Title :
Detection and removal of impulsive colored noise for speech enhancement
Author :
He, Zhiyong ; Guo, Xuhong ; Zhang, Maoqing
Author_Institution :
Sch. of Mech. & Electr. Eng., Soochow Univ., Suzhou, China
Abstract :
Speech enhancement aims at denoising noisy speech signal and to extract the clean speech. In this work, impulsive colored noise is regarded. The detail coefficient from discrete wavelet transform is used to analyze the distribution of impulsive colored noise in time domain. The energy of impulsive colored noise in different frequency bands can be used to find thresholds for wavelet thresholding techniques. The efficiency of the algorithm is evaluated.
Keywords :
signal denoising; speech enhancement; wavelet transforms; impulsive colored noise detection; impulsive colored noise removal; noisy speech signal denoising; speech enhancement; wavelet thresholding; Additive white noise; Colored noise; Discrete wavelet transforms; Gaussian noise; Noise reduction; Speech analysis; Speech enhancement; Time domain analysis; Wavelet domain; Working environment noise;
Conference_Titel :
Information and Automation (ICIA), 2010 IEEE International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-5701-4
DOI :
10.1109/ICINFA.2010.5512179
