CN108447497A - A method of independently going out oneself sounding in noisy environment - Google Patents
A method of independently going out oneself sounding in noisy environment Download PDFInfo
- Publication number
- CN108447497A CN108447497A CN201810187542.2A CN201810187542A CN108447497A CN 108447497 A CN108447497 A CN 108447497A CN 201810187542 A CN201810187542 A CN 201810187542A CN 108447497 A CN108447497 A CN 108447497A
- Authority
- CN
- China
- Prior art keywords
- oneself
- microphone
- vibration
- sound
- audio signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000005236 sound signal Effects 0.000 claims abstract description 68
- 210000001260 vocal cord Anatomy 0.000 claims description 64
- 230000003111 delayed effect Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 241000209140 Triticum Species 0.000 claims description 3
- 235000021307 Triticum Nutrition 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 7
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0272—Voice signal separating
- G10L21/028—Voice signal separating using properties of sound source
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L2021/02161—Number of inputs available containing the signal or the noise to be suppressed
- G10L2021/02166—Microphone arrays; Beamforming
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
The invention discloses one kind being related to audio area, more particularly to a kind of method independently going out oneself sounding in noisy environment；It is realized using following technical scheme：Including：Microphone array, speech recording apparatus subtract microphone noise around it is further characterized in that in audio signal by main shotgun microphone, it is remaining go out the accurate pronunciation of oneself；In the audio signal by main shotgun microphone, subtract microphone noise around, it is remaining go out the accurate pronunciation of oneself, be the method that the noise that microphone records around the main shotgun microphone of ring is subtracted in the audio signal that main shotgun microphone records；In complicated noise circumstance, oneself one's voice in speech is accurately found out.
Description
Technical field
The present invention relates to audio areas, more particularly to a kind of side independently going out oneself sounding in noisy environment
Method.
Background technology
Voice input is accurate, it is most important that the sounding data how acquisitor speaks.In quiet environment, under record
The data of oneself one's voice in speech, record are exactly the sounding data of oneself；But in the big place of ambient noise, record is lower oneself to be said
The sound of words is just not necessarily the sounding data of oneself, because in the voice data under record, carries the sound number of ambient noise
According to；This problem is resolved, is a key technology of voice input.
Invention content
The problem to be solved in the present invention is to provide a kind of method, and when speaking in complicated noise circumstance, voice record is set
It is standby the sounding data of oneself individually, accurately to be separated.
In order to achieve the object, a kind of method independently going out oneself sounding in noisy environment of the present invention, use with
Lower technical solution is realized：Including：Microphone array, speech recording apparatus, it is further characterized in that in the audio of main shotgun microphone
In signal, microphone noise around is subtracted, obtains the accurate pronunciation of oneself；
In the audio signal by main shotgun microphone, subtract microphone noise around, it is remaining go out the accurate pronunciation of oneself, be
The method that the noise of surrounding's microphone record of the main shotgun microphone of ring is subtracted in the audio signal of main shotgun microphone record；Tool
Body is：Microphone array is made of several microphones, the main shotgun microphone position at the pronunciation face center of people, with main oriented microphone
There is a microphone in each orientation centered on wind, in various sound collected in this way, can determine which direction hair that sound wave is
Go out, after the sound wave in other directions is removed in the voice data in centre, remaining is exactly the sound of oneself pronunciation
Data.
Advantageous effect：In complicated noise circumstance, oneself one's voice in speech is accurately found out.
A kind of method independently going out oneself sounding in noisy environment of the present invention, using following technical scheme come real
It is existing：Including：Microphone array, speech recording apparatus, it is further characterized in that the audio signal wind delay of main oriented microphone is arrived and its week
Enclose shotgun microphone audio signal synchronize after, carry out two kinds of audio signals comparison, the common audio compared out after delay
Signal, the audio signal spoken for pure people；The microphone array is made of several microphones, the pronunciation face center of people
There is microphone in main shotgun microphone position, each orientation centered on main shotgun microphone；The delay, sound transmission are
Speed, the sound of main shotgun microphone recipient and the sound of surrounding shotgun microphone recipient have the time difference, this when
Difference, the time being exactly delayed.
Preferably, around microphone audio signal delay it is synchronous with the audio signal of main shotgun microphone after, into
The comparison of two kinds of audio signals of row, the common audio signal after delay are exactly the audio signal of noise, in main shotgun microphone
Common audio signal is excluded in audio signal, the audio signal that just remaining pure people speaks.
Advantageous effect：In complicated noise circumstance, oneself one's voice in speech is accurately found out.
A kind of method independently going out oneself sounding in noisy environment of the present invention, using following technical scheme come real
It is existing：Including：Microphone, speech recording apparatus, vibration acquisition device, the position that vocal cord vibration can be acquired, it is further characterized in that sound
Band vibration matching method；
Vibration acquisition device, is positioned over the position that can acquire vocal cord vibration, is believed with vocal cord vibration by the vocal cord vibration matching method
Number be source, the voice data of oneself is matched in the audio signal of main shotgun microphone；Specific practice is：With the sound of neck
Band position vibration signal is source, is coached with the parameter of the vibration of vocal cords position and voice data, in the voice data of microphone
The sounding of oneself is matched in record；
Preferably, the acquisition of vocal cords position vibration is adjacent to installation vibration acquisition device at or near the vocal cords of neck, and people one says
Words, collector can collect the vibration at vocal cords position in real time；And ignoring or subtracting inside of human body vibration signal include heart
Assert that this signal is the real-time vibration signal that people speaks for no environment interference signal after vibration signal.
Preferably, the parameter of the vibration of vocal cords position and voice data generates：Under extremely quiet environment, oneself is acquired
Vocal cords position vibrates and voice data, establishes a parameter, the vibration of vocal cords position and the pronunciation of oneself can be made to build by parameter
A relationship is erected, by this relationship, can will collect the vibration of vocal cords position from the voice data recording of microphone
Allot the sounding of oneself.
Advantageous effect：Can be under complicated noise circumstance, the accurate typing sound of oneself, to utilize.
A kind of method independently going out oneself sounding in noisy environment of the present invention, using following technical scheme come real
It is existing：Including：The vocal cords position of microphone, speech recording apparatus, vibration acquisition device, neck, it is further characterized in that establishing vocal cords
Position vibrates and the corresponding card of pronunciation, and the corresponding card for establishing the vibration of vocal cords position and pronunciation records the vocal cords portion of oneself
Position vibration data, while recording the pronunciation of oneself, the two is formed corresponding card, and is that the vocal cords position of every a word shakes
Corresponding card is all built up in dynamic and its pronunciation, can thus be vibrated by vocal cords position and be obtained the accurate pronunciation of oneself.
Advantageous effect：Can be under complicated noise circumstance, the accurate typing sound of oneself, to utilize.
A kind of method independently going out oneself sounding in noisy environment of the present invention, using following technical scheme come real
It is existing：Including：Microphone, speech recording apparatus, sound word corresponds to card, it is further characterized in that using oneself sound characteristic as target, in master
The extraction method of the voice data of oneself is extracted in the audio signal of shotgun microphone, is used《A kind of individual character voice input device》《One
Kind human-computer dialogue platform》In sound word with oneself sound characteristic correspond to card, using oneself sound characteristic as target, in main orientation
The voice data of oneself is extracted in the audio signal of microphone.
Advantageous effect：In complicated noise circumstance, oneself one's voice in speech is accurately found out.
6. a kind of method independently going out oneself sounding in noisy environment of the present invention, using following technical scheme come real
It is existing：Including：Microphone, speech recording apparatus,《A kind of individual character voice input device》《A kind of human-computer dialogue platform》In have from
The sound word of own tamber characteristic corresponds to card, it is further characterized in that main shotgun microphone only acquire the language with typing band oneself sound characteristic
The acquisition method of sound data, the main shotgun microphone only acquires and the acquisition method of the voice data of typing band oneself sound characteristic,
For the voice data for only acquiring with typing band oneself sound characteristic.
Advantageous effect：In complicated noise circumstance, oneself one's voice in speech is accurately found out.
A kind of purposes for the method independently going out oneself sounding in noisy environment, after obtaining this sound, puts in sound equipment
In big system, only with this, pronunciation is amplified for source in real time, is just avoided that the generation uttered long and high-pitched sounds.
Advantageous effect：Can be under complicated noise circumstance, the accurate typing sound of oneself, to utilize.
Specific implementation mode：
The present invention is described in detail below, and technical scheme in the embodiment of the invention is clearly and completely described, shows
So, described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based on the reality in the present invention
Example is applied, every other embodiment obtained by those of ordinary skill in the art without making creative efforts all belongs to
In the scope of protection of the invention.
Embodiment 1
A kind of method independently going out oneself sounding in noisy environment of the present invention, is realized using following technical scheme：Packet
It includes：Microphone array, speech recording apparatus subtract Mike around it is further characterized in that in the audio signal of main shotgun microphone
Wind noise obtains the accurate pronunciation of oneself.
The present embodiment is further arranged to：In the audio signal by main shotgun microphone, it is miscellaneous to subtract microphone around
Sound, it is remaining go out the accurate pronunciation of oneself, be the week that the main shotgun microphone of ring is subtracted in the audio signal that main shotgun microphone records
Enclose the method for the noise of microphone record；Specially：Microphone array is made of several microphones, the master at the pronunciation face center of people
There is a microphone in shotgun microphone position, each orientation centered on main shotgun microphone, in various sound collected in this way, energy
Enough judge that sound wave is which direction is sent out, is removed in the voice data in centre when the sound wave in other directions
Afterwards, it is remaining be exactly oneself pronunciation voice data.
Operation principle：Microphone is shotgun microphone, and the mouth of main shotgun microphone alignment people, the reverse side of mouth has orientation wheat
Gram wind also has circular shotgun microphone between main shotgun microphone direction and its section；It is collected in main shotgun microphone
In audio data, after the sound wave audio data in other directions is removed, remaining is exactly the voice data of oneself pronunciation.
Embodiment 2
A kind of method independently going out oneself sounding in noisy environment of the present invention, is realized using following technical scheme：Packet
It includes：Microphone array, speech recording apparatus, it is further characterized in that main oriented microphone audio signal wind delay to and its around orient
After the audio signal of microphone synchronizes, in the comparison for carrying out two kinds of audio signals, the common audio signal compared out after delay is
The audio signal that pure people speaks.
The present embodiment is further arranged to：The microphone array is made of several microphones, the pronunciation face center of people
There is microphone in main shotgun microphone position, each orientation centered on main shotgun microphone；The delay, sound transmission are
Speed, the sound of main shotgun microphone recipient and the sound of surrounding shotgun microphone recipient have the time difference, this when
Difference, the time being exactly delayed.
Operation principle：Main shotgun microphone is close from mouth, first records to obtain audio signal, and the microphone of surrounding is opposite remote from mouth, after
Record to obtain audio signal；On the contrary, the audio signal of noise is to come from surrounding, the microphone of surrounding is first added, main orientation wheat is added afterwards
Gram wind, original signal just lags, then is delayed, just rear, will not be identical with the audio signal of main shotgun microphone, also just matches
Not, it can be excluded.
Embodiment 3
According to a kind of method independently going out oneself sounding in noisy environment, it is characterised in that the audio of microphone around it
It is common after delay in the comparison for carrying out two kinds of audio signals after signal delay is synchronous with the audio signal of main shotgun microphone
Audio signal is exactly the audio signal of noise, common audio signal is excluded in the audio signal of main shotgun microphone, just remaining
The audio signal that pure people speaks down.
Operation principle：Main shotgun microphone is close from mouth, first records to obtain audio signal, and the microphone of surrounding is opposite remote from mouth, after
Audio signal is recorded to obtain, but noise signals are in advance；The audio signal of noise is to come from surrounding, and the Mike of surrounding is first added
Wind, noise audio signal is delayed, and main shotgun microphone is added afterwards, makes the audio signal of noise identical, subtracts these audios letter
It is number identical, it is exactly the audio signal that people speak.
Embodiment 4
A kind of method independently going out oneself sounding in noisy environment of the present invention, is realized using following technical scheme：Packet
It includes：Microphone, speech recording apparatus, vibration acquisition device, the position that vocal cord vibration can be acquired, it is further characterized in that vocal cord vibration
Matching method.
The present embodiment is further arranged to：The vocal cord vibration matching method, vibration acquisition device, which is positioned over, can acquire sound
Position with vibration matches the voice of oneself using laryngograph signal as source in the audio signal of main shotgun microphone
Data；Specific practice is：It is vibrated for source with the vocal cords position of neck, is referred to the parameter work of the vibration of vocal cords position and voice data
It leads, the sounding of oneself is matched in the voice data recording of microphone.
Operation principle：Vocal cords position vibrate with oneself sound synchronize send out, noise will not be sent out during this time；Separately
Outside, noise does not influence the vibration of vocal cords position yet；Oneself audio is matched in microphone with the vibration of vocal cords position and its parameter
Signal, it should be most believable.
Embodiment 5
According to a kind of vocal cord vibration matching method for the method independently going out oneself sounding in noisy environment, it is characterised in that sound
Acquisition with position vibration.
The acquisition of vocal cords position vibration is adjacent to installation vibration acquisition device at or near the vocal cords of neck, and people one speaks,
Collector can collect the vibration at vocal cords position in real time；And ignore or subtract inside of human body vibration signal include heart vibration
Assert that this signal is the real-time vibration signal that people speaks for no environment interference signal after signal.
Embodiment 6
According to a kind of vocal cord vibration matching method for the method independently going out oneself sounding in noisy environment, it is characterised in that sound
Parameter with position vibration and voice data generates：Under extremely quiet environment, the vocal cords position vibration harmony of oneself is acquired
Sound data establish a parameter, the vibration of vocal cords position and the pronunciation of oneself can be made to set up a relationship, led to by parameter
This relationship is crossed, the vibration of vocal cords position can will be collected and match the sounding of oneself from the voice data recording of microphone.
Embodiment 7
A kind of vocal cord vibration correspondence card for the method independently going out oneself sounding in noisy environment, using following technical scheme
To realize：Including：The vocal cords position of microphone, speech recording apparatus, vibration acquisition device, neck, it is further characterized in that establishing
Vocal cords position vibrates and the corresponding card of pronunciation.
The present embodiment is further arranged to：The corresponding card for establishing the vibration of vocal cords position and pronunciation, records oneself
Vocal cords position vibration data, while the pronunciation of oneself is recorded, the two is formed corresponding card, and be the vocal cords of every a word
Position vibrates and corresponding card is all built up in its pronunciation, can thus be vibrated by vocal cords position and obtain the accurate pronunciation of oneself.
Operation principle：After corresponding card is all built up in the vibration of vocal cords position and its pronunciation per a word, each section of vocal cords in this way
Position vibrates, and the corresponding card for vibrating and pronouncing by vocal cords position can accurately just correspond to out the pronunciation of oneself.
Embodiment 8
A kind of extraction sound characteristic for the method independently going out oneself sounding in noisy environment, using following technical scheme come
It realizes：Including：Microphone, speech recording apparatus, sound word correspond to card, it is further characterized in that using oneself sound characteristic as target,
The extraction method of the voice data of oneself is extracted in the audio signal of main shotgun microphone, is used《A kind of individual character voice input device》
《A kind of human-computer dialogue platform》In sound word with oneself sound characteristic correspond to card, using oneself sound characteristic as target, in master
The voice data of oneself is extracted in the audio signal of shotgun microphone.
Operation principle：Sound word with oneself sound characteristic corresponds to card, and the line point that each sound word corresponds to card carries
Oneself sound characteristic, this is extracted in the audio signal of audio signal and main shotgun microphone with oneself sound characteristic
The voice data of oneself.
Embodiment 9
A kind of oneself sound characteristic of the method for independently going out oneself sounding in noisy environment, using following technical scheme come
It realizes：Including：Microphone, speech recording apparatus,《A kind of individual character voice input device》《A kind of human-computer dialogue platform》In have
The sound word of oneself tamber characteristic corresponds to card, it is further characterized in that main shotgun microphone only acquire and typing band oneself sound characteristic
The acquisition method of voice data.
The present embodiment is further arranged to：The main shotgun microphone only acquires and the voice of typing band oneself sound characteristic
The acquisition method of data, for the voice data of only oneself sound characteristic of acquisition and typing band.
Operation principle：Sound word with oneself tamber characteristic corresponds to card, and the line point that each sound word corresponds to card carries
Oneself tamber characteristic, with having oneself tamber characteristic on main shotgun microphone, only record and typing carries oneself tone color for this
The voice data of feature.
Embodiment 10
A kind of purposes for the method independently going out oneself sounding in noisy environment after obtaining this sound, amplifies system in sound equipment
In system, only with this, pronunciation is amplified for source in real time, is just avoided that the generation uttered long and high-pitched sounds.
Operation principle：The main reason for generation is uttered long and high-pitched sounds is that the pronunciation of lag is amplified generation；Because the pronunciation of lag is
Amplify through being received by microphone, by power amplifier, also pass through loudspeaker broadcast and received by microphone, sound has doubled, several times
Cycle is easy to generate and utter long and high-pitched sounds, if in multiplying arrangement, excludes the pronunciation of this part lag, does not amplify it, would not generate
It utters long and high-pitched sounds.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (10)
1. a kind of method independently going out oneself sounding in noisy environment, is realized using following technical scheme：Including：Wheat
It is miscellaneous to subtract microphone around it is further characterized in that in the audio signal of main shotgun microphone for gram wind battle array, speech recording apparatus
Sound obtains the accurate pronunciation of oneself；
In the audio signal by main shotgun microphone, subtract microphone noise around, it is remaining go out the accurate pronunciation of oneself, be
The method that the noise of surrounding's microphone record of the main shotgun microphone of ring is subtracted in the audio signal of main shotgun microphone record；Tool
Body is：Microphone array is made of several microphones, the main shotgun microphone position at the pronunciation face center of people, with main oriented microphone
There is a microphone in each orientation centered on wind, in various sound collected in this way, can determine which direction hair that sound wave is
Go out, after the sound wave in other directions is removed in the voice data in centre, remaining is exactly the sound of oneself pronunciation
Data.
2. a kind of method independently going out oneself sounding in noisy environment, is realized using following technical scheme：Including：Wheat
Gram wind battle array, speech recording apparatus, it is further characterized in that the audio signal wind of main oriented microphone prolong to and shotgun microphone around it
Audio signal synchronize after, in the comparison for carrying out two kinds of audio signals, the common audio signal compared out after delay is pure
The audio signal that people speaks；
The microphone array is made of several microphones, the main shotgun microphone position at the pronunciation face center of people, with main orientation
There is microphone in each orientation centered on microphone；The delay, sound transmission are also speed, main shotgun microphone recipient
Sound and the sound of surrounding shotgun microphone recipient have the time difference, this time difference, the time being exactly delayed.
3. according to claim 2, a method of independently going out oneself sounding in noisy environment, it is characterised in that around it
Microphone audio signal delay it is synchronous with the audio signal of main shotgun microphone after, carry out two kinds of audio signals comparison,
Common audio signal after delay is exactly the audio signal of noise, is excluded jointly in the audio signal of main shotgun microphone
Audio signal, the audio signal that just remaining pure people speaks.
4. a kind of method independently going out oneself sounding in noisy environment, including：Microphone, speech recording apparatus, vibration
Harvester, the position that vocal cord vibration can be acquired, it is further characterized in that vocal cord vibration matching method；
Vibration acquisition device, is positioned over the position that can acquire vocal cord vibration, is believed with vocal cord vibration by the vocal cord vibration matching method
Number be source, the voice data of oneself is matched in the audio signal of main shotgun microphone；Specific practice is：With the sound of neck
Band position vibration signal is source, is coached with the parameter of the vibration of vocal cords position and voice data, in the voice data of microphone
The sounding of oneself is matched in record.
5. according to claim 4, a kind of vocal cord vibration matching method for the method independently going out oneself sounding in noisy environment,
It is characterized in that the acquisition of vocal cords position vibration is adjacent to installation vibration acquisition device at or near the vocal cords of neck, people one says
Words, collector can collect the vibration at vocal cords position in real time；And ignoring or subtracting inside of human body vibration signal include heart
Assert that this signal is the real-time vibration signal that people speaks for no environment interference signal after vibration signal.
6. according to claim 4, a kind of vocal cord vibration matching method for the method independently going out oneself sounding in noisy environment,
It is characterized in that the parameter of the vibration of vocal cords position and voice data generates：Under extremely quiet environment, the vocal cords of oneself are acquired
Position vibrates and voice data, establishes a parameter, the vibration of vocal cords position and the pronunciation of oneself can be made to set up by parameter
One relationship can will be collected the vibration of vocal cords position and be matched from the voice data recording of microphone by this relationship
The sounding of oneself.
7. a kind of method independently going out oneself sounding in noisy environment, including：Microphone, speech recording apparatus, vibration
The vocal cords position of harvester, neck, it is further characterized in that the corresponding card of the vibration of vocal cords position and pronunciation is established, it is described to establish sound
The corresponding card for vibrating and pronouncing with position, records the vocal cords position vibration data of oneself, while recording the pronunciation of oneself,
The two forms corresponding card, and is that corresponding card is all built up in the vocal cords position vibration of every a word and its pronunciation, thus can be with
It is vibrated by vocal cords position and obtains the accurate pronunciation of oneself.
8. a kind of method independently going out oneself sounding in noisy environment, is realized using following technical scheme：Including：Wheat
Gram wind, speech recording apparatus, sound word corresponds to card, it is further characterized in that using oneself sound characteristic as target, in main shotgun microphone
Audio signal in extract the extraction method of the voice data of oneself, use《A kind of individual character voice input device》《A kind of human-computer dialogue
Platform》In sound word with oneself sound characteristic correspond to card, using oneself sound characteristic as target, in the sound of main shotgun microphone
The voice data of oneself is extracted in frequency signal.
9. a kind of method independently going out oneself sounding in noisy environment, is realized using following technical scheme：Including：Wheat
Gram wind, speech recording apparatus,《A kind of individual character voice input device》《A kind of human-computer dialogue platform》In have oneself tamber characteristic
Sound word correspond to card, adopted with the voice data of typing band oneself sound characteristic it is further characterized in that main shotgun microphone only acquire
Collection method, the main shotgun microphone only acquires and the acquisition method of the voice data of typing band oneself sound characteristic, for only acquisition and
The voice data of oneself sound characteristic of typing band.
10. a kind of purposes for the method independently going out oneself sounding in noisy environment after obtaining this sound, is amplified in sound equipment
In system, only with this, pronunciation is amplified for source in real time, is just avoided that the generation uttered long and high-pitched sounds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810187542.2A CN108447497A (en) | 2018-03-07 | 2018-03-07 | A method of independently going out oneself sounding in noisy environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810187542.2A CN108447497A (en) | 2018-03-07 | 2018-03-07 | A method of independently going out oneself sounding in noisy environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108447497A true CN108447497A (en) | 2018-08-24 |
Family
ID=63193517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810187542.2A Pending CN108447497A (en) | 2018-03-07 | 2018-03-07 | A method of independently going out oneself sounding in noisy environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108447497A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516265A (en) * | 2019-08-31 | 2019-11-29 | 青岛谷力互联科技有限公司 | A kind of single identification real-time translation system based on intelligent sound |
| CN110956870A (en) * | 2019-11-25 | 2020-04-03 | 中北大学 | Solfeggio teaching method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101290720A (en) * | 2008-06-17 | 2008-10-22 | 李伟 | Visualized pronunciation teaching method and apparatus |
| CN102610236A (en) * | 2012-02-29 | 2012-07-25 | 山东大学 | Method for improving voice quality of throat microphone |
| CN102831195A (en) * | 2012-08-03 | 2012-12-19 | 河南省佰腾电子科技有限公司 | Individualized voice collection and semantics determination system and method |
| CN105355213A (en) * | 2015-11-11 | 2016-02-24 | 广东欧珀移动通信有限公司 | Method and device for directional recording |
| CN205508400U (en) * | 2015-12-24 | 2016-08-24 | 深圳市凯木金科技有限公司 | Electronic product sound noise reduction system |
| CN106101351A (en) * | 2016-07-26 | 2016-11-09 | 哈尔滨理工大学 | A kind of many MIC noise-reduction method for mobile terminal |
| CN106448697A (en) * | 2016-09-28 | 2017-02-22 | 惠州Tcl移动通信有限公司 | Double-microphone noise elimination implementation method and system and smart glasses |
| CN106965246A (en) * | 2017-05-04 | 2017-07-21 | 杨铭英 | A kind of clothing cloth hollow out device |
| CN206421638U (en) * | 2017-02-06 | 2017-08-18 | 湖北宝声堂医药科技有限公司 | A kind of vocal cords sounding simulation demonstrating apparatus |
-
2018
- 2018-03-07 CN CN201810187542.2A patent/CN108447497A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101290720A (en) * | 2008-06-17 | 2008-10-22 | 李伟 | Visualized pronunciation teaching method and apparatus |
| CN102610236A (en) * | 2012-02-29 | 2012-07-25 | 山东大学 | Method for improving voice quality of throat microphone |
| CN102831195A (en) * | 2012-08-03 | 2012-12-19 | 河南省佰腾电子科技有限公司 | Individualized voice collection and semantics determination system and method |
| CN105355213A (en) * | 2015-11-11 | 2016-02-24 | 广东欧珀移动通信有限公司 | Method and device for directional recording |
| CN205508400U (en) * | 2015-12-24 | 2016-08-24 | 深圳市凯木金科技有限公司 | Electronic product sound noise reduction system |
| CN106101351A (en) * | 2016-07-26 | 2016-11-09 | 哈尔滨理工大学 | A kind of many MIC noise-reduction method for mobile terminal |
| CN106448697A (en) * | 2016-09-28 | 2017-02-22 | 惠州Tcl移动通信有限公司 | Double-microphone noise elimination implementation method and system and smart glasses |
| CN206421638U (en) * | 2017-02-06 | 2017-08-18 | 湖北宝声堂医药科技有限公司 | A kind of vocal cords sounding simulation demonstrating apparatus |
| CN106965246A (en) * | 2017-05-04 | 2017-07-21 | 杨铭英 | A kind of clothing cloth hollow out device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516265A (en) * | 2019-08-31 | 2019-11-29 | 青岛谷力互联科技有限公司 | A kind of single identification real-time translation system based on intelligent sound |
| CN110956870A (en) * | 2019-11-25 | 2020-04-03 | 中北大学 | Solfeggio teaching method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100619215B1 (en) | Microphone and communication interface system | |
| US20070276658A1 (en) | Apparatus and Method for Detecting Speech Using Acoustic Signals Outside the Audible Frequency Range | |
| CN107112026A (en) | System, the method and apparatus for recognizing and handling for intelligent sound | |
| CN110349582B (en) | Display device and far-field voice processing circuit | |
| CN102138337A (en) | Wearable headset with self-contained vocal feedback and vocal command | |
| CN103124165A (en) | Automatic gain control | |
| CN107124647A (en) | A kind of panoramic video automatically generates the method and device of subtitle file when recording | |
| CN108200492A (en) | Voice control optimization method, device and the earphone and wearable device that integrate In-Ear microphone | |
| Akimoto et al. | POCO: A Voice Spoofing and Liveness Detection Corpus Based on Pop Noise. | |
| CN108447497A (en) | A method of independently going out oneself sounding in noisy environment | |
| Nakamura et al. | Speaking aid system for total laryngectomees using voice conversion of body transmitted artificial speech | |
| CN110248281A (en) | Independently go out the vocal cord vibration matching of the method for oneself sounding in noisy environment | |
| US12106765B2 (en) | Speech signal processing method and apparatus with external and ear canal speech collectors | |
| Katz et al. | Human voice phoneme directivity pattern measurements | |
| CN213154723U (en) | A interrogation table that role separation double-circuit audio frequency and video for interrogation | |
| CN108337620A (en) | A kind of loudspeaker and its control method of voice control | |
| US20220189498A1 (en) | Signal processing device, signal processing method, and program | |
| CN207518797U (en) | Neck wears the voice control optimization device of formula interactive voice earphone | |
| WO2021004067A1 (en) | Display device | |
| JP6598323B1 (en) | Hearing aid and program | |
| CN208337877U (en) | A kind of loudspeaker of voice control | |
| CN109961785A (en) | A kind of voice control optimization method | |
| CN110248276A (en) | The delay for independently going out the method for oneself sounding in noisy environment compares | |
| CN105791713A (en) | Intelligent device for playing voices and captions synchronously | |
| CN110248277A (en) | It is a kind of that independently the keynote of the method for oneself sounding subtracts noise out in noisy environment |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180824 |