A Speech Enhancement Method in Low SNR Environment

2013 ◽  
Vol 645 ◽  
pp. 179-183
Author(s):  
Yao Qi Wang ◽  
Xiao Peng Wang ◽  
Raji Rafiu King
Keyword(s):  
Wavelet Transform ◽  
Speech Enhancement ◽  
Experimental Results ◽  
Threshold Function ◽  
Morphological Filter ◽  
Wavelet Domain ◽  
Low Snr ◽  
Morphological Filtering ◽  
Enhancement Method ◽  
Enhancement Algorithm

A new method of speech enhancement is proposed based on morphological filter and wavelet transform. The system begins by first conducting morphological filtering, then distinguishing the unvoiced, voiced and noise using TEO in the wavelet domain. It then executes wavelet transform using different threshold on multiscale, and at the same time to improve the threshold function. Experimental results showed that the method not only suppressed noise effectively but also reduced the loss of the unvoiced. It also not only enhanced SNR, but also improved voice clarity and comfort. The merits it espouses makes it an effective speech enhancement algorithm.

scholarly journals An Adaptive Weighted Threshold Image Restoration Method Based on Wavelet Domain

2021 ◽  
Vol 15 ◽  
pp. 297-305
Author(s):  
Lili Chen ◽  
Hongjun Guo
Keyword(s):  
Wavelet Transform ◽  
Image Quality ◽  
Image Restoration ◽  
Visual Analysis ◽  
Weight Coefficient ◽  
Threshold Function ◽  
Wavelet Domain ◽  
Restoration Method ◽  
High Level ◽  
The Relationship

Due to the limitation of imaging equipment, the influence of transmission medium and external environment, image quality degradation will inevitably occur in the process of generation, transmission and reception. These degradation not only worsens the visual effect of the image, but also makes the image lose a lot of useful information, which seriously affects image recognition, target detection and other high-level visual analysis. Wavelet analysis can extract useful information from image signal and meanwhile its profound wavelet basis can get adapted to signals of different properties. To better apply wavelet transform into image restoration domain, this paper according to the characteristics of wavelet transform, analyzes the method to select threshold function and the relationship within and between layers of wavelet coefficients, gets a proper threshold weight coefficient and propose an adaptive weighted threshold image restoration method based on wavelet domain, which makes smaller deviation and variance between the de-noised image and the original signal. The experiment result shows that the algorithm of this paper can obtain good subjective and objective image quality and effectively retain most detailed information of the image.

Algorithm for Improving Image Denoising Based on Adaptive Wavelet Transform

2014 ◽  
Vol 912-914 ◽  
pp. 1134-1137
Author(s):  
Xiang Shi Wang
Keyword(s):  
Image Processing ◽  
Wavelet Transform ◽  
Specific Property ◽  
Threshold Function ◽  
Natural Image ◽  
Wavelet Domain ◽  
Adaptive Wavelet ◽  
Threshold Functions ◽  
Adaptive Wavelet Transform ◽  
Adaptive Neighborhood

The denoising of a natural image is the important area in image processing. As a tool of image processing, wavelet transform is widly applied in removing of gauss noise for the partial specific property in time and frequency domain.The main goal of this paper is to eliminate the noise by an adaptive neighborhood window of the wavelet domain and focused on selecting a medium-soft threshold function based on wavelet. Simulation results have shown that the modified function improves the denoising effect comparing with the other threshold functions.

Speech Enhancement Method under Low SNR

2012 ◽  
Vol 457-458 ◽  
pp. 1490-1493
Author(s):  
Wen Long Cai ◽  
Guang Ma
Keyword(s):  
Speech Enhancement ◽  
Duffing Oscillator ◽  
Sinusoidal Signal ◽  
Test Results ◽  
Pitch Period ◽  
Enhancing Effect ◽  
Low Snr ◽  
Harmonic Method ◽  
Speech Distortion ◽  
Enhancement Method

In this document, the pitch period is detected according to the sensitivity to weak sinusoidal signal and strong immunity ability to noise of Duffing oscillator, at the background of strong noise. And then enhancing pitch obtained by harmonic method. The test results show that the enhancing effect of this method is obvious under low SNR condition, and speech distortion is small.

Speech Enhancement Method under Low SNR

2012 ◽  
Vol 457-458 ◽  
pp. 1490-1493
Author(s):  
Wen Long Cai ◽  
Guang Ma
Keyword(s):  
Speech Enhancement ◽  
Low Snr ◽  
Enhancement Method

Speech Enhancement Based on Bionic Wavelet Transform and Correlation Denoising

2014 ◽  
Vol 912-914 ◽  
pp. 1386-1390
Author(s):  
Li Ming Wu ◽  
Yao Fei Li ◽  
Fu Jian Li ◽  
Xin Luo
Keyword(s):  
Correlation Function ◽  
Wavelet Transform ◽  
Speech Enhancement ◽  
Enhancement Effect ◽  
Wavelet Coefficients ◽  
Enhancement Method ◽  
Simulation Results

A new speech enhancement method based on bionic wavelet transform is presented here. Voice signals with noise would be bionic wavelet coefficients by bionic wavelet transform, then, the purpose of speech enhancement can be achieved by means of the bionic wavelet coefficients based on the improved correlation function processing. The simulation results show that the method under the condition of various noises is good speech enhancement effect. Keywords: Speech enhancement; BWT; Correlation de-noising

scholarly journals Speech Enhancement Based on the Multi-Scales and Multi-Thresholds of the Auditory Perception Wavelet Transform

2011 ◽  
Vol 36 (3) ◽  
pp. 519-532 ◽  
Author(s):  
Zhi Tao ◽  
He-Ming Zhao ◽  
Xiao-Jun Zhang ◽  
Di Wu
Keyword(s):  
Wavelet Transform ◽  
Speech Enhancement ◽  
Auditory Perception ◽  
Noise Suppression ◽  
Signal To Noise Ratio ◽  
Masking Effect ◽  
Auditory Masking ◽  
Low Snr ◽  
Residual Noise ◽  
Multi Scales

Abstract This paper proposes a speech enhancement method using the multi-scales and multi-thresholds of the auditory perception wavelet transform, which is suitable for a low SNR (signal to noise ratio) environment. This method achieves the goal of noise reduction according to the threshold processing of the human ear's auditory masking effect on the auditory perception wavelet transform parameters of a speech signal. At the same time, in order to prevent high frequency loss during the process of noise suppression, we first make a voicing decision based on the speech signals. Afterwards, we process the unvoiced sound segment and the voiced sound segment according to the different thresholds and different judgments. Lastly, we perform objective and subjective tests on the enhanced speech. The results show that, compared to other spectral subtractions, our method keeps the components of unvoiced sound intact, while it suppresses the residual noise and the background noise. Thus, the enhanced speech has better clarity and intelligibility.

Sign in / Sign up

Export Citation Format

Share Document