Speech enhancement for nonstationary noise environment

Author

Lin, L. ; Ambikairajah, E. ; Holmes, W.H.

Author_Institution

Sch. of Electr. Eng. & Telecommun., New South Wales Univ., Sydney, NSW, Australia

Volume

1

fYear

2002

fDate

2002

Firstpage

177

Abstract

A speech denoising technique based on an auditory filterbank is proposed in this paper. The noisy speech is first decomposed by the auditory filterbank into critical band signals. The denoising gain is calculated from the variance estimate for the subband signal and noise. The time varying subband noise variance is estimated by tracking the minimum variance of the subband noisy signal. This noise reduction technique is suitable for colored and nonstationary noise environment. It results in naturally sounding speech with a very low level of musical noise.

Keywords

estimation theory; filtering theory; random noise; signal denoising; speech enhancement; auditory filterbank; colored noise environment; critical band signals; denoising gain calculation; noise reduction technique; noisy speech decomposition; nonstationary noise environment; speech denoising technique; speech enhancement; subband noise variance estimation; time varying subband noise variance; Acoustic noise; Colored noise; Filter bank; Finite impulse response filter; IIR filters; Noise reduction; Signal to noise ratio; Speech enhancement; Speech synthesis; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2002. APCCAS '02. 2002 Asia-Pacific Conference on

Print_ISBN

0-7803-7690-0

Type

conf

DOI

10.1109/APCCAS.2002.1114931

Filename

1114931