Probabilistic optimum filtering for robust speech recognition

Author

Neumeyer, Leonardo ; Weintraub, Mitchel

Author_Institution

Speech Res. & Technol. Program, SRI Int., Menlo Park, CA, USA

fYear

1994

fDate

19-22 Apr 1994

Abstract

We present a new mapping algorithm for speech recognition that relates the features of simultaneous recordings of clean and noisy speech. The model is a piecewise linear transformation applied to the noisy speech feature. The transformation is a set of multidimensional linear least-squares filters whose outputs are combined using a conditional Gaussian model. The algorithm was tested using SRI´s DECIPHER speech recognition system. Experimental results show how the mapping is used to reduce recognition errors when the training and testing acoustic environments do not match

Keywords

Gaussian processes; filtering theory; least squares approximations; multidimensional digital filters; piecewise-linear techniques; probability; speech recognition; DECIPHER speech recognition system; SRI; clean speech; conditional Gaussian model; experimental results; mapping algorithm; microphones; multidimensional linear least-squares filters; multidimensional transversal filters; noisy speech; piecewise linear transformation; probabilistic optimum filtering; recognition errors reduction; robust speech recognition; simultaneous recordings; testing acoustic environment; training; training acoustic environments; Acoustic noise; Acoustic testing; Filtering; Multidimensional systems; Nonlinear filters; Piecewise linear techniques; Robustness; Simultaneous localization and mapping; 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.1994.389267

Filename

389267