A coupled HMM approach to video-realistic speech animation

DOI10.1016/J.PATCOG.2006.12.001MaRDI QIDQ882283zbMATH OpenOpenAlexFDO

Authors Lei Xie, Zhiqiang Liu

Publication date 23 May 2007

Published in Pattern Recognition (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.patcog.2006.12.001

zbMATH Keywords

audio-to-visual conversionCoupled hidden Markov modelsfacial animationspeech animationtalking faces

Mathematics Subject Classification ID

Machine vision and scene understanding (68T45)

Recommendations

• Hidden Markov model inversion for audio-to-visual conversion in an MPEG-4 facial animation system
• Conversion of continuous speech sound to articulation animation as an application of visual coarticulation modeling
• Speech-to-lip movement synthesis by maximizing audio-visual joint probability based on the EM algorithm
• scientific article; zbMATH DE number 1929202
• scientific article; zbMATH DE number 2089703

Cites work

• Dynamic Bayesian networks for audio-visual speech recognition
• Hidden Markov model inversion for audio-to-visual conversion in an MPEG-4 facial animation system
• scientific article; zbMATH DE number 1634667 (Why is no real title available?)
• scientific article; zbMATH DE number 3567782 (Why is no real title available?)
• scientific article; zbMATH DE number 1929202 (Why is no real title available?)
• Synthesizing realistic facial animations using energy minimization for model-based coding

Cited in

(4)

• Conversion of continuous speech sound to articulation animation as an application of visual coarticulation modeling
• scientific article; zbMATH DE number 1929202 (Why is no real title available?)
• Speech-to-lip movement synthesis by maximizing audio-visual joint probability based on the EM algorithm
• Hidden Markov model inversion for audio-to-visual conversion in an MPEG-4 facial animation system

This page was built for publication: A coupled HMM approach to video-realistic speech animation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q882283)