Speech-to-Lip Movement Synthesis Maximizing Audio-Visual Joint Probability Based on EM Algorithm


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/8125

Title:	Speech-to-Lip Movement Synthesis Maximizing Audio-Visual Joint Probability Based on EM Algorithm
Authors:	Eli Yamamoto Satoshi Nakamura Kiyohiro Shikano
Issue Date:	Dec-1998
Publisher:	IEEE
Start page:	53
End page:	58
Abstract:	We investigate methods using the hidden Markov model (HMM) to drive a lip movement sequence with input speech. We have already investigated a mapping method based on the Viterbi decoding algorithm which converts an input speech to a lip movement sequence through the most likely HMM state sequence conducted by audio HMMs. However, the method contains a substantial problem of producing errors along incorrectly decoded HMM states. This paper newly proposes a method to re-estimate the visual parameters using the HMMs of the audio-visual joint probability under the expectation-maximization (EM) algorithm. In experiments, the proposed mapping method using the EM algorithm shows an error reduction of 26% compared to a method using the Viterbi algorithm at incorrectly decoded bi-labial consonants.
Description:	IEEE Second Workshop on Multimedia Signal Processing, December 7-9, 1998, Redondo Beach, California, USA.
URI:	http://hdl.handle.net/10061/8125
ISBN:	0780349199
Rights:	Copyright 1998 IEEE
Text Version:	Publisher
Publisher DOI:	10.1109/MMSP.1998.738912
Appears in Collections:	情報科学研究科 / Graduate School of Information Science

Files in This Item:

File	Size	Format
MMSP_1998_53.pdf	905.59 kB	Adobe PDF	View/Open