The adc circuit is set between the microphone and the voice de-noising processing circuit, for the microphone
After the primary speech signal analog-to-digital conversion of input, export to the voice de-noising processing circuit and carry out noise reduction process.
Optionally, it further includes：Multiplier (-icator)；
The multiplier (-icator) is set between the microphone and the adc circuit, for the original of the microphone input
Voice signal carries out gain amplification.
Optionally, it further includes：Audio compression module；
The audio compression module is connect with the voice de-noising processing circuit, for the voice de-noising processing circuit
Voice signal after the noise reduction of output carries out compression processing, and will compression treated that voice signal exports.
Optionally, the speech processes mouse is connect by USB interface or wireless mode with external equipment, accordingly, is led to
It crosses USB interface or power supply module is powered.
Optionally, the speech processes mouse is connect with the translation unit of the external equipment；
The speech processes mouse exports the voice signal after the noise reduction to the translation unit, so that the translation
Unit translates the voice signal after the noise reduction.
Optionally, the speech processes mouse is connect with the Application on Voiceprint Recognition unit of the external equipment；
The speech processes mouse exports the voice signal after the noise reduction to the recognition unit, so that the identification
Unit carries out Application on Voiceprint Recognition to the voice signal after the noise reduction.
Optionally, the speech processes mouse is connect with the voice recognition unit of the external equipment；
The speech processes mouse exports the voice signal after the noise reduction to the voice recognition unit, so that described
Voice recognition unit carries out speech recognition to the voice signal after the noise reduction.
Optionally, it further includes：Memory；
The memory is connect with the voice de-noising processing circuit, for storaged voice noise reduction process algorithm.
As shown from the above technical solution, the utility model embodiment receives microphone by voice de-noising processing circuit
Primary speech signal carries out noise reduction process, can export the preferable voice signal of voice quality, improves the voice under noise circumstance
Discrimination meets the voice record demand under adverse noise environment.
Description of the drawings
It 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 attached drawings can also be obtained according to these figures.
Fig. 1 is the structure diagram of a kind of speech processes mouse that one embodiment of the utility model provides；
Fig. 2 is the structure diagram of a kind of speech processes mouse that another embodiment of the utility model provides；
Fig. 3 is the structure diagram of a kind of speech processes mouse that another embodiment of the utility model provides.
Specific embodiment
Below in conjunction with the accompanying drawings, the specific embodiment of utility model is further described.Following embodiment is only used for more
Add and clearly demonstrate the technical solution of the utility model, and cannot the scope of protection of the utility model be limited with this.
Fig. 1 shows a kind of structure diagram of speech processes mouse provided in this embodiment, including：101 He of microphone
Voice de-noising processing circuit 102；
The microphone 101 and the voice de-noising processing circuit 102 connect, for receiving externally input raw tone
Signal, and the primary speech signal is exported to the voice de-noising processing circuit 102.
Microphone 101 described in the present embodiment can be one or more, when the microphone 101 is more than or equal to two
When, it is properly termed as microphone array.
Specifically, when the quantity of microphone is more than or equal to 2, the speech processes mouse of this programme includes：Microphone array
101 and voice de-noising processing circuit 102；The microphone array 101 and the voice de-noising processing circuit 102 connect, and are used for
Externally input primary speech signal is received, and the primary speech signal is exported to the voice de-noising processing circuit 102.
The voice de-noising processing circuit 102 is connect with the speech processes mouse, for the primary speech signal
Noise reduction process is carried out, obtains the voice signal after noise reduction, and the voice signal after the noise reduction is exported.
Wherein, the microphone 101 can be electret microphone, silicon microphone etc. or multiple electret wheats
The microphone array of the formation such as gram wind, silicon microphone.
The processor based on ARM Cortex-M4 may be used in the voice de-noising processing circuit 102, and model such as million is easy
The GD32F450IGH6 of innovation.
Existing mouse function is segmented into two kinds substantially, and a kind of is traditional mouse, and another kind is integrated speech identification
Function, but existing this microphone mouse function is equivalent to mouse and monomer microphone simple combination, in a noisy environment base
Originally speech recognition cannot be used, and speech recognition can not be used under the scene of far field.
Speech processes mouse applications scene provided in this embodiment is very extensive, can identify that scene makes in voice near field
With, can also far field identify scene use, such as factory, airport and office space；It can apply in speech recognition business simultaneously
Or audio recording business etc..So that under the particular surroundings such as noise, efficient interactive voice settling mode is capable of providing, is solved
User's both hands are put, voice direct interaction mode into row information record or controlling equipment, is greatly improved office efficiency, improves man-machine
Effect.
The present embodiment carries out noise reduction process, energy by voice de-noising processing circuit to the primary speech signal that microphone receives
The preferable voice signal of voice quality is enough exported, the phonetic recognization rate under noise circumstance is improved, meets under adverse noise environment
Voice record demand.
Further, on the basis of above-described embodiment, as shown in Fig. 2, further including：Speech recognition button 104.
The speech recognition button 104 is set on the outer surface of the speech processes mouse.
If the speech recognition button 104 is triggered, starts the microphone 101 and start to receive primary speech signal；
If the speech recognition button 104 is reconditioned, the microphone 101 is closed, stops receiving primary speech signal.
During specifically used, user selects to open speech identifying function, i.e., by triggering the speech recognition button 104
To start the microphone 101；It can also select to close speech identifying function, i.e., by restoring the speech recognition button 104
It closes the microphone 101, user is facilitated flexibly to be used according to specific requirement.
Further, on the basis of above-described embodiment, as shown in Fig. 2, further including：Analog-to-digital conversion adc circuit 105.
The adc circuit 105 is set between the microphone 101 and the voice de-noising processing circuit 102, for institute
After the primary speech signal analog-to-digital conversion for stating the input of microphone 101, export to the voice de-noising processing circuit 102 and carry out noise reduction
Processing.
Specifically, the integrated chip of TI, such as model may be used in the audio amplification adc circuit 105
The chip of LTV320AIC3106, the chip can support two-way input and analog signal enlarging function, enable to voice simultaneously
Noise reduction process circuit preferably carries out noise reduction process.
Further, it on the basis of above-described embodiment, further includes：Multiplier (-icator)；
The multiplier (-icator) is set between the microphone 101 and the adc circuit 105, for the microphone input
Primary speech signal carry out gain amplification.
Further, on the basis of above-described embodiment, as shown in Fig. 2, further including：Audio compression module 106.
The audio compression module 106 is connect with the voice de-noising processing circuit 102, to the voice de-noising
It manages the voice signal after the noise reduction of circuit output and carries out compression processing, and by the voice signal after the noise reduction that compresses that treated
It is exported.
By carrying out compression processing to the voice signal after noise reduction, the transmission rate of data output can be improved.
Further, on the basis of above-described embodiment, as shown in Fig. 2, the speech processes mouse by USB interface or
Wireless mode is connect with external equipment.
Accordingly, it is powered by USB interface or power supply module.
Specifically, USB interface can convert signal, mainly USB2.0PHY, such as model MicroChip
USB3320.Power supply chip in USB interface is based on DC-DC integrated chips, such as the TPS62160DGKT cores of model TI
Piece realizes 5V conversion 3.3V voltage conversions.General integrated chip, such as model may be used in the mouse that the present embodiment uses
The chip of PAN3401.
When wirelessly connecting and transmitting data, can be powered by power supply module.
Further, on the basis of above-described embodiment, as shown in Fig. 2, the speech processes mouse is set with the outside
Standby translation unit 107 connects.
The speech processes mouse exports the voice signal after the noise reduction to the translation unit 107, so that described
Translation unit 107 translates the voice signal after the noise reduction.
It is realized it should be noted that existing fpga chip may be used in translation unit.
Specifically, the mobile equipment translated for the voice signal after the noise reduction obtained using speech processes mouse,
English is translated in such as, it is difficult to avoid user and be used under different distances and varying environment, under the particular surroundings such as noise, be led to
It crosses using speech processes mouse provided in this embodiment, is capable of providing efficient interactive voice settling mode, liberate user's both hands,
Voice direct interaction mode into row information record or controlling equipment, is greatly improved translation efficiency and accuracy, improves man-machine work(
Effect.
Further, on the basis of above-described embodiment, the vocal print of the speech processes mouse and the external equipment is known
Other unit connection；
The speech processes mouse exports the voice signal after the noise reduction to the recognition unit, so that the identification
Unit carries out Application on Voiceprint Recognition to the voice signal after the noise reduction.
It is realized it should be noted that existing fpga chip may be used in Application on Voiceprint Recognition unit.
Specifically, the mobile equipment being identified for the voice signal after the noise reduction obtained using speech processes mouse,
Such as Application on Voiceprint Recognition, it is difficult to avoid user and used under different distances and varying environment, under the particular surroundings such as noise,
By using speech processes mouse provided in this embodiment, efficient interactive voice settling mode is capable of providing, liberation user is double
Into row information record or controlling equipment, recognition efficiency and accuracy is greatly improved in hand, voice direct interaction mode.
Further, on the basis of above-described embodiment, as shown in Fig. 2, the speech processes mouse is set with the outside
Standby voice recognition unit 108 connects.
The speech processes mouse exports the voice signal after the noise reduction to the voice recognition unit 108, so that
The voice recognition unit 108 carries out speech recognition to the voice signal after the noise reduction.
It is realized it should be noted that existing fpga chip may be used in voice recognition unit.
Specifically, for speech processes kind equipment, after voice de-noising processing circuit processes obtain the voice signal after noise reduction,
Voice signal after the noise reduction is sent to the voice recognition unit of speech processes kind equipment, after voice recognition unit is according to noise reduction
Voice signal identify to obtain corresponding text message, convenient for speech processes kind equipment perform subsequent operation.
Further, on the basis of above-described embodiment, as shown in Fig. 2, further including：Memory 109.
The memory 109 is connect with the voice de-noising processing circuit 102, for storaged voice noise reduction process algorithm.
Specifically, the memory is realized using existing chip, such as the easily innovation GD25Q64CSIGY of model million
Chip.Memory inside is solidificated in by voice de-noising Processing Algorithm, not only increases microphone signal signal-to-noise ratio, additionally it is possible to is real
Existing multichannel microphone is collected, and can be realized that far field identifies, be greatlyd improve phonetic recognization rate, improve audio signal-to-noise ratio.
For example, as shown in figure 3, the microphone 101 includes the first microphone 1011 and second microphone 1012, point
It She Yu not mouse roller both sides.
It should be noted that the microphone can set one or more, specific installation position according to needs
It is not construed as limiting, not influence mouse normal use.
Speech processes mouse provided in this embodiment not only has decrease of noise functions, and far field and near field voice can be used to identify
Scene, and appearance looks elegant, assembling are simple and convenient.
With reference to Fig. 2 and Fig. 3, the speech processes mouse provided in this embodiment based on microphone or microphone array can wrap
Include mousebutton and idler wheel 110, mouse control circuit 111, voice de-noising processing circuit 102, speech recognition button 104, Mike
Wind 101, audio amplification adc circuit 105, audio compression module 106 etc., wherein voice de-noising processing circuit 102 are completed noise reduction and are calculated
Method processing also needs to carry out wired or wireless communication, voice de-noising processing electricity with output interface 103 when no audio compression module
Road can inhibit stable state and unsteady condition noise.Translation unit 107 and voice recognition unit 108 be not in speech processes mouse
It is interior, it may reside within PC locals or speech cloud or other private clounds.
The speech recognition button 104 is used to start voice de-noising processing circuit 102.
The microphone 101, for sound to be converted electric signal.
Audio amplification adc circuit 105 carries out ADC and is converted into digital signal again for analog signal to be amplified.
The mouse control circuit 111 is used to obtain mobile user's mouse, mouse-click and operational order.
Where the voice de-noising processing circuit 102 is mounted on mouse in structure, noise reduction algorithm is integrated in voice de-noising
In processing circuit or it is stored in memory 109.
The output interface 103 is used to the voice after mousebutton and the upload of rolling wheel encoding value, noise reduction upload.
The external interface of speech processes mouse provided in this embodiment is USB interface, and language is supplied electricity to by the 5V of USB interface
Sound noise reduction process circuit 102 and mouse control circuit 111 are powered.
Speech processes mouse provided in this embodiment based on microphone or microphone array passes through in traditional mouse
Voice de-noising processing circuit is set, ADC is carried out, then complete noise reduction process using microphone acquisition voice, exports high noise all the way
Than voice, then smart machine is uploaded to after being handled by audio compression algorithm, identifies and transcription is into text, effectively solve noise ring
Recording problem under border.Speech processes mouse provided in this embodiment not only can also pass through voice by mouse operation and control
Information recording is realized in input, increases the function of mouse, using interactive voice mode more operated quickly and conveniently, solves noise circumstance
Lower phonetic entry problem.
In the specification of the utility model, numerous specific details are set forth.It is to be appreciated, however, that the reality of the utility model
Applying example can put into practice without these specific details.In some instances, well known method, knot is not been shown in detail
Structure and technology, so as not to obscure the understanding of this description.
Finally it should be noted that：Above example is only to illustrate the technical solution of the utility model, rather than its limitations；
Although the utility model is described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that：
It still can modify to the technical solution recorded in foregoing embodiments or which part technical characteristic is carried out etc.
With replacement；And these modifications or replacement, various embodiments of the utility model technology that it does not separate the essence of the corresponding technical solution
The spirit and scope of scheme.
Claims (10)
1. a kind of speech processes mouse, which is characterized in that including：Microphone and voice de-noising processing circuit；
The microphone is connected with the voice de-noising processing circuit, for receiving externally input primary speech signal, and will
The primary speech signal is exported to the voice de-noising processing circuit；
The voice de-noising processing circuit is used to carry out noise reduction process to the primary speech signal, obtains the letter of the voice after noise reduction
Number, and the voice signal after the noise reduction is exported.
2. speech processes mouse according to claim 1, which is characterized in that further include：Speech recognition button；
The speech recognition button is set on the outer surface of the speech processes mouse；
If the speech recognition button is triggered, starts microphone and receive primary speech signal.
3. speech processes mouse according to claim 1, which is characterized in that further include：Analog-to-digital conversion adc circuit；
The adc circuit is set between the microphone and the voice de-noising processing circuit, for the microphone input
Primary speech signal analog-to-digital conversion after, export to the voice de-noising processing circuit carry out noise reduction process.
4. speech processes mouse according to claim 3, which is characterized in that further include：Multiplier (-icator)；
The multiplier (-icator) is set between the microphone and the adc circuit, for the raw tone to the microphone input
Signal carries out gain amplification.
5. speech processes mouse according to claim 1, which is characterized in that further include：Audio compression module；
The audio compression module is connect with the voice de-noising processing circuit, for being exported to the voice de-noising processing circuit
The noise reduction after voice signal carry out compression processing, and will compression treated that voice signal exports.
6. speech processes mouse according to claim 1, which is characterized in that the speech processes mouse passes through USB interface
Or wireless mode is connect with external equipment, accordingly, is powered by USB interface or power supply module.
7. speech processes mouse according to claim 6, which is characterized in that the speech processes mouse is set with the outside
Standby translation unit connection；
The speech processes mouse exports the voice signal after the noise reduction to the translation unit, so that the translation unit
Voice signal after the noise reduction is translated.
8. speech processes mouse according to claim 6, which is characterized in that the speech processes mouse is set with the outside
Standby Application on Voiceprint Recognition unit connection；
The speech processes mouse exports the voice signal after the noise reduction to the recognition unit, so that the recognition unit
Application on Voiceprint Recognition is carried out to the voice signal after the noise reduction.
9. speech processes mouse according to claim 6, which is characterized in that the speech processes mouse is set with the outside
Standby voice recognition unit connection；
The speech processes mouse exports the voice signal after the noise reduction to the voice recognition unit, so that the voice
Recognition unit carries out speech recognition to the voice signal after the noise reduction.
10. speech processes mouse according to claim 1, which is characterized in that further include：Memory；
The memory is connect with the voice de-noising processing circuit, for storaged voice noise reduction process algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721628253.9U CN207473563U (en) | 2017-11-29 | 2017-11-29 | A kind of speech processes mouse |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201721628253.9U CN207473563U (en) | 2017-11-29 | 2017-11-29 | A kind of speech processes mouse |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN207473563U true CN207473563U (en) | 2018-06-08 |
Family
ID=62259857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201721628253.9U Active CN207473563U (en) | 2017-11-29 | 2017-11-29 | A kind of speech processes mouse |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN207473563U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109683734A (en) * | 2018-12-29 | 2019-04-26 | 安徽咪鼠科技有限公司 | A kind of intelligent sound mouse self-defining key control method |
| CN109947269A (en) * | 2019-01-10 | 2019-06-28 | 重庆蓝岸通讯技术有限公司 | The voice recognition mouse of more acoustic aperture radio reception |
| CN111768768A (en) * | 2020-06-17 | 2020-10-13 | 北京百度网讯科技有限公司 | Voice processing method and device, peripheral control equipment and electronic equipment |
-
2017
- 2017-11-29 CN CN201721628253.9U patent/CN207473563U/en active Active
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109683734A (en) * | 2018-12-29 | 2019-04-26 | 安徽咪鼠科技有限公司 | A kind of intelligent sound mouse self-defining key control method |
| CN109947269A (en) * | 2019-01-10 | 2019-06-28 | 重庆蓝岸通讯技术有限公司 | The voice recognition mouse of more acoustic aperture radio reception |
| CN111768768A (en) * | 2020-06-17 | 2020-10-13 | 北京百度网讯科技有限公司 | Voice processing method and device, peripheral control equipment and electronic equipment |
| CN111768768B (en) * | 2020-06-17 | 2023-08-29 | 北京百度网讯科技有限公司 | Voice processing method and device, peripheral control equipment and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN207473563U (en) | A kind of speech processes mouse | |
| US9779725B2 (en) | Voice wakeup detecting device and method | |
| CN104254884B (en) | Low-power integrated-circuit for analyzing digitized audio stream | |
| CN206713016U (en) | Wireless speech interacts microphone system | |
| CN105338459A (en) | MEMS (Micro-Electro-Mechanical System) microphone and signal processing method thereof | |
| CN103838714A (en) | Method and device for converting voice information | |
| CN106941001A (en) | Automatic page turning method and device | |
| CN108447483A (en) | Speech recognition system | |
| WO2022057759A1 (en) | Voice conversion method and related device | |
| CN202796043U (en) | Voice recognition system | |
| CN103607611A (en) | Voice control method and system of intelligent television | |
| CN109712623A (en) | Sound control method, device and computer readable storage medium | |
| CN207010925U (en) | A kind of Headphone device for carrying voice and waking up identification | |
| CN106303829B (en) | Double nip head circuit and its control method | |
| CN201177871Y (en) | Hand-hold sound remote-controlling device | |
| CN209625783U (en) | Intelligent sound box and smart home system | |
| CN209691386U (en) | A kind of speech recognition system | |
| CN107357174A (en) | A kind of distributed intelligence audio amplifier speech control system | |
| CN110211612A (en) | A kind of recording pen and the way of recording | |
| CN207181990U (en) | A kind of distributed intelligence audio amplifier speech control system | |
| CN207039811U (en) | A kind of multimedia microphone Intelligent Measurement audio amplifier | |
| CN213635361U (en) | Online voice intelligent control PD charging head | |
| CN206460412U (en) | Table top type multi-purpose computer peripheral input device based on keyboard | |
| CN201717937U (en) | Mobile terminal | |
| CN207382541U (en) | Intelligent sound speaker |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |