Connectionist Approaches to the Use of Markov Models for Speech Recognition
Abstract
Previous work has shown the ability of Multilayer Perceptrons (MLPs) to estimate emission probabilities for Hidden Markov Mod(cid:173) els (HMMs). The advantages of a speech recognition system incor(cid:173) porating both MLPs and HMMs are the best discrimination and the ability to incorporate multiple sources of evidence (features, temporal context) without restrictive assumptions of distributions or statistical independence. This paper presents results on the speaker-dependent portion of DARPA's English language Resource Management database. Results support the previously reported utility of MLP probability estimation for continuous speech recog(cid:173) nition. An additional approach we are pursuing is to use MLPs as nonlinear predictors for autoregressive HMMs. While this is shown to be more compatible with the HMM formalism, it still suffers from several limitations. This approach is generalized to take ac(cid:173) count of time correlation between successive observations, without any restrictive assumptions about the driving noise.
Cite
Text
Bourlard et al. "Connectionist Approaches to the Use of Markov Models for Speech Recognition." Neural Information Processing Systems, 1990.Markdown
[Bourlard et al. "Connectionist Approaches to the Use of Markov Models for Speech Recognition." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/bourlard1990neurips-connectionist/)BibTeX
@inproceedings{bourlard1990neurips-connectionist,
title = {{Connectionist Approaches to the Use of Markov Models for Speech Recognition}},
author = {Bourlard, Hervé and Morgan, Nelson and Wooters, Chuck},
booktitle = {Neural Information Processing Systems},
year = {1990},
pages = {213-219},
url = {https://mlanthology.org/neurips/1990/bourlard1990neurips-connectionist/}
}