HMM-based transmodal mapping from audio speech to talking faces
Author:
- 7 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (10893555) , 33-42
Abstract
Describes a transmodal mapping from audio speech to talking faces based on hidden Markov models (HMMs). If face movements are synthesized well enough for natural communication, a lot of benefits will be brought to human-machine communication. This paper describes an HMM-based speech-driven lip movement synthesis. The paper also describes its improvement by audio-visual joint estimation and its extension to talking face generation. The results of evaluation experiments show that the proposed method generates natural and accurate talking faces from audio speech inputs.Keywords
This publication has 2 references indexed in Scilit:
- Converting speech into lip movements: a multimedia telephone for hard of hearing peopleIEEE Transactions on Rehabilitation Engineering, 1995
- A media conversion from speech to facial image for intelligent man-machine interfaceIEEE Journal on Selected Areas in Communications, 1991