Genones: Generalized Mixture Tying in Continuous Hidden Markov Model-Based Speech Recognizers (1996)
| Venue: | IEEE Transactions on Speech and Audio Processing |
| Citations: | 36 - 7 self |
BibTeX
@ARTICLE{Digalakis96genones:generalized,
author = {V. Digalakis and P. Monaco and H. Murveit and Vassilios Digalakis},
title = {Genones: Generalized Mixture Tying in Continuous Hidden Markov Model-Based Speech Recognizers},
journal = {IEEE Transactions on Speech and Audio Processing},
year = {1996},
volume = {4},
pages = {281--289}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
An algorithm is proposed that achieves a good trade-off between modeling resolution and robustness by using a new, general scheme for tying of mixture components in continuous mixture-density hidden Markov model (HMM)-based speech recognizers. The sets of HMM states that share the same mixture components are determined automatically using agglomerative clustering techniques. Experimental results on ARPA's Wall-Street Journal corpus show that this scheme reduces errors by 25% over typical tied-mixture systems. New fast algorithms for computing Gaussian likelihoods--the most time-consuming aspect of continuous-density HMM systems--are also presented. These new algorithms significantly reduce the number of Gaussian densities that are evaluated with little or no impact on speech recognition accuracy. Corresponding Author: Vassilios Digalakis Address: Electronic and Computer Engineering Department Technical University of Crete, Kounoupidiana Chania, 73100 GREECE Phone: +30-821...
