Presentation 1997/5/22
LIP MOVEMENT SYNTHESIS USING HMMS
Takashi Masuko, Takao Kobayashi, Keiichi Tokuda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a new technique for synthesizing lip movements from an arbitrarily given text using the algorithm for parameter generation from HMMs with dynamic features. In the training stage of the technique, speech unit HMMs are trained with visual parameter vector sequences that represent lip movements. In the synthesis stage, a sentence HMM is constructed by concatenating speech unit HMMs corresponding to the transcription for the given text. Then an optimum parameter vector sequence is obtained from the sentence HMM based on the maximum likelihood criterion. The technique enables us to realize a synthesis system that can generate synchronized lip movements with speech in a unified framework. Generated parameter sequence reflects statistical information of both static and dynamic features, and synthetic lip animation becomes quite smooth and natural.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) lip movement systhesis / hidden Markov model / lip synchronization / multimodal interface
Paper # SP97-6
Date of Issue

Conference Information
Committee SP
Conference Date 1997/5/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) LIP MOVEMENT SYNTHESIS USING HMMS
Sub Title (in English)
Keyword(1) lip movement systhesis
Keyword(2) hidden Markov model
Keyword(3) lip synchronization
Keyword(4) multimodal interface
1st Author's Name Takashi Masuko
1st Author's Affiliation Precision and Intelligence Laboratory, Tokyo Institute of Technology()
2nd Author's Name Takao Kobayashi
2nd Author's Affiliation Precision and Intelligence Laboratory, Tokyo Institute of Technology
3rd Author's Name Keiichi Tokuda
3rd Author's Affiliation Department of Computer Science, Nagoya Institute of Technology
Date 1997/5/22
Paper # SP97-6
Volume (vol) vol.97
Number (no) 64
Page pp.pp.-
#Pages 6
Date of Issue