Global Optimization of a Neural Network - Hidden Markov Model Hybrid (1991)
| Venue: | IEEE Transactions on Neural Networks |
| Citations: | 63 - 16 self |
BibTeX
@ARTICLE{Bengio91globaloptimization,
author = {Yoshua Bengio and Renato De Mori and Giovanni Flammia and Ralf Kompe},
title = {Global Optimization of a Neural Network - Hidden Markov Model Hybrid},
journal = {IEEE Transactions on Neural Networks},
year = {1991},
volume = {3},
pages = {252--259}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
In this paper an original method for integrating Artificial Neural Networks (ANN) with Hidden Markov Models (HMM) is proposed. ANNs are suitable to perform phonetic classification, whereas HMMs have been proven successful at modeling the temporal structure of the speech signal. In the approach described here, the ANN outputs constitute the sequence of observation vectors for the HMM. An algorithm is proposed for global optimization of all the parameters. Results on speaker-independent recognition experiments using this integrated ANN-HMM system on the TIMIT continuous speech database are reported. 1 Introduction In spite of the fact that speech exhibits features that cannot be represented by a first-order Markov model, Hidden Markov Models (HMMs) of speech units (e.g., phonemes) have been used with a good degree of success in Automatic Speech Recognition (ASR) (Rabiner & Levinson 85; Lee & Hon 89). Artificial Neural Networks (ANNs) have proven to be useful for classifying speech prop...
