A modified Ephraim-Malah noise suppression rule for automatic speech recognition

Author

Gemello, Roberto ; Mana, Franco ; de Mori, Renato

Author_Institution

LOQUENDO, Torino, Italy

Volume

1

fYear

2004

fDate

17-21 May 2004

Abstract

A soft decision gain modification is introduced and applied to the Ephraim-Malah gain function based on maximum mean square error estimation (MMSE) (Ephraim, Y. and Malah, D., IEEE Trans. Acoust. Speech Sig. Process., vol.ASSP-32, no.6, p.1109-21, 1984; vol.ASSP-33, no.2, p.443-5, 1985) after amplitude compression. Non-linear evaluations of the noise overestimation factor and spectral floor are used in the same way for the proposed gain modification and for non-linear spectral subtraction (NSS). Consistent and statistically significant ASR improvements of the proposed approach with respect to NSS are observed for different noise conditions considered in the AURORA2 and AURORA3 corpora. As the non-linearity affects the two approaches in the same way, the comparison result is particularly interesting.

Keywords

acoustic noise; interference suppression; mean square error methods; parameter estimation; random noise; spectral analysis; speech recognition; AURORA2 corpus; AURORA3 corpus; amplitude compression; automatic speech recognition; maximum mean square error estimation; modified Ephraim-Malah noise suppression rule; noise overestimation factor; nonlinear spectral subtraction; soft decision gain modification; spectral floor; Acoustic distortion; Acoustic noise; Additive noise; Amplitude estimation; Automatic speech recognition; Estimation error; Mean square error methods; Nonlinear distortion; Speech enhancement; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-8484-9

Type

conf

DOI

10.1109/ICASSP.2004.1326146

Filename

1326146