MMI training for continuous phoneme recognition on the TIMIT database

Authors:
S. Kapadia;V. Valtchev;S. J. Young
Affiliations:
Cambridge University Engineering Department, England;Cambridge University Engineering Department, England;Cambridge University Engineering Department, England
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II
Year:
1993

Citing 2
Cited 1

Hidden Markov models, maximum mutual information estimation, and the speech recognition problem

Hidden Markov models, maximum mutual information estimation, and the speech recognition problem
The general use of tying in phoneme-based HMM speech recognisers

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1

A variable initialization approach to the EM algorithm for better estimation of the parameters of hidden markov model based acoustic modeling of speech signals

ICDM'06 Proceedings of the 6th Industrial Conference on Data Mining conference on Advances in Data Mining: applications in Medicine, Web Mining, Marketing, Image and Signal Mining

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper reports our experiences with a phoneme recognition system for the TIMIT database which uses multiple mixture continuous density monophone HMMs trained using MMI. A comprehensive set of results are presented comparing the ML and MMI training criteria for both diagonal and full covariance models. These results using simple monophone HMMs show clear performance gains achieved by MMI training, and are comparable to the best reported by others including those which use context-dependent models. In addition, the paper discusses a number of performance and implementation issues which are crucial to successful MMI training.