Hybrid phoneme based clustering approach for audio driven facial animation

B Havell; PL Rosin; S Sanei; A Aubrey; D Marshall; Y Hicks

doi:10.1109/ICASSP.2012.6288364

Back

Journal article

Hybrid phoneme based clustering approach for audio driven facial animation

B Havell, PL Rosin, S Sanei, A Aubrey, D Marshall and Y Hicks

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp.2261-2264

25/03/2012 - 30/03/2012

2012

DOI: https://doi.org/10.1109/ICASSP.2012.6288364

Abstract

We consider the problem of producing accurate facial animation corresponding to a given input speech signal. A popular technique previously used for Audio Driven Facial Animation is to build a joint audio-visual model using Active Appearance Models (AAMs) to represent possible facial variations and Hidden Markov Models (HMMs) to select the correct appearance based on the input audio. © 2012 IEEE.

Metrics

22 Record Views

Details

Title: Hybrid phoneme based clustering approach for audio driven facial animation
Creators: B Havell
PL Rosin
S Sanei
A Aubrey
D Marshall
Y Hicks
Publication Details: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp.2261-2264
Event: 25/03/2012 - 30/03/2012
Date published: 2012
Date submitted: 06/12/2012
Identifiers: 99516819502346
Academic Unit: University of Surrey
Resource Type: Journal article

Hybrid phoneme based clustering approach for audio driven facial animation

Abstract

Metrics

Details

Usage Policy