Text-to-Visual Speech Synthesis for General Objects Using Parameter-Based Lip Models

Authors:
Ze-Jing Chuang;Chung-Hsien Wu
Affiliations:
-;-
Venue:
PCM '02 Proceedings of the Third IEEE Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Year:
2002

Citing 3
Cited 0

A muscle model for animation three-dimensional facial expression

SIGGRAPH '87 Proceedings of the 14th annual conference on Computer graphics and interactive techniques
Synthesizing realistic facial expressions from photographs

Proceedings of the 25th annual conference on Computer graphics and interactive techniques
FaceEngine a 3D facial animation engine for real time applications

Proceedings of the sixth international conference on 3D Web technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents four parameter-based 3-dimension (3D) lip models for Chinese text-to-visual speech synthesis. This model can be applied to general objects with lip-like meshes. Three main components will be described in this paper: the generation of weighted parameter sequence of lip motions for each Mandarin syllable, the definition and construction of parameter-based lip models, and the synchronization of speech and facial animation. The result shows that the system produces a promising and encouraging speech and facial animation output.