Continuous speech recognition in noise using spectral subtraction and HMM adaptation

Author

Flores, J. A Nolazco ; Young, S.J.

Author_Institution

Dept. of Eng., Cambridge Univ., UK

fYear

1994

fDate

19-22 Apr 1994

Abstract

This paper describes a scheme fur robust speech recognition at very poor signal to noise ratios. It consists of a continuous spectral subtraction (CSS) scheme integrated into a parallel model combination (PMC) compensation framework. In this CSS-PMC scheme, a smoothed estimate of the long term spectrum is continuously calculated and subtracted from the signal. At the same time, the HMMs are compensated using PMC for the signal distortion caused by the CSS stage. The paper presents an evaluation of the CSS-PMC approach using the Noisex 92 database. The results show high recognition performance for very noisy environments. For example, for the Lynx helicopter noise, CSS-PMC gives 97% accuracy at 0 dB SNR

Keywords

acoustic noise; helicopters; hidden Markov models; spectral analysis; speech recognition; HMM adaptation; Lynx helicopter noise; Noisex 92 database; SNR; compensation method; continuous speech recognition; long term spectrum; noisy environments; parallel model combination; recognition performance; signal distortion; smoothed estimate; spectral subtraction; Cascading style sheets; Detectors; Hidden Markov models; Noise level; Nonlinear distortion; Signal to noise ratio; Speech analysis; Speech enhancement; Speech recognition; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1994. ICASSP-94., 1994 IEEE International Conference on

Conference_Location

Adelaide, SA

ISSN

1520-6149

Print_ISBN

0-7803-1775-0

Type

conf

DOI

10.1109/ICASSP.1994.389269

Filename

389269