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.
Cite as: Suzuki, M., Abe, T., Mori, H., Makino, S., Aso, H. (1998) High-speed speaker adaptation using phoneme dependent tree-structured speaker clustering. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0992, doi: 10.21437/ICSLP.1998-745
@inproceedings{suzuki98d_icslp,
author={Motoyuki Suzuki and Toshiaki Abe and Hiroki Mori and Shozo Makino and Hirotomo Aso},
title={{High-speed speaker adaptation using phoneme dependent tree-structured speaker clustering}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0992},
doi={10.21437/ICSLP.1998-745}
}