Audiovisual Speech Synthesis

This paper presents the main approaches used to synthesize talking faces & provides greater detail on a handful of these approaches. An attempt is made to distinguish between facial synthesis itself (ie, the manner in which facial movements are rendered on a computer screen), & the way these...

Full description

Saved in:
Bibliographic Details
Published in:International journal of speech technology 2003-10, Vol.6 (4), p.331-346
Main Authors: Bailly, G, Berar, M, Elisei, F, Odisio, M
Format: Article
Language:English
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents the main approaches used to synthesize talking faces & provides greater detail on a handful of these approaches. An attempt is made to distinguish between facial synthesis itself (ie, the manner in which facial movements are rendered on a computer screen), & the way these movements may be controlled & predicted using phonetic input. The two main synthesis techniques (model-based vs image-based) are contrasted & presented by a brief description of the most illustrative existing systems. The challenging issues - evaluation, data acquisition, & modeling - that may drive future models are also discussed & illustrated by our current work at ICP. 16 Figures, 64 References. Adapted from the source document
ISSN:1381-2416
DOI:10.1023/A:1025700715107