Speech to Lip Synthesis by HMM


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/7919

Title:	Speech to Lip Synthesis by HMM
Authors:	Eli Yamamoto Satoshi Nakamura Kiyohiro Shikano
Issue Date:	Sep-1997
Start page:	137
End page:	140
Abstract:	Synthesized lip movement images can compensate lack of auditory information for hearing impaired people, and also contribute to realize a human-like face of computer agents. We propose a novel method to synthesize lip movement based on mapping from an input speech using HMM. This paper compares the HMM method and a conventional method using VQ or ANN to convert speech-to-lip movement images. In the experiment, error and time difference error between synthesized lip movement images and original ones are utilized for evaluation. The result shows that the error of the HMM method is 8.6% smaller than that of the VQ method. Moreover, the HMM method reduces time difference error by 34.8% than the VQ's. The result also shows that the errors are mostly caused by phoneme /h/ and /Q/. Since those phonemes are dependent on succeeding phoneme, the context-dependent synthesis on the HMM method is applied to reduce the error. The context-dependent HMM method realizes that the error(difference error) is reduced by 11.3%(8.9%) compared with the original HMM method.
Description:	AVSP 1997: Audio Visual Signal Processing Workshop, September 6-7, 1997, Rhodes, Greece.
URI:	http://hdl.handle.net/10061/7919
ISSN:	1018-4554
Rights:	Copyright 1997 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
AVSP_1997_137.pdf	565.63 kB	Adobe PDF	View/Open