Copyright © 2002 Elsevier Science B.V. All rights reserved.
Speaker clustering for speech recognition using vocal tract parameters
Received 4 April 2000;
References and further reading may be available for this article. To view references and further reading you must purchase this article.
Abstract
We propose speaker clustering methods for speech recognition based on vocal tract (VT) size related articulatory parameters associated with individual speakers. Two parameters characterizing gross VT dimensions are first derived from the formant frequencies of two vowels and are then used to cluster speakers. The resulting speaker clusters are significantly different from speaker clusters obtained by conventional acoustic criteria. Then phoneme recognition experiments are carried out by using speaker-clustered HMMs (SC-HMMs) trained for each cluster. The proposed method requires a small amount of speech data for speaker clustering and for selecting the most suitable SC-HMM for a target speaker, but gives higher recognition rates than conventional speaker clustering methods based on acoustic criteria.
Author Keywords: Vocal tract parameters; Speaker-clustering; Speech recognition
Article Outline
- 1. Introduction
- 2. Speaker clustering methods
- 3. Speaker cluster selection
- 3.1. Speaker cluster selection based on the VT parameters
- 3.2. Speaker cluster selection based on the maximum likelihood criterion
- 4. Experiments
- 4.1. Conditions
- 4.2. Speaker clustering
- 4.3. Distribution of VT parameters
- 4.4. Results of speaker clustering
- 4.5. Speech recognition experiments using speaker cluster selection based on VT parameters
- 4.6. Speech recognition experiments using speaker cluster selection based on likelihood
- 5. Conclusions
- Acknowledgements
- References







E-mail Article
Add to my Quick Links

Cited By in Scopus (7)





