Speech enhancement with reduction of noise components in the wavelet domain

Author

Seok, Jong Won ; Bae, Keun Sung

Author_Institution

Sch. of Electron. & Electr. Eng., Kyungpook Nat. Univ., Taegu, South Korea

Volume

2

fYear

1997

fDate

21-24 Apr 1997

Firstpage

1323

Abstract

This paper describes a general problem of removing additive background noise from the noisy speech in the wavelet domain. A semisoft thresholding is used to remove noise components from the wavelet coefficients of noisy speech. To prevent the quality degradation of the unvoiced sounds during the denoising process, the unvoiced region is classified first and then thresholding is applied in a different way. Experimental results demonstrate that the speech enhancement algorithm using the wavelet transform is very promising

Keywords

speech enhancement; wavelet transforms; white noise; additive background noise removal; denoising process; experimental results; noise components reduction; noisy speech; semisoft thresholding; spectral distance; speech enhancement algorithm; speech quality degradation; unvoiced region classification; unvoiced sounds; wavelet coefficients; wavelet domain; white noise; Acoustic noise; Continuous wavelet transforms; Discrete wavelet transforms; Frequency; Noise reduction; Signal processing; Speech enhancement; Speech processing; Wavelet analysis; Wavelet domain;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.596190

Filename

596190