Comparison of Different Types of Visemes using a Constraint-based Coarticulation Model

Lazalde, Oscar M. Martinez; Maddock, Steve

Comparison of Different Types of Visemes using a Constraint-based Coarticulation Model

Files

199-206.pdf (514.54 KB)

Date

2010

Authors

Lazalde, Oscar M. Martinez
Maddock, Steve

Publisher

The Eurographics Association

Abstract

A common approach to producing visual speech is to interpolate the parameters describing a sequence of mouth shapes, known as visemes, where visemes are the visual counterpart of phonemes. A single viseme typically represents a group of phonemes that are visually similar. Often these visemes are based on the static poses used in producing a phoneme. In this paper we investigate alternative representations for visemes, produced using motion-captured data, in conjunction with a constraint-based approach for visual speech production. We show that using visemes which incorporate more contextual information produces better results that using static pose visemes.

        @inproceedings{:10.2312/LocalChapterEvents/TPCG/TPCG10/199-206
,
booktitle = {Theory and Practice of Computer Graphics
},
editor = {John Collomosse and Ian Grimstead
},
title = {{Comparison of Different Types of Visemes using a Constraint-based Coarticulation Model
}},
author = {Lazalde, Oscar M. Martinez and 
Maddock, Steve
},
year = {2010
},
publisher = {The Eurographics Association
},
ISBN = {978-3-905673-75-3
},
DOI = {/10.2312/LocalChapterEvents/TPCG/TPCG10/199-206
}
}