Discriminative training of Gaussian mixture models for large vocabulary speech recognition systems

Author

Bahl, L.R. ; Padmanabhan, M. ; Nahamoo, D. ; Gopalakrishnan, P.S.

Author_Institution

IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA

Volume

2

fYear

1996

fDate

7-10 May 1996

Firstpage

613

Abstract

Two discriminative techniques are described (and evaluated) for estimating the parameters of the Gaussians in a large vocabulary speech-recognition system. The first technique is based on using a modification of the maximum mutual information (MMI) objective function, and appears to provide no improvement over standard ML estimation. The second technique is based on a heuristic correction of the Gaussian parameters, and is seen to give a 2-5% improvement over ML estimation

Keywords

Gaussian processes; information theory; maximum likelihood estimation; speech recognition; Gaussian mixture models; Gaussian parameters; ML estimation; MMI objective function; discriminative training; heuristic correction; large vocabulary speech recognition systems; maximum likelihood estimation; maximum mutual information; parameter estimation; Context modeling; Hidden Markov models; Maximum likelihood estimation; Parameter estimation; Production systems; Speech recognition; Training data; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on

Conference_Location

Atlanta, GA

ISSN

1520-6149

Print_ISBN

0-7803-3192-3

Type

conf

DOI

10.1109/ICASSP.1996.543195

Filename

543195