Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition

C. Dugast, P. Beyerlein, R. Haeb-Umbach, in: ICASSP, Detroit, 1995.

Conference Paper | English
Author
Dugast, Christian; Beyerlein, Peter; Haeb-Umbach, ReinholdLibreCat
Abstract
Clustering techniques have been integrated at different levels into the training procedure of a continuous-density hidden Markov model (HMM) speech recognizer. These clustering techniques can be used in two ways. First acoustically similar states are tied together. It will help to reduce the number of parameters but also allow to train otherwise rarely seen states together with more robust ones (state-tying). Secondly densities are clustered across states, this reduces the number of densities while at the same time keeping the best performances of our recognizer (density-clustering). We have applied these techniques both to word-based small-vocabulary and phoneme-based large-vocabulary recognition tasks. On the WSJ task, we could achieve a reduction of the word error rate by 7%. On the TI/NIST-connected digit task, the number of parameters was reduced by a factor 2-3 while keeping the same string error rate.
Publishing Year
Proceedings Title
ICASSP, Detroit
LibreCat-ID

Cite this

Dugast C, Beyerlein P, Haeb-Umbach R. Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition. In: ICASSP, Detroit. ; 1995.
Dugast, C., Beyerlein, P., & Haeb-Umbach, R. (1995). Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition. In ICASSP, Detroit.
@inproceedings{Dugast_Beyerlein_Haeb-Umbach_1995, title={Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition}, booktitle={ICASSP, Detroit}, author={Dugast, Christian and Beyerlein, Peter and Haeb-Umbach, Reinhold}, year={1995} }
Dugast, Christian, Peter Beyerlein, and Reinhold Haeb-Umbach. “Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition.” In ICASSP, Detroit, 1995.
C. Dugast, P. Beyerlein, and R. Haeb-Umbach, “Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition,” in ICASSP, Detroit, 1995.
Dugast, Christian, et al. “Application of Clustering Techniques to Mixture Density Modelling for Continuous-Speech Recognition.” ICASSP, Detroit, 1995.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar