Improved Hidden Markov Model Speech Recognition Using Radial Basis Function Networks
Abstract
A high performance speaker-independent isolated-word hybrid speech rec(cid:173) ognizer was developed which combines Hidden Markov Models (HMMs) and Radial Basis Function (RBF) neural networks. In recognition ex(cid:173) periments using a speaker-independent E-set database, the hybrid rec(cid:173) ognizer had an error rate of 11.5% compared to 15.7% for the robust unimodal Gaussian HMM recognizer upon which the hybrid system was based. These results and additional experiments demonstrate that RBF networks can be successfully incorporated in hybrid recognizers and sug(cid:173) gest that they may be capable of good performance with fewer parameters than required by Gaussian mixture classifiers. A global parameter opti(cid:173) mization method designed to minimize the overall word error rather than the frame recognition error failed to reduce the error rate.
Cite
Text
Singer and Lippmann. "Improved Hidden Markov Model Speech Recognition Using Radial Basis Function Networks." Neural Information Processing Systems, 1991.Markdown
[Singer and Lippmann. "Improved Hidden Markov Model Speech Recognition Using Radial Basis Function Networks." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/singer1991neurips-improved/)BibTeX
@inproceedings{singer1991neurips-improved,
title = {{Improved Hidden Markov Model Speech Recognition Using Radial Basis Function Networks}},
author = {Singer, Elliot and Lippmann, Richard P},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {159-166},
url = {https://mlanthology.org/neurips/1991/singer1991neurips-improved/}
}