Maximum A Posteriori Adaptation for Many-to-One Eigenvoice Conversion


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/8159

Title:	Maximum A Posteriori Adaptation for Many-to-One Eigenvoice Conversion
Authors:	Daisuke Tani Tomoki Toda Yamato Ohtani Hiroshi Saruwatari Kiyohiro Shikano
Keywords:	speech synthesis voice conversion GMM eigenvoice MAP
Issue Date:	Sep-2008
Start page:	1461
End page:	1464
Abstract:	Many-to-one eigenvoice conversion (EVC) allows the conversion from an arbitrary speaker's voice into the pre-determined target speaker's voice. In this method, a canonical eigenvoice Gaussian mixture model is effectively adapted to any source speaker using only a few utterances as the adaptation data. In this paper, we propose a many-to-one EVC based on maximum a posteriori (MAP) adaptation for further improving the robustness of the adaptation process to the amount of adaptation data. Results of objective and subjective evaluations demonstrate that the proposed method is the most effective among the other conventional many-to-one VC methods when using any amount of adaptation data (e.g., from 300 ms to 16 utterances).
Description:	INTERSPEECH2008: 9th Annual Conference of the International Speech Communication Association, September 22-26, 2008, Brisbane, Australia.
URI:	http://hdl.handle.net/10061/8159
Rights:	Copyright 2008 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
INTERSPEECH_2008_1461.pdf	757.82 kB	Adobe PDF	View/Open