Automated lip-synch and speech synthesis for character animation

Authors:
J. P. Lewis;F. I. Parke
Affiliations:
Computer Graphics Laboratory, New York Institute of Technology;Computer Graphics Laboratory, New York Institute of Technology
Venue:
CHI '87 Proceedings of the SIGCHI/GI Conference on Human Factors in Computing Systems and Graphics Interface
Year:
1986

Citing 6
Cited 8

Speech and expression: a computer solution to face animation

Proceedings on Graphics Interface '86/Vision Interface '86
Methods for stochastic spectral synthesis

Proceedings on Graphics Interface '86/Vision Interface '86
Principles of Computer Speech

Principles of Computer Speech
Programs for Digital Signal Processing

Programs for Digital Signal Processing
Linear Prediction of Speech

Linear Prediction of Speech
A parametric model for human faces.

A parametric model for human faces.

An automatic lip-synchronization algorithm for synthetic faces

MULTIMEDIA '94 Proceedings of the second ACM international conference on Multimedia
Automatic Creation of 3D Facial Models

IEEE Computer Graphics and Applications
Analysis and Synthesis of Facial Image Sequences Using Physical and Anatomical Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
3D Models Of The Lips For Realistic Speech Animation

CA '96 Proceedings of the Computer Animation
Building an advanced facial expression system

Graphics programming methods
Creating Speech-Synchronized Animation

IEEE Transactions on Visualization and Computer Graphics
Intelligent content production for a virtual speaker

IMTCI'04 Proceedings of the Second international conference on Intelligent Media Technology for Communicative Intelligence
Speech driven facial animation using HMMs in basque

TSD'06 Proceedings of the 9th international conference on Text, Speech and Dialogue

Quantified Score

Hi-index	0.00

Visualization

Abstract

An automated method of synchronizing facial animation to recorded speech is described. In this method, a common speech synthesis method (linear prediction) is adapted to provide simple and accurate phoneme recognition. The recognized phonemes are then associated with mouth positions to provide keyframes for computer animation of speech using a parametric model of the human face.The linear prediction software, once implemented, can also be used for speech resynthesis. The synthesis retains intelligibility and natural speech rhythm while achieving a “synthetic realism” consistent with computer animation. Speech synthesis also enables certain useful manipulations for the purpose of computer character animation.