DMCA
A maximum likelihood approach to continuous speech recognition (1983)
| Venue: | IEEE Trans. Pattern Anal. Machine Intell |
| Citations: | 476 - 9 self |
BibTeX
@ARTICLE{Bahl83amaximum,
author = {Lalit R. Bahl and Frederick Jelinek and Robert and L. Mercer},
title = {A maximum likelihood approach to continuous speech recognition},
journal = {IEEE Trans. Pattern Anal. Machine Intell},
year = {1983},
pages = {179--190}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract-Speech recognition is formulated as a problem of maximum likelihood decoding. This formulation requires statistical models of the speech production process. In this paper, we describe a number of sta-tistical models for use in speech recognition. We give special attention to determining the parameters for such models from sparse data. We also describe two decoding methods, one appropriate for constrained artificial languages and one appropriate for more realistic decoding tasks. To illustrate the usefulness of the methods described, we review a number of decoding results that have been obtained with them. Index Terms-Markov models, maximum likelihood, parameter esti-mation, speech recognition, statistical models. I.
Keyphrases
maximum likelihood approach continuous speech recognition speech recognition statistical model maximum likelihood sparse data special attention abstract-speech recognition artificial language parameter esti-mation sta-tistical model maximum likelihood decoding speech production process index terms-markov model realistic decoding task
