CN109616133A - A kind of environmental noise removal system - Google Patents
A kind of environmental noise removal system Download PDFInfo
- Publication number
- CN109616133A CN109616133A CN201811142872.6A CN201811142872A CN109616133A CN 109616133 A CN109616133 A CN 109616133A CN 201811142872 A CN201811142872 A CN 201811142872A CN 109616133 A CN109616133 A CN 109616133A
- Authority
- CN
- China
- Prior art keywords
- frame
- noise
- sound
- signal
- antenna
- 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.)
- Granted
Links
- 230000007613 environmental effect Effects 0.000 title description 6
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 14
- 206010002953 Aphonia Diseases 0.000 claims abstract description 4
- 230000005236 sound signal Effects 0.000 claims description 41
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 30
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims description 27
- 229910052802 copper Inorganic materials 0.000 claims description 27
- 239000010949 copper Substances 0.000 claims description 27
- 239000000463 material Substances 0.000 claims description 23
- 229910052742 iron Inorganic materials 0.000 claims description 15
- 230000004888 barrier function Effects 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 239000004744 fabric Substances 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 229920000742 Cotton Polymers 0.000 claims description 3
- 239000004677 Nylon Substances 0.000 claims description 3
- 239000004743 Polypropylene Substances 0.000 claims description 3
- 239000012530 fluid Substances 0.000 claims description 3
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 claims description 3
- 229920001778 nylon Polymers 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- -1 polypropylene Polymers 0.000 claims description 3
- 229920001155 polypropylene Polymers 0.000 claims description 3
- 239000000843 powder Substances 0.000 claims description 3
- 239000002689 soil Substances 0.000 claims description 3
- 238000010897 surface acoustic wave method Methods 0.000 claims description 3
- 230000003746 surface roughness Effects 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000003466 welding Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 10
- 238000001914 filtration Methods 0.000 abstract description 4
- 238000005070 sampling Methods 0.000 description 8
- 210000001260 vocal cord Anatomy 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000009467 reduction Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 239000004831 Hot glue Substances 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 239000010451 perlite Substances 0.000 description 1
- 235000019362 perlite Nutrition 0.000 description 1
- 239000000741 silica gel Substances 0.000 description 1
- 229910002027 silica gel Inorganic materials 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000010455 vermiculite Substances 0.000 description 1
- 235000019354 vermiculite Nutrition 0.000 description 1
- 229910052902 vermiculite Inorganic materials 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
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/84—Detection of presence or absence of voice signals for discriminating voice from 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/87—Detection of discrete points within a voice signal
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (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)
- Quality & Reliability (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Soundproofing, Sound Blocking, And Sound Damping (AREA)
Abstract
The present invention provides a kind of ambient noises to remove system, comprising: trapping module, for capturing the first sound frame of voice play signal and previous frame the second sound frame of the first sound frame；Detection module determines corresponding frame type and the corresponding different frame address of different frame type in the first sound frame for detecting high frequency region, low frequency range and the overlay region of the first sound frame；Filter module, for being filtered to obtain filter factor to the first sound frame；Determining module when there are voice signal, calculates the noise estimation value of the second sound frame, and estimate reference value for the noise estimation value of the second sound frame as the noise of the first sound frame for determining the first sound frame with the presence or absence of voice signal；Processing module obtains decaying noise according to frame type, filter factor, noise estimation reference value three with calculating, the signal after handling the first audio by filtering algorithm and denoised, by solving the adjoint noise problem of audio, the experience effect of Lai Tigao user.
Description
Technical field
The present invention relates to Noise cancellation technology field, in particular to a kind of environmental noise removes system.
Background technique
Currently, with the extensive use of electronic technology, people be increasingly accustomed to completing by using intelligence machine to audio,
The broadcasting of video is made a phone call, but in audio, video playing or during make a phone call, may be occurred along with some syllable
Occur multiple syllables in distorsion or some period, intelligence machine may be to user to intelligence with the adjoint noise of sound intermediate frequency
The use of energy machine is brought a negative impact, and causes user that cannot experience audio bring effect well.
Summary of the invention
The present invention provides a kind of ambient noise removal system, next to realize by solving the adjoint noise problem of audio
Improve the experience effect of user.
To achieve the above object, the present invention provides a kind of environmental noise removal system, comprising:
Trapping module, for capturing the first sound frame of voice play signal and previous frame the second sound frame of the first sound frame；
Detection module determines corresponding in the first sound frame for detecting high frequency region, low frequency range and the overlay region of the first sound frame
Frame type and the corresponding different frame address of different frame type, frame type includes: speech frame, noise frame, secondary speech frame, secondary noise
Frame；
Filter module, for being filtered to obtain filter factor to the first sound frame；
Determining module when there are voice signal, calculates the second sound for determining the first sound frame with the presence or absence of voice signal
The noise estimation value of frame, and reference value is estimated using the noise estimation value of the second sound frame as the noise of the first sound frame；
Processing module obtains decaying noise according to frame type, filter factor, noise estimation reference value three with calculating, leads to
Signal after crossing filtering the first audio of algorithm process and being denoised.
In a kind of mode in the cards, trapping module includes:
Acquisition unit, for the corresponding energy of stepped-frequency signal each in the first sound frame of acquisition；
Detection module, comprising:
First judging unit, for judging the corresponding frame type of the first sound frame, when the energy of stepped-frequency signal is in first
When threshold value, judge that current first sound frame for speech frame, and demarcates the corresponding first position of speech frame；When the energy of stepped-frequency signal
When in second threshold, judge that current first sound frame for noise frame, and demarcates the corresponding second position of noise frame；Work as frequency sampling
The energy of point is when be in third threshold value, judge that current first sound frame is secondary speech frame, and the secondary corresponding third position of speech frame of calibration
It sets；When the energy of stepped-frequency signal is in four threshold values, judge that current first sound frame for time noise frame, and demarcates time noise frame
Corresponding 4th position.
In a kind of mode in the cards, detection module includes:
Storage unit, for saving the corresponding high frequency region of stepped-frequency signal and low frequency range in the first sound frame, and according to capture
The successive sequence of voice play signal carries out sample number, by the corresponding length of sampled point and the corresponding sample number of sampled point into
Row saves, and length is the memory space that sampled point occupies；
Second judgment unit, for whether within the preset frequency range to judge sampled point, when the corresponding frequency of sampled point is super
Out when predeterminated frequency range, the corresponding length of sampled point and the corresponding sample number of sampled point are obtained, is calculated by processing module
Obtain interference phase；
Wherein, compared according to second judgment unit and obtain the corresponding maximum of high frequency region minimum corresponding with low frequency range；
Processing unit is also used to that interference signal amplitude is calculated according to maximum and minimum point.
In a kind of mode in the cards, the frame type of the first sound frame is speech frame, noise frame, secondary speech frame, secondary makes an uproar
Any one or more combination of acoustic frame.
In a kind of mode in the cards, further includes:
At least two acoustic sensors, wherein including at least one first acoustic sensor and at least one second acoustics
Sensor, for receiving the audio signal outside acoustic sensor；
Processing module is also used to handle the first audio signal of the first acoustic sensor acquisition, subtracts the second acoustics sensor
The second audio signal that device obtains, obtains third audio signal；
Third judging unit, for judging that the sound wave of the first audio signal and the second audio signal whether there is delay, when
In the presence of, by the first audio signal and the second audio signal, carry out signal synchronous contrast, the common signal obtained after delay is the
Three audio signals；Delay is master control direction and non-master prosecutor to during sound transmission, since range difference forms the time difference；
Wherein, the first audio signal is the sending of master control direction with noisy voice signal, the second audio signal right and wrong
The noise signal that master control direction issues, third audio signal are the voice signals after the denoising of the first audio signal.
In a kind of mode in the cards, acoustic sensor is also used to the discharge scenario of device in detection circuit, acoustics
Sensor includes: ultrasonic sensor, sound pressure sensor, surface acoustic wave sensor, and discharge scenario is by the inspection in detection module
Survey what device obtained；
Detection device includes: half package copper sheet 101 on detection means, by adjustable screw 102 is fixed on copper
The ultrasonic sensor 103 of 101 inside of plate；Ultrasonic sensor includes antenna 1021 and passive coaxial device 1022；102 top of screw is solid
The insulating regions of antenna 1021 are scheduled on, bottom end is connect with copper sheet 101；It is connected between copper sheet 101 and detection device；Antenna 1021
Energization body 1023 is distinguished its immediate screw 102 and is connected；
Wherein, the energization body of antenna 1021 passes through its immediate screw 102 of signal wire 1026 respectively and connects, signal wire
1026 one end are connected to the end of an antenna energization body 1023, and the other end is connected on adjacent screw 102；Antenna 1021 with
Detection device inner surface is non-intersecting；Antenna 1021 is fixedly connected with copper sheet 101 by screw 102, and the length of screw 102 is according to super
The depth in detection device of sonic transducer 103 determines；Passive coaxial device 1022 in ultrasonic sensor 103 is attached to antenna
1021 lower surfaces, 1021 upper surface of antenna are equipped with first through hole 1027, are installed with signal wire 1026 in first through hole 1027；
1022 one end of passive coaxial device is equipped with protrusion 1028, and the length of protrusion 1028 is slightly above the thickness of antenna 1021, convex
The size and first through hole 1027 for playing 1028 match and are placed in first through hole 1027, and protrusion 1028 is in 1021 front of antenna
The current-carrying part of exposing with the positive antenna energization body 1023 of antenna 1021 by welding；Passive coaxial device 1022 is attached to antenna
1021 back side；1027 inner wall of first through hole is covered with the conductive strips 1030 connecting with antenna energization body 1023, conductive strips 1030 with
The current-carrying part of protrusion 1028 is in contact；
Ultrasonic sensor 103 further includes connector 1031, and accordingly connecing for passive coaxial device 1022 is arranged in connector one end
On mouth, connector 1031 is embedded in copper sheet 101；
Passive coaxial device 1022 is fixedly connected with 102 lower surface of antenna；Copper sheet 101 is equipped with annular groove 1011, annular groove
Ring pads are equipped in 1011；The insulating regions of antenna 1021 are equipped with the second through-hole 1031, and the top of screw 102 passes through the second through-hole
1031 are fixedly connected with antenna 1021, and the bottom end of screw 102 is fixed on copper sheet 101 equipped with opposite with 1031 position of the second through-hole
In the mounting hole answered, screw 102 will test device by mounting hole and be fixed, and wherein mounting hole is zh circular configuration, round
The inside surface roughness of structure is less than Ra1.0, and the corresponding ring pads of connector are placed in the inside of copper sheet 101.
It further include mechanical noise reducing apparatus in a kind of mode in the cards, mechanical noise reducing apparatus includes: top denoising body
01, middle part articulamentum 02 and bottom noise reducing plate 03,
Wherein, denoising body 01 in top includes: denoising container 001, denoising medium 002, air pump 003, denoises and sets in container 001
There is reserved space, denoising medium 002 is placed in reserved space, and denoising medium 002 includes absorbing particles, absorbs powder or absorption
Fluid it is one or more, the connection of air pump 003 is denoised container 001 and wraps up tracheae 004, what air pump 003 generated is made an uproar by tracheae 004
Sound is passed by tracheae 004 and denoising medium 002, wherein when denoising body 001 obtains external sound when top, generates vibration
It is dynamic, container 001 is denoised at this time and denoising medium 002 absorbs simultaneously, obstructs the vibration that top denoising body 001 generates, and denoises container
001 material is flexible material, and flexible material includes rubber material, nylon material, cotton wool fabric material；
It denoises and is equipped with n1 barrier assembly 005 in container 001, barrier assembly 005 will denoise container 001 and be divided into n2 mutually
Independent small space, barrier assembly 005 are sheets, and being subsequently placed in denoising container with laterally and longitudinally cross arrangement
001, each mutually independent small space is placed with denoising medium 002, placed denoising medium 002 there are skies in small space
Gap, and denoise medium 002 and placed in small space uniform, small space is being arranged to n3 layers along sound direction of transfer, top denoising
Body 01 is placed in the top of bottom noise reducing plate 03；
Wherein, cylinder 031, lever 032, iron pan (pedestal) 033, spring 034, support rod are equipped in bottom noise reducing plate 03
035, lantern ring 036, iron pan 033 are fixed on soil surface, and polypropylene material, the lower end of lever 032 are wrapped in outside iron pan 033
It is mounted on iron pan 033 by lantern ring 036, the top of lever 032 is the tubular structure on hemispherical convex surface, under lever 032
Side pressure is equipped with lantern ring 036, cylinder 031 is for upper end closed on iron pan 033 between support rod 035 and the inner wall of lever 032
Column construction, the inner surface of cylinder 031 have the convex surface of semicircle shape, and 032 upper end of lever is goed deep into cylinder 031 in column construction,
For spring 034 on the top of support rod 035, spring 034 is located at the convex of 031 upper end closed end lower surface of cylinder and 032 upper end of lever
Electric wire is equipped on surface, in support rod 035 to be connected with the air pump 003 in top denoising body 01；
Middle part articulamentum 02 is equipped with through-hole 021, and electric wire is connected by through-hole with air pump 003, and intermediate connecting layer 02 is
The plank of rectangular shape, and inside is empty slot 022, and empty slot 022 is placed and winds cricoid denoising medium 002.
Wherein, mechanical noise reducing apparatus, for reducing the noise of machinery itself.
The invention mainly by capturing to the high frequency region, low frequency range, overlay region that occur in audio, judges these three
The corresponding frame type in region obtains decaying noise by frame type, filter factor, noise estimation reference value three, through filtering algorithm
Processing denoised after signal, can not only alleviate the noise problem occurred in audio, but also can also improve user has body
Test effect.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by written explanation
Specifically noted structure is achieved and obtained in book, claims and attached drawing.
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example to be used to explain the present invention together, not be construed as limiting the invention.In the accompanying drawings:
Fig. 1 is a kind of environmental noise removal system structure diagram in the embodiment of the present invention；
Fig. 2 is the recursive average algorithm flow chart of minimum value control in the embodiment of the present invention；
Fig. 3 is the structure chart of detection device in the embodiment of the present invention；
Fig. 4 is the structure chart of mechanical noise reducing apparatus in the embodiment of the present invention；
Fig. 5 is that middle and upper part of the embodiment of the present invention denoises body structural schematic diagram；
Fig. 6 is bottom noise reducing plate structural schematic diagram in the embodiment of the present invention.
Specific embodiment
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein
Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
The embodiment of the present invention provides a kind of environmental noise removal system, as shown in Figure 1, comprising:
Trapping module 1, for capturing the first sound frame of voice play signal and previous frame the second sound frame of the first sound frame；
Detection module 2 determines corresponding in the first sound frame for detecting high frequency region, low frequency range and the overlay region of the first sound frame
Frame type and the corresponding different frame address of different frame type, frame type include: speech frame, noise frame, secondary speech frame, secondary make an uproar
Acoustic frame；
Filter module 3, for being filtered to obtain filter factor to the first sound frame；
Determining module 4 when there are voice signal, calculates second for determining the first sound frame with the presence or absence of voice signal
The noise estimation value of sound frame, and reference value is estimated using the noise estimation value of the second sound frame as the noise of the first sound frame；
Processing module 5 obtains decaying noise according to frame type, filter factor, noise estimation reference value three with calculating, leads to
Signal after crossing filtering the first audio of algorithm process and being denoised；
Preferably, the frame type of the first sound frame is that speech frame, noise frame, secondary speech frame, secondary noise frame are any one or more
Combination.
Wherein, voice signal whether there is for determining first sound frame, such as VAD (Voice Activity can be used
Detection, Voice activity detection) algorithm realization, above-mentioned vad algorithm includes but is not limited to: frame amplitude algorithm, frame energy are calculated
Method, short-time zero-crossing rate parser, energy and sliding window algorithm, neural network algorithm etc., benefit is can be improved to sound
The identification of voice signal present in frame.
The above-mentioned algorithm for noise estimation value, such as the recursive average algorithm that minimum value controls can be used and sought,
As shown in Fig. 2, referring to step 201-203:
Step 201: being detected by detection module and obtain the minimum value with noise frequency；
It should be noted that the minimum value in step 201 be to noise according to a preliminary estimate.
Step 202: Probability p existing for voice is calculated by minimum value that step 201 obtains；
Step 203: noise is calculated according to formula p (λ, k)=p (Hk1 | Y (λ, k)) p (λ, k)=p (Hk1 | Y (λ, k))
The smoothing factor of estimation；
It should be noted that making smoothing factor be intended to 1 when probability P is not less than 0.5, that is, using the noise of previous frame
Estimated value is estimated as the noise of present frame, when probability P is less than 0.5, so that smoothing factor is intended to 0, i.e., using present frame
Power carries out noise estimation；
Wherein, λ indicates that frame number, k indicate that frequency point index, Y indicate the noisy speech spectrum of frequency domain, and P indicates frequency.
Step 204: being estimated according to minimum value, probability P and the smooth silver that above-mentioned steps obtain by recursive average
Noise.
The beneficial effect of the technical solution is: by the detection to the first sound frame, judging high frequency present in the first sound frame
Area, low frequency range and overlay region, and determine corresponding frame type in the first sound frame, the accuracy to frame detection is improved, according to frame
Type can be effectively treated the noise occurred in audio, improve machine operating speed, alleviate the noise occurred in audio
While problem, improve user has experience effect.
The embodiment of the present invention provides a kind of ambient noise removal system, and trapping module includes:
Acquisition unit, for the corresponding energy of stepped-frequency signal each in the first sound frame of acquisition；
Detection module, comprising: the first judging unit works as stepped-frequency signal for judging the corresponding frame type of the first sound frame
Energy when being in first threshold, judge that current first sound frame for speech frame, and demarcates the corresponding first position of speech frame；When frequency
When the energy of rate sampled point is in second threshold, judge current first sound frame for noise frame, and demarcate noise frame corresponding second
Position；When the energy of stepped-frequency signal is in third threshold value, judge that current first sound frame for time speech frame, and demarcates time voice
The corresponding the third place of frame；When the energy of stepped-frequency signal is in four threshold values, judge current first sound frame for time noise frame,
And demarcate time corresponding 4th position of noise frame.
The principle of audio sample is: sound is a kind of energy wave in fact, therefore also has the feature of frequency and amplitude, frequency pair
Should be in time axis, amplitude corresponds to level axis, due to wave be it is unlimited smooth, string can be regarded as by numerous points group
At, due to memory space be it is relatively limited, in digital encoding procedure, it is necessary to sample to the point of string, wherein sampling
Process is exactly to extract the frequency values of certain point, and obtain the corresponding energy of point.Its benefit is that can have by the sampling to audio
Present frame state in which is judged on effect ground, then by the comparison of threshold value, can understand the corresponding frame type of present frame in time.
Such as it is normalized the energy of the corresponding sampled point of different frame type to obtain corresponding decibel value, it is assumed that
When decibel is greater than 500 decibels, this frame is judged for noise frame, when decibel is greater than 300 decibels and when less than 500 decibels, judges this
Frame is time noise frame, when decibel is greater than 100 decibels and when less than 300 decibels, judges that this frame is secondary speech frame, when decibel is less than
At 100 decibels, judge this frame for speech frame.Wherein, it should be noted that above-mentioned first threshold is less than third threshold value, third threshold value
Less than the 4th threshold value, the 4th threshold value is less than third threshold value.
The beneficial effect of the technical solution is: by carrying out threshold comparison to the energy of acquisition, obtaining the corresponding frame of the frame
Type not only accelerates audio identification speed, but also also improves the treatment effeciency to the noise in audio.
The embodiment of the present invention provides a kind of ambient noise removal system, and detection module includes:
Storage unit, for saving the corresponding high frequency region of stepped-frequency signal and low frequency range in the first sound frame, and according to capture
The successive sequence of voice play signal carries out sample number, by the corresponding length of sampled point and the corresponding sample number of sampled point into
Row saves, and length is the memory space that sampled point occupies；
Second judgment unit, for whether within the preset frequency range to judge sampled point, when the corresponding frequency of sampled point is super
Out when predeterminated frequency range, the corresponding length of sampled point and the corresponding sample number of sampled point are obtained, is calculated by processing module
Obtain interference phase；
Wherein, compared according to second judgment unit and obtain the corresponding maximum of high frequency region minimum corresponding with low frequency range；
Processing unit is also used to that interference signal amplitude is calculated according to maximum and minimum point.
Wherein occupying memory space for sampled point is because for sampled point, and sampling system can distribute certain storage position and come
The sonic wave amplitude state of sound wave is expressed, for example, it is assumed that carrying out 8 samplings, the corresponding energy value of sampled point to a sound wave
Respectively A1-A8, if but using 2 sample space sizes, it as a result can only retain the value of preceding 4 points in A1-A8, if using 3
The sample space size of position, then can recorde all information of 8 points, wherein and the value of sample rate and sample space size is bigger,
For the sound waveform of record closer to original signal, benefit is not only can store more by setting biggish memory space
Data, but also can sampling precision be got higher, improve the reduction rate of audio.
The beneficial effect of the technical solution is: by setting biggish storage position, available more sampled points are improved
Also improve audio reduction rate while sampling precision, calculated by the sampling to sampled point the amplitude for obtaining interference signal and
Phase can effectively reject the interference signal in original signal, improve the accuracy for obtaining pure voice signal.
The embodiment of the present invention provides a kind of ambient noise removal system, further includes:
At least two acoustic sensors, wherein including at least one first acoustic sensor and at least one second acoustics
Sensor, for receiving the audio signal outside acoustic sensor；
Processing module is also used to handle the first audio signal of the first acoustic sensor acquisition, subtracts the second acoustics sensor
The second audio signal that device obtains, obtains third audio signal；
Third judging unit, for judging that the sound wave of the first audio signal and the second audio signal whether there is delay, when
In the presence of, by the first audio signal and the second audio signal, carry out signal synchronous contrast, the common signal obtained after delay is the
Three audio signals；Delay is master control direction and non-master prosecutor to during sound transmission, since range difference forms the time difference；
Wherein, the first audio signal is the sending of master control direction with noisy voice signal, the second audio signal right and wrong
The noise signal that master control direction issues, third audio signal are the voice signals after the denoising of the first audio signal.
For above-mentioned delay, for example, by using delay caused by vocal cord vibration matching, being placed in acquisition module can adopt first
The first position for collecting vocal cords vibration, then using the vocal cord vibration of neck as source, in main the first acoustic sensor for determining direction
Voice signal in, match the first voice data of oneself；Acquisition module, which is placed in, again can collect the second of vocal cords vibration
Position in the main voice signal of the first acoustic sensor for determining direction, matches then using the vocal cord vibration of neck as source
The second speech data of oneself.It is 2-4mm at a distance from vocal cords vibration that wherein first position, which is acquisition device, and the second position is to adopt
Acquisition means are 7-9mm at a distance from vocal cords vibration, obtain the first voice data and second position acquisition with first position second
Voice data compares, it may appear that voice delay, it should be noted that the first voice data is normal data.
The beneficial effect of the technical solution is: being obtained by the second audio signal that the first audio signal of acquisition subtracts acquisition
To third audio signal, the sound of the directionally independent sending of master control accurately can be obtained in complex situations.
The embodiment of the present invention provides a kind of ambient noise removal system, and acoustic sensor is also used to device in detection circuit
Discharge scenario, acoustic sensor include: ultrasonic sensor, sound pressure sensor, surface acoustic wave sensor, and discharge scenario is to pass through inspection
What the detection device surveyed in module obtained；
Detection device includes: half package copper sheet 101 on detection means, by adjustable screw 102 is fixed on copper
The ultrasonic sensor 103 of 101 inside of plate；Ultrasonic sensor includes antenna 1021 and passive coaxial device 1022；102 top of screw is solid
The insulating regions of antenna 1021 are scheduled on, bottom end is connect with copper sheet 101；It is connected between copper sheet 101 and detection device；Antenna 1021
Energization body 1023 is distinguished screw 102 adjacent thereto and is connected；
Wherein, the energization body 1023 of antenna 1021 is connected by the screw 102 adjacent thereto of signal wire 1026 respectively, signal
1026 one end of line is connected to the end of an antenna energization body 1023, and the other end is connected on adjacent screw 102；Antenna 1021
It is non-intersecting with detection device inner surface；Antenna 1021 and copper sheet 101 are fixedly connected by screw 102, the length of screw 102 according to
The depth in detection device of ultrasonic sensor 103 determines；Passive coaxial device 1022 in ultrasonic sensor 103 is attached to day
1021 lower surface of line, 1021 upper surface of antenna are equipped with first through hole 1027, are installed with signal wire 1026 in first through hole 1027；
1022 one end of passive coaxial device is equipped with protrusion 1028, and the length of protrusion 1028 is slightly above the thickness of antenna 1021, convex
The size and first through hole 1027 for playing 1028 match and are placed in first through hole 1027, and protrusion 1028 is in 1021 front of antenna
The current-carrying part and the positive antenna energization body 1023 of antenna 1021 of exposing weld；Passive coaxial device 1022 is attached to antenna 1021
The back side；1027 inner wall of first through hole is covered with the conductive strips 1030 connecting with antenna energization body 1023, conductive strips 1030 and protrusion
1028 conductive portions contact；
Ultrasonic sensor 103 further includes connector 1031, and accordingly connecing for passive coaxial device 1022 is arranged in connector one end
On mouth, connector 1031 is embedded in copper sheet 101；
Passive coaxial device 1022 is fixedly connected with 102 lower surface of antenna；Copper sheet 101 is equipped with annular groove 1011, annular groove
Ring pads are equipped in 1011；The insulating regions of antenna 1021 are equipped with the second through-hole 1031, and the top of screw 102 passes through the second through-hole
1031 are fixedly connected with antenna 1021, and the bottom end of screw 102 is fixed on copper sheet 101 equipped with opposite with 1031 position of the second through-hole
In the mounting hole answered, screw 102 will test device by mounting hole and be fixed, and wherein mounting hole is circular configuration, circle knot
The inside surface roughness of structure is less than Ra1.0, and the corresponding ring pads of connector are placed in the inside of copper sheet 101.
It should be noted that screw bottom end is placed with non-conductive gasket, allow between screw bottom end and ring pads in barrier-like
State；Protrusion passes through the antenna energization body of welding antenna face in the current-carrying part that antenna face is exposed, and is not only to guarantee to lead to
The key of electricity, wherein conductive strips are in contact with the current-carrying part of protrusion, are to make circuit conducting can more one layer of guarantee；Together
When, passive coaxial device and antenna are attached by hot melt adhesive, and the stability of the two connection can be improved.
The beneficial effect of the technical solution is: the technical program makes to be screwed, and enhances the stability of machinery itself,
The low-frequency minimum of detection device can be made to be effectively reduced by ultrasonic sensor, low-frequency range characteristic is well changed
It is kind.
The embodiment of the present invention provides a kind of ambient noise removal system, further includes mechanical noise reducing apparatus, as shown in figure 4, machine
Tool noise reducing apparatus includes: that top denoises body 01, middle part articulamentum 02 and bottom noise reducing plate 03,
Wherein, as shown in figure 5, top denoising body 01 includes: denoising container 001, denoising medium 002, air pump 003, denoising
Reserved space is equipped in container 001, denoising medium 002 is placed in reserved space, and denoising medium 002 includes absorbing particles, inhales
It receives powder or absorbs the one or more of fluid, the connection of air pump 003 is denoised container 001 and wrapped up tracheae 004, air pump by tracheae 004
003 noise generated is passed by tracheae 004 and denoising medium 002, wherein when top, denoising body 001 obtains extraneous sound
When sound, vibration is generated, container 001 is denoised at this time and denoising medium 002 absorbs simultaneously, obstructs the vibration that top denoising body 001 generates
Dynamic, the material of denoising container 001 is flexible material, and flexible material includes rubber material, nylon material, cotton wool fabric material；
It denoises and is equipped with n1 barrier assembly 005 in container 001, barrier assembly 005 will denoise container 001 and be divided into n2 mutually
Independent small space, barrier assembly 005 are sheets, and being subsequently placed in denoising container with laterally and longitudinally cross arrangement
001, each mutually independent small space is placed with denoising medium 002, placed denoising medium 002 there are skies in small space
Gap, and denoise medium 002 and placed in small space uniform, small space is being arranged to n3 layers along sound direction of transfer, top denoising
Body 01 is placed in the top of bottom noise reducing plate 03；
Wherein, cylinder 031, lever 032, iron pan (pedestal) 033, spring 034, support rod are equipped in bottom noise reducing plate 03
035, lantern ring 036, iron pan 033 are fixed on soil surface, and polypropylene material, the lower end of lever 032 are wrapped in outside iron pan 033
It is mounted on iron pan 033 by lantern ring 036, the top of lever 032 is the tubular structure on hemispherical convex surface, under lever 032
Side pressure is equipped with lantern ring 036, cylinder 031 is for upper end closed on iron pan 033 between support rod 035 and the inner wall of lever 032
Column construction, the inner surface of cylinder 031 have the convex surface of semicircle shape, and 032 upper end of lever is goed deep into cylinder 031 in column construction,
For spring 034 on the top of support rod 035, spring 034 is located at the convex of 031 upper end closed end lower surface of cylinder and 032 upper end of lever
Electric wire is equipped on surface, in support rod 035 to be connected with the air pump 003 in top denoising body 01；
Middle part articulamentum 02 is equipped with through-hole 021, and electric wire is connected by through-hole with air pump 003, and intermediate connecting layer 02 is
The plank of rectangular shape, and inside is empty slot 022, and empty slot 022 is placed and winds cricoid denoising medium 002.
Preferably, mechanical noise reducing apparatus, for reducing the noise of machinery itself.
Wherein, denoising container is divided into n2 mutually independent small spaces by n1 barrier assembly, so that the row of denoising medium
Cloth and layout more diversification, are conducive to for different positions, the denoising medium for filling unlike material reaches noise reduction effect
Most preferably；Certainly, it if the identical component being arranged in each separate space denoises medium, and is placed accordingly according to space size
Component can reach preferable noise reduction effect.
Denoising medium includes the sound-absorbing medium for absorbing acoustic energy and the acoustic isolation medium for separating sound transmission.Its
In, sound-absorbing medium includes but is not limited to perlite medium, vermiculite medium etc., and sound-absorbing medium length is generally 2mm-4mm；Sound insulation is situated between
Matter includes but is not limited to Rubber Media, silica gel medium etc., and the length of acoustic isolation medium is generally 2mm-6mm.
The beneficial effect of the technical solution is: denoising medium and denoising container can be absorbed top denoising body vibration and generate
Sound effectively reduces noise caused by top denoising body, advantageously reduces noise pollution；
Vibration not only can preferably be absorbed using the denoising container of flexible material and generate ground sound, while can be preferably
The propagation for obstructing sound is put into corresponding denoising medium by denoising in body, middle part articulamentum and bottom noise reducing plate on top, can
Mechanical whole noise itself is effectively reduced.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (8)
1. a kind of ambient noise removes system characterized by comprising
Trapping module, for capturing the first sound frame of voice play signal and previous frame the second sound frame of the first sound frame；
Detection module determines corresponding frame class in the first sound frame for detecting high frequency region, low frequency range and the overlay region of the first sound frame
Type and the corresponding different frame address of different frame type, frame type includes: speech frame, noise frame, secondary speech frame, secondary noise frame；
Filter module, for being filtered to obtain filter factor to the first sound frame；
Determining module when there are voice signal, calculates the second sound frame for determining the first sound frame with the presence or absence of voice signal
Noise estimation value, and reference value is estimated using the noise estimation value of the second sound frame as the noise of the first sound frame；
Processing module obtains decaying noise according to frame type, filter factor, noise estimation reference value three with calculating, passes through filter
The first audio of wave algorithm process and the signal after being denoised.
2. a kind of ambient noise as claimed in claim 1 removes system, which is characterized in that
Trapping module includes:
Acquisition unit, for the corresponding energy of stepped-frequency signal each in the first sound frame of acquisition；
Detection module, comprising:
First judging unit, for judging the corresponding frame type of the first sound frame, when the energy of stepped-frequency signal is in first threshold
When, judge that current first sound frame for speech frame, and demarcates the corresponding first position of speech frame；When the energy of stepped-frequency signal is in
When second threshold, judge that current first sound frame for noise frame, and demarcates the corresponding second position of noise frame；When stepped-frequency signal
When energy is in third threshold value, judge that current first sound frame for time speech frame, and demarcates time corresponding the third place of speech frame；When
When the energy of stepped-frequency signal is in four threshold values, current first sound frame is judged for time noise frame, and it is corresponding to demarcate time noise frame
The 4th position.
3. a kind of ambient noise as claimed in claim 1 removes system, which is characterized in that detection module includes:
Storage unit, for saving the corresponding high frequency region of stepped-frequency signal and low frequency range in the first sound frame, and according to capture voice
The successive sequence of play signal carries out sample number, and the corresponding length of sampled point and the corresponding sample number of sampled point are protected
It deposits, length is the memory space that sampled point occupies；
Second judgment unit, for whether within the preset frequency range to judge sampled point, when the corresponding frequency of sampled point is beyond pre-
If when frequency range, obtaining the corresponding length of sampled point and the corresponding sample number of sampled point, being calculated by processing module
Interfere phase；
Wherein, compared according to second judgment unit and obtain the corresponding maximum of high frequency region minimum corresponding with low frequency range；
Processing unit is also used to that interference signal amplitude is calculated according to maximum and minimum point.
4. as a kind of claim 1-3 any ambient noise removes system, which is characterized in that the frame type of the first sound frame is language
Any one or more combination of sound frame, noise frame, secondary speech frame, secondary noise frame.
5. a kind of ambient noise as claimed in claim 1 removes system, which is characterized in that further include:
At least two acoustic sensors, wherein including at least one first acoustic sensor and at least one second acoustics sensor
Device, for receiving the audio signal outside acoustic sensor；
Processing module is also used to handle the first audio signal of the first acoustic sensor acquisition, subtracts the second acoustic sensor and obtain
The second audio signal taken, obtains third audio signal；
Third judging unit, the sound wave for judging the first audio signal and the second audio signal work as presence with the presence or absence of delay
When, by the first audio signal and the second audio signal, signal synchronous contrast is carried out, the common signal obtained after delay is third sound
Frequency signal；Delay is master control direction and non-master prosecutor to during sound transmission, since range difference forms the time difference；
Wherein, the first audio signal is the sending of master control direction with noisy voice signal, and the second audio signal is non-master control
The noise signal that direction issues, third audio signal are the voice signals after the denoising of the first audio signal.
6. a kind of ambient noise as claimed in claim 5 removes system, acoustic sensor is also used to the electric discharge of device in detection circuit
Situation, acoustic sensor include: ultrasonic sensor, sound pressure sensor, surface acoustic wave sensor, and discharge scenario is by detecting mould
What the detection device in block obtained；
Detection device includes: half package copper sheet 101 on detection means, by adjustable screw 102 is fixed on copper sheet 101
The ultrasonic sensor 103 of inside；Ultrasonic sensor includes antenna 1021 and passive coaxial device 1022；102 top of screw is fixed on
The insulating regions of antenna 1021, bottom end are connect with copper sheet 101；It is connected between copper sheet 101 and detection device；The energization of antenna 1021
Body 1023 is distinguished its immediate screw 102 and is connected；
Wherein, the energization body of antenna 1021 passes through its immediate screw 102 of signal wire 1026 respectively and connects, signal wire 1,026 1
End is connected to the end of an antenna energization body 1023, and the other end is connected on adjacent screw 102；Antenna 1021 and detection fill
It is non-intersecting to set inner surface；Antenna 1021 is fixedly connected with copper sheet 101 by screw 102, and the length of screw 102 is according to ultrasonic sensing
The depth in detection device of device 103 determines；Passive coaxial device 1022 in ultrasonic sensor 103 is attached under antenna 1021
Surface, 1021 upper surface of antenna are equipped with first through hole 1027, are installed with signal wire 1026 in first through hole 1027；
1022 one end of passive coaxial device is equipped with protrusion 1028, and the length of protrusion 1028 is slightly above the thickness of antenna 1021, protrusion
1028 size and first through hole 1027 matches and is placed in first through hole 1027, and protrusion 1028 is just being showed in antenna 1021
Current-carrying part out with the positive antenna energization body 1023 of antenna 1021 by welding；Passive coaxial device 1022 is attached to antenna
1021 back side；1027 inner wall of first through hole is covered with the conductive strips 1030 connecting with antenna energization body 1023, conductive strips 1030 with
The current-carrying part of protrusion 1028 is in contact；
Ultrasonic sensor 103 further includes connector 1031, and connector one end is arranged on the corresponding interface of passive coaxial device 1022,
Connector 1031 is embedded in copper sheet 101；
Passive coaxial device 1022 is fixedly connected with 102 lower surface of antenna；Copper sheet 101 is equipped with annular groove 1011, annular groove 1011
It is interior to be equipped with ring pads；The insulating regions of antenna 1021 are equipped with the second through-hole 1031, and the top of screw 102 passes through the second through-hole 1031
It is fixedly connected with antenna 1021, the bottom end of screw 102 is fixed on copper sheet 101 equipped with corresponding with 1031 position of the second through-hole
In mounting hole, screw 102 will test device by mounting hole and be fixed, and wherein mounting hole is circular configuration, circular configuration
Inside surface roughness is less than Ra1.0, and the corresponding ring pads of connector are placed in the inside of copper sheet 101.
7. a kind of ambient noise as claimed in claim 1 removes system, which is characterized in that it further include mechanical noise reducing apparatus, machinery drop
Equipment of making an uproar includes: that top denoises body 01, middle part articulamentum 02 and bottom noise reducing plate 03,
Wherein, denoising body 01 in top includes: denoising container 001, denoising medium 002, air pump 003, is denoised in container 001 equipped with pre-
Spacing, denoising medium 002 are placed in reserved space, and denoising medium 002 includes absorbing particles, absorbs powder or absorb fluid
It is one or more, the connection of air pump 003 is denoised container 001 and wraps up tracheae 004, the noise that air pump 003 generates is logical by tracheae 004
Tracheae 004 is crossed to pass with denoising medium 002, wherein when denoising body 001 obtains external sound when top, vibration is generated, this
When denoising container 001 and denoise medium 002 and absorb simultaneously, obstruct the vibration that top denoising body 001 generates, denoise container 001
Material is flexible material, and flexible material includes rubber material, nylon material, cotton wool fabric material；
It denoises and is equipped with n1 barrier assembly 005 in container 001, barrier assembly 005 will denoise container 001 and be divided into n2 independently of each other
Small space, barrier assembly 005 is sheet, and with laterally and longitudinally cross arrangement being subsequently placed at denoising container in 001,
Each mutually independent small space is placed with denoising medium 002, placed denoising medium 002 there are gaps in small space, and
It denoises medium 002 to place in small space uniform, small space is being arranged to n3 layers along sound direction of transfer, and top denoising body 01 is set
In the top of bottom noise reducing plate 03；
Wherein, cylinder 031, lever 032, iron pan (pedestal) 033, spring 034, support rod 035, set are equipped in bottom noise reducing plate 03
Ring 036, iron pan 033 are fixed on soil surface, and polypropylene material is wrapped in outside iron pan 033, and the lower end of lever 032 passes through set
Ring 036 is mounted on iron pan 033, and the top of lever 032 is the tubular structure on hemispherical convex surface, and the lower end of lever 032 is pressed in
On iron pan 033, lantern ring 036 is equipped between support rod 035 and the inner wall of lever 032, cylinder 031 is the cylindricality knot for upper end closed
Structure, the inner surface of cylinder 031 have the convex surface of semicircle shape, and 032 upper end of lever is goed deep into cylinder 031 in column construction, spring 034
On the top of support rod 035, spring 034 is located on the nonreentrant surface of 031 upper end closed end lower surface of cylinder and 032 upper end of lever,
Electric wire is equipped in support rod 035 to be connected with the air pump 003 in top denoising body 01；
Middle part articulamentum 02 is equipped with through-hole 021, and electric wire is connected by through-hole with air pump 003, and intermediate connecting layer 02 is rectangular
The plank of shape, and inside is empty slot 022, and empty slot 022 is placed and winds cricoid denoising medium 002.
8. a kind of ambient noise as claimed in claim 7 removes system, which is characterized in that mechanical noise reducing apparatus, for reducing machinery
The noise of itself.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811142872.6A CN109616133B (en) | 2018-09-28 | 2018-09-28 | Environmental noise removing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811142872.6A CN109616133B (en) | 2018-09-28 | 2018-09-28 | Environmental noise removing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109616133A true CN109616133A (en) | 2019-04-12 |
| CN109616133B CN109616133B (en) | 2021-11-30 |
Family
ID=66002245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811142872.6A Active CN109616133B (en) | 2018-09-28 | 2018-09-28 | Environmental noise removing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109616133B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111968615A (en) * | 2020-08-31 | 2020-11-20 | Oppo广东移动通信有限公司 | Noise reduction processing method and device, terminal equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5485522A (en) * | 1993-09-29 | 1996-01-16 | Ericsson Ge Mobile Communications, Inc. | System for adaptively reducing noise in speech signals |
| CN102938254A (en) * | 2012-10-24 | 2013-02-20 | 中国科学技术大学 | Voice signal enhancement system and method |
| CN103813251A (en) * | 2014-03-03 | 2014-05-21 | 深圳市微纳集成电路与系统应用研究院 | Hearing-aid denoising device and method allowable for adjusting denoising degree |
| CN205406087U (en) * | 2016-02-29 | 2016-07-27 | 武汉大学 | System of making an uproar that goes that can be used to automobile engine failure recognition |
| CN106486131A (en) * | 2016-10-14 | 2017-03-08 | 上海谦问万答吧云计算科技有限公司 | A kind of method and device of speech de-noising |
-
2018
- 2018-09-28 CN CN201811142872.6A patent/CN109616133B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5485522A (en) * | 1993-09-29 | 1996-01-16 | Ericsson Ge Mobile Communications, Inc. | System for adaptively reducing noise in speech signals |
| CN102938254A (en) * | 2012-10-24 | 2013-02-20 | 中国科学技术大学 | Voice signal enhancement system and method |
| CN103813251A (en) * | 2014-03-03 | 2014-05-21 | 深圳市微纳集成电路与系统应用研究院 | Hearing-aid denoising device and method allowable for adjusting denoising degree |
| CN205406087U (en) * | 2016-02-29 | 2016-07-27 | 武汉大学 | System of making an uproar that goes that can be used to automobile engine failure recognition |
| CN106486131A (en) * | 2016-10-14 | 2017-03-08 | 上海谦问万答吧云计算科技有限公司 | A kind of method and device of speech de-noising |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111968615A (en) * | 2020-08-31 | 2020-11-20 | Oppo广东移动通信有限公司 | Noise reduction processing method and device, terminal equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109616133B (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11534100B2 (en) | On-ear detection | |
| US9538301B2 (en) | Device comprising a plurality of audio sensors and a method of operating the same | |
| CN205847524U (en) | Loudspeaker enclosure | |
| EP2278356B1 (en) | Apparatus and method for detecting usage profiles of mobile devices | |
| CN102832908A (en) | Wavelet transform and variable-step-size LMS (least mean square) adaptive filtering based signal denoising method | |
| KR101786855B1 (en) | Damping vibrational wave reflections | |
| CN109920451A (en) | Voice activity detection method, noise suppressing method and noise suppressing system | |
| CN205864675U (en) | Noise cancelling headphone | |
| CN109243426A (en) | A kind of automatization judgement voice false wake-up system and its judgment method | |
| CN109616133A (en) | A kind of environmental noise removal system | |
| CN204902995U (en) | Rotating machinery noise collector with effect gives sound insulation | |
| CN110300362B (en) | Electret bone conduction vibration microphone | |
| CN105909979B (en) | Leakage acoustic characteristic extracting method based on Wavelet Transform Fusion blind source separation algorithm | |
| EP3879184A1 (en) | Noise reduction method and apparatus for household appliance, household appliance, and cooker hood | |
| CN110133363B (en) | Cable level change detection device and method | |
| CN101796799B (en) | Method and communication terminal for detecting the status of a telephone receiver | |
| CN104457970B (en) | A kind of half silencer box of broadband measurement | |
| JP2014055783A (en) | Movement sound detection device and operation method thereof | |
| CN111734393A (en) | Oil well working fluid level testing device and operation method | |
| CN105928666A (en) | Leakage acoustic characteristic extraction method based on Hilbert-Huang transform and blind source separation | |
| CN113970409B (en) | Liquefied gas leakage monitoring method and device based on time-frequency domain analysis | |
| WO2018223466A1 (en) | Intelligent police van loudspeaker | |
| CN106331958A (en) | Echo cancellation method and device | |
| CN210603575U (en) | Noise detection device | |
| CN207556754U (en) | Container tightness digital test machine based on ultrasonic wave |
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 | ||
| CB02 | Change of applicant information |
Address after: 510000 unit on the fourth floor of the first, second and third floors on the west side of No. 1383-5, Guangzhou Avenue South, Haizhu District, Guangzhou City, Guangdong Province (office only) (not for plant use) Applicant after: GUANGZHOU ZIB ARTIFICIAL INTELLIGENCE TECHNOLOGY CO.,LTD. Address before: Room a, unit 1902, 374-2, Beijing Road, Yuexiu District, Guangzhou, Guangdong 510000 Applicant before: GUANGZHOU ZIB ARTIFICIAL INTELLIGENCE TECHNOLOGY CO.,LTD. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |