This paper presents a new approach to improve the conventional eigenvoice technique. In the conventional eigenvoice, an eigenspace is established by introducing a priori knowledge of training speakers via PCA. The adaptation data is then used to determine a group of coefficients with respect to the eigenspace and build the SD model for the testing speaker. In the proposed approach, the eigenspace in the conventional eigenvoice is segmented into N sub-eigenspaces. Each sub-eigenspace is established by those components in the training speaker SD models with similar properties to each other. With the adaptation data, N groups of coefficients corresponding to the N sub-eigenspaces can be determined to build SD model for the new testing speaker. Here, both mixture-based and feature-based segmentation of eigenspace were tested, and improved results compared to the conventional eigenvoice were obtained in both cases. Even better results were obtained when these approaches were properly combined.
Cite as: Tsao, Y., Lee, S.-M., Chou, F.-C., Lee, L.-S. (2001) Segmental eigenvoice for rapid speaker adaptation. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 1269-1272, doi: 10.21437/Eurospeech.2001-329
@inproceedings{tsao01_eurospeech,
author={Yu Tsao and Shang-Ming Lee and Fu-Chiang Chou and Lin-Shan Lee},
title={{Segmental eigenvoice for rapid speaker adaptation}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={1269--1272},
doi={10.21437/Eurospeech.2001-329}
}