KR20140052489A - Method and apparatus of adaptive audio gain adjustment in multiple mic based sound quality enhancement system - Google Patents
Method and apparatus of adaptive audio gain adjustment in multiple mic based sound quality enhancement system Download PDFInfo
- Publication number
- KR20140052489A KR20140052489A KR1020120118610A KR20120118610A KR20140052489A KR 20140052489 A KR20140052489 A KR 20140052489A KR 1020120118610 A KR1020120118610 A KR 1020120118610A KR 20120118610 A KR20120118610 A KR 20120118610A KR 20140052489 A KR20140052489 A KR 20140052489A
- Authority
- KR
- South Korea
- Prior art keywords
- noise
- present
- sound quality
- speech
- gain adjustment
- Prior art date
Links
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 8
- 238000000034 method Methods 0.000 title abstract description 12
- 230000006872 improvement Effects 0.000 claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 6
- 238000010295 mobile communication Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 239000000470 constituent Substances 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000276489 Merlangius merlangus Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R3/00—Circuits for transducers, loudspeakers or microphones
- H04R3/005—Circuits for transducers, loudspeakers or microphones for combining the signals of two or more microphones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R2410/00—Microphones
- H04R2410/01—Noise reduction using microphones having different directional characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Otolaryngology (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
The present invention relates to sound quality improvement and provides a method and apparatus for adaptive audio gain adjustment in a multi-microphone based sound quality improvement system. According to the present invention, even when the kind of noise changes, it can adaptively react to provide a uniform tone, and has a small voice loss even in an abnormal noise environment of low SNR (Signal to Noise Ratio). It can cope with real time, and even if the kind of noise suddenly changes, it can be processed in real time. In addition, it uses the low power according to the small amount of computation, the solution is provided by the software type library, the general purpose is increased, and the short time tuning is required.
Description
The present invention relates to sound quality improvement, and more particularly, to a method and apparatus for adaptive audio gain adjustment in a multi-microphone-based sound quality improvement system.
The ambient noise that occurs in real life always pollutes the pure voice and severely lowers the sound quality of mobile communication. Various methods have been studied for improving the sound quality of mobile communication by removing the effect of ambient noise for a long time. Recently, the elimination or solving of ambient noise in mobile communication has become a big issue.
A technical problem of the present invention is to extract only noise from a voice contaminated by ambient noise and to provide clean sound quality in mobile communication based on the extracted noise.
According to one aspect of the present invention, there is provided an adaptive audio gain adjustment method in a multiple microphone-based sound quality improvement system.
According to another aspect of the present invention, there is provided an adaptive audio gain adjustment apparatus in a multi-microphone-based sound quality improvement system.
According to the present invention, even if the type of noise changes, it can adaptively respond to provide a certain tone color, and has a small voice loss even in a noisy noise environment with low SNR (Signal to Noise Ratio).
Also, according to the present invention, impulse noise can be responded in real time, and even if the kind of noise suddenly changes, it can be processed in real time.
Further, according to the present invention, there is an advantage that a low power according to a small amount of computation is used, a solution is provided by a software type library, the versatility is increased, and short-term tuning is required.
1 shows a method for processing a noisy speech signal according to the present invention.
2 shows an example of a waveform and a spectrogram of speech according to the present invention.
Fig. 3 shows another example of the waveform and spectrogram of speech according to the present invention.
Fig. 4 shows another example of waveforms and spectrograms of speech according to the present invention.
Hereinafter, some embodiments of the present invention will be described in detail with reference to exemplary drawings. It should be noted that, in adding reference numerals to the constituent elements of the drawings, the same constituent elements are denoted by the same reference symbols as possible even if they are shown in different drawings. In the following description of the embodiments of the present invention, a detailed description of known configurations or functions will be omitted when it is determined that the description of the present invention may be omitted.
Various methods are proposed for solving the problem of ambient noise in mobile communication and providing clean sound quality. However, existing methods do not provide a uniform tone when the type of noise changes, and a lot of voice loss occurs in a non-static noise environment with low SNR. Also, according to the conventional methods, impulse noise occurring over a short period of time can not be coped with in real time, and a certain adaptation time is required when the kind of noise suddenly changes. In addition, the conventional methods require a high computation amount, so that high power is used in many cases, and a solution is provided with a chip of a hardware type, so that there is no general versatility and a case where a long tuning is required There were many.
In order to solve the above-mentioned problems, the present invention proposes the following method. The present invention may be referred to as ElectroVox-2.
1 shows a method for processing a noisy speech signal according to the present invention.
Referring to FIG. 1, a sound quality improvement apparatus according to the present invention acquires noisy speech through a first microphone and a second microphone, respectively. For example, the first microphone may be a rear mic, and the second microphone may be a front mic.
Then, the sound quality improvement apparatus performs pre-processing. The preprocessing step includes applying adaptive gain, performing mixture tracking, and performing spectrum whiting.
Then, the sound quality improvement apparatus performs noise estimation. The noise estimation step includes applying a probability weight, applying a psychoacoustic forgetting factor, and performing an estimated noise refine.
Then, the sound quality improvement device performs speech enhancement. The speech enhancement step includes performing noise masking and performing enhanced speech tuning.
Through the above process, the sound quality improvement apparatus can obtain improved speech. According to the technical advantages of the present invention as described above, even when the kind of noise changes, the system can adaptively respond to a certain tone color, and has a small voice loss even in an abnormal noise environment of low SNR (Signal to Noise Ratio). Also, according to the present invention, impulse noise can be responded in real time, and even if the kind of noise suddenly changes, it can be processed in real time. Further, according to the present invention, there is an advantage that a low power according to a small amount of computation is used, a solution is provided by a software type library, the versatility is increased, and short-term tuning is required.
2 shows an example of a waveform and a spectrogram of speech according to the present invention. 2 shows a case where the present invention is applied to a clear voice.
(B) is a spectrogram of the clean speech; (c) is a waveform of the speech processed by the present invention on the clean speech; (d) Represents a spectrogram about the processed speech. When a clear voice as shown in (a) is input, most of the existing solutions cause voice loss. However, according to the present invention, the spectrogram of the clean speech and the clean speech in (a) and (b) and the waveform of the processed speech in (c) and (d) It can be seen that the loss of the original signal hardly occurs when the spectrograms are compared with each other.
Fig. 3 shows another example of the waveform and spectrogram of speech according to the present invention. FIG. 3 shows a case where the present invention is applied to a voice contaminated with public noise.
Referring to FIG. 3, (a) is a waveform of a voice contaminated with public noise, (b) is a spectrogram of a voice contaminated with the public noise, and (c) The waveform of the speech processed by the invention, and (d) the spectrogram of the processed speech. It is technically very difficult to accurately remove noise from a voice polluted by a public noise generated in a restaurant such as the above (a). Generally, even when the noise is removed, the effect of haptic effect is not appreciable due to the noise remaining in the human audible range . However, when comparing (a) and (b) for speech contaminated with public noise and (c) and (d) for speech treated according to the present invention, It can be seen that there is an effect. As shown by the white dotted line in (d) of FIG. 3, the public noise is removed and replaced with a comport residual noise, which provides a highly audible noise canceling performance (or effect).
Fig. 4 shows another example of waveforms and spectrograms of speech according to the present invention. FIG. 4 shows a case where the present invention is applied to a voice contaminated with music noise.
Referring to FIG. 4, (a) is a waveform of a voice contaminated with music noise, (b) is a spectrogram of a voice contaminated with the music noise, and (c) The waveform of the speech processed by the invention, and (d) the spectrogram of the processed speech. It is technically very difficult to remove noise from a voice contaminated with music noise composed of an impulse component as in (a). However, when comparing (a) and (b) with respect to the voice contaminated with music noise and (c) and (d) with the voice treated according to the present invention, It can be seen that there is an effect. According to the present invention, as shown by the white dotted line in FIG. 4 (d), the reaction occurs in real time even in a region where noise suddenly occurs. In addition, as shown by the yellow dotted line in FIG. 4 (d), the impulse noise is largely replaced with the remnant noise after the impulse noise is removed.
The foregoing description is merely illustrative of the technical idea of the present invention and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas falling within the scope of the same shall be construed as falling within the scope of the present invention.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020120118610A KR20140052489A (en) | 2012-10-24 | 2012-10-24 | Method and apparatus of adaptive audio gain adjustment in multiple mic based sound quality enhancement system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020120118610A KR20140052489A (en) | 2012-10-24 | 2012-10-24 | Method and apparatus of adaptive audio gain adjustment in multiple mic based sound quality enhancement system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| KR20140052489A true KR20140052489A (en) | 2014-05-07 |
Family
ID=50885719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| KR1020120118610A KR20140052489A (en) | 2012-10-24 | 2012-10-24 | Method and apparatus of adaptive audio gain adjustment in multiple mic based sound quality enhancement system |
Country Status (1)
| Country | Link |
|---|---|
| KR (1) | KR20140052489A (en) |
-
2012
- 2012-10-24 KR KR1020120118610A patent/KR20140052489A/en not_active Application Discontinuation
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9558755B1 (en) | Noise suppression assisted automatic speech recognition | |
| US8538035B2 (en) | Multi-microphone robust noise suppression | |
| US8781137B1 (en) | Wind noise detection and suppression | |
| KR20150005979A (en) | Systems and methods for audio signal processing | |
| EP3005362B1 (en) | Apparatus and method for improving a perception of a sound signal | |
| GB2465910A (en) | Method and device for low-latency auditory model-based single-channel speech enhancement | |
| US11380312B1 (en) | Residual echo suppression for keyword detection | |
| Wang et al. | Deep neural network based supervised speech segregation generalizes to novel noises through large-scale training | |
| CN109151663B (en) | Signal processor and signal processing system | |
| Li et al. | Single-channel speech enhancement based on improved frame-iterative spectral subtraction in the modulation domain | |
| Miyazaki et al. | Theoretical analysis of parametric blind spatial subtraction array and its application to speech recognition performance prediction | |
| Mowlaee et al. | Sinusoidal masks for single channel speech separation | |
| KR20140052489A (en) | Method and apparatus of adaptive audio gain adjustment in multiple mic based sound quality enhancement system | |
| KR20140052486A (en) | Sound quality enhancement and adaptive comport noise addition system in voice communication | |
| KR20140052487A (en) | Method and apparatus of adaptive noise estimation in multiple mic based sound quality enhancement | |
| KR20140052488A (en) | Method and apparatus of psychoacoustic spectral substraction in multiple mic based sound quality enhancement system | |
| KR20140052491A (en) | Method and apparatus of probabilistic voice activity detection for voice detection in multiple mic based sound quality enhancement system | |
| Rao et al. | Speech enhancement using perceptual Wiener filter combined with unvoiced speech—A new Scheme | |
| CN110933235A (en) | Noise removing method in intelligent calling system based on machine learning | |
| Sun et al. | A variable momentum factor algorithm for a priori SNR estimation in speech enhancement | |
| Aung et al. | Two‐microphone subband noise reduction scheme with a new noise subtraction parameter for speech quality enhancement | |
| Liu et al. | An improved spectral subtraction method | |
| US11200908B2 (en) | Method and device for improving voice quality | |
| Karabashetti et al. | Speech enhancement using multiband spectral subtraction with cross spectral component reduction | |
| Lemercier et al. | Endto-end optimization of online neural network-supported two-stage dereverberation for hearing devices |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| WITN | Withdrawal due to no request for examination |