A constraint-based approach to visual speech for a Mexican-Spanish talking head

Authors:
Oscar Martinez Lazalde;Steve Maddock;Michael Meredith
Affiliations:
Department of Computer Science, Faculty of Engineering, University of Sheffield, Sheffield, UK;Department of Computer Science, Faculty of Engineering, University of Sheffield, Sheffield, UK;Department of Computer Science, Faculty of Engineering, University of Sheffield, Sheffield, UK
Venue:
International Journal of Computer Games Technology - Joint International Conference on Cyber Games and Interactive Entertainment 2006
Year:
2008

Citing 4
Cited 2

Computer facial animation

Computer facial animation
Spacetime constraints

SIGGRAPH '88 Proceedings of the 15th annual conference on Computer graphics and interactive techniques
Principal Components of Expressive Speech Animation

CGI '01 Computer Graphics International 2001
Constraint-based synthesis of visual speech

SIGGRAPH '04 ACM SIGGRAPH 2004 Sketches

A talking head for speech tutoring

Proceedings of the SSPNET 2nd International Symposium on Facial Analysis and Animation
Spanish Sign Language synthesis system

Journal of Visual Languages and Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A common approach to produce visual speech is to interpolate the parameters describing a sequence of mouth shapes, known as visemes, where a viseme corresponds to a phoneme in an utterance. The interpolation process must consider the issue of context-dependent shape, or coarticulation, in order to produce realistic-looking speech. We describe an approach to such pose-based interpolation that deals with coarticulation using a constraint-based technique. This is demonstrated using a Mexican-Spanish talking head, which can vary its speed of talking and produce coarticulation effects.