Evaluation on Unsupervised Speaker Adaptation Based on Sufficient HMM Statictics of Selected Speakers


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/7952

Title:	Evaluation on Unsupervised Speaker Adaptation Based on Sufficient HMM Statictics of Selected Speakers
Authors:	Shinichi Yoshizawa Akira Baba Kanako Matsunami Yuichiro Mera Miichi Yamada Akinobu Lee Kiyohiro Shikano
Issue Date:	Sep-2001
Start page:	1219
End page:	1222
Abstract:	This paper describes an efficient method of unsupervised speaker adaptation. This method is based on (1) selecting a subset of speakers who are acoustically close to a test speaker, and (2) calculating adapted model parameters according to the previously stored sufficient statistics of the selected speakers' data. In this method, only a few unsupervised test speaker's data are necessary for the adaptation. Also, by using the sufficient HMM statistics of the selected speakers' data, a quick adaptation can be done. Compared with a pre-clustering method, the proposed method can obtain a more optimal cluster because the clustering result is determined according to test speaker's data on-line. Experimental results show that the proposed method attains better improvement than MLLR from the speaker-independent model. The proposed method is evaluated in details and discussed.
Description:	EUROSPEECH2001: the 7th European Conference on Speech Communication and Technology, September 3-7, 2001, Aalborg, Denmark.
URI:	http://hdl.handle.net/10061/7952
ISSN:	1018-4074
Rights:	Copyright 2001 ISCA
Text Version:	Publisher
Appears in Collections:	情報科学研究科 / Graduate School of Information Science

Files in This Item:

File	Size	Format
EUROSPEECH_2001_1219.pdf	737.62 kB	Adobe PDF	View/Open