Unsupervised Learning for Speech Motion Editing

Thumbnail Image
Date
2003
Authors
Cao, Yong
Faloutsos, Petros
Pighin, Frédéric
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
We present a new method for editing speech related facial motions. Our method uses an unsupervised learning technique, Independent Component Analysis (ICA), to extract a set of meaningful parameters without any annotation of the data. With ICA, we are able to solve a blind source separation problem and describe the original data as a linear combination of two sources. One source captures content (speech) and the other captures style (emotion). By manipulating the independent components we can edit the motions in intuitive ways.
Description

        
@inproceedings{
:10.2312/SCA03/225-231
,
booktitle = {
Symposium on Computer Animation
},
editor = {
D. Breen and M. Lin
},
title = {{
Unsupervised Learning for Speech Motion Editing
}},
author = {
Cao, Yong
 and 
Faloutsos, Petros
 and 
Pighin, Frédéric
},
year = {
2003
},
publisher = {
The Eurographics Association
},
ISSN = {
1727-5288
},
ISBN = {
1-58113-659-5
},
DOI = {
/10.2312/SCA03/225-231
}
}
Citation
URI
https://doi.org/10.2312/SCA03/225-231
Collections
SCA 03: Eurographics/SIGGRAPH Symposium on Computer Animation