Improved Hidden Markov Modeling for Speaker-Independent Continuous Speech Recognition (1990)
| Venue: | Proc. DARPA Speech and Natural language Workshop |
| Citations: | 10 - 1 self |
BibTeX
@INPROCEEDINGS{Huang90improvedhidden,
author = {Xuedong Huang and Fil Alleva and Satoru Hayamizu and Hsiao-wuen Hon and Mei-yuh Hwang and Kai-fu Lee},
title = {Improved Hidden Markov Modeling for Speaker-Independent Continuous Speech Recognition},
booktitle = {Proc. DARPA Speech and Natural language Workshop},
year = {1990},
pages = {327--331},
publisher = {Morgan Kaufmann Publishers}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
This paper reports recent efforts to further improve the perfor-mance of the Sphinx system for speaker-independent contin-uous speech recognition. The recognition error rate is signifi-cantly reduced with incorporation of additional dynamic fea-tures, semi-continuous hidden Markov models, and speaker clustering. For the June 1990 (RM2) evaluation test set, the error rates of our current system are 4.3 % and 19.9 % for word-pair grammar and no grammar respectively.
