5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

High-Speed Speaker Adaptation Using Phoneme Dependent Tree-Structured Speaker Clustering

Motoyuki Suzuki (1), Toshiaki Abe (2), Hiroki Mori (2), Shozo Makino (1), Hirotomo Aso (2)

(1) Computer Center / Graduate school of Information Sciences, Tohoku Univ., Japan
(2) Graduate school of Engineering, Tohoku Univ., Japan

The tree-structured speaker clustering was proposed as a high-speed speaker adaptation method. It can select the model which is most similar to a target speaker. However, this method does not consider speaker difference dependent on phoneme class. In this paper, we propose a speaker adaptation method based on speaker clustering by taking speaker difference dependent on phoneme class into account. The experimental results showed that the new method gave a better performance than the original method. Furthermore, we propose the improved method which use a tree-structure of a similar phoneme as the substitute for the phoneme which does not appear in the adaptation data. From the experimental results, the improved method gave a better performance than the method previously proposed.

Full Paper

Bibliographic reference.  Suzuki, Motoyuki / Abe, Toshiaki / Mori, Hiroki / Makino, Shozo / Aso, Hirotomo (1998): "High-speed speaker adaptation using phoneme dependent tree-structured speaker clustering", In ICSLP-1998, paper 0992.