Speech-to-Lip Movement Synthesis Based on the EM Algorithm Using Audio-Visual HMMs


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/8099

Title:	Speech-to-Lip Movement Synthesis Based on the EM Algorithm Using Audio-Visual HMMs
Authors:	Eli Yamamoto Satoshi Nakamura Kiyohiro Shikano
Issue Date:	Nov-1998
Start page:	1275
End page:	1278
Article Number:	0756
Abstract:	This paper proposes a method to re-estimate output visual parameters for speech-to-lip movement synthesis using audio-visual Hidden Markov Models (HMMs) under the Expectation-Maximization(EM) algorithm. In the conventional methods for speech-to-lip movement synthesis, there is a synthesis method estimating a visual parameter sequence through the Viterbi alignment of an input acoustic speech signal using audio HMMs. However, the HMM-Viterbi method involves a substantial problem that incorrect HMM state alignment may output incorrect visual parameters. The problem in the HMM-Viterbi method is caused by the deterministic synthesis process to assign a single HMM state for an input audio frame. The proposed method avoids the deterministic process by re-estimating non-deterministic visual parameters while maximizing the likelihood of the audio-visual observation sequence under the EM algorithm.
Description:	ICSLP1998: the 5th International Conference on Spoken Language Processing, November 30 - December 4, 1998, Sydney, Australia.
URI:	http://hdl.handle.net/10061/8099
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
ICSLP_1998_1275.pdf	802.96 kB	Adobe PDF	View/Open