Sciweavers

ICMCS
2006
IEEE

Acoustically-Driven Talking Face Synthesis using Dynamic Bayesian Networks

14 years 4 months ago
Acoustically-Driven Talking Face Synthesis using Dynamic Bayesian Networks
Dynamic Bayesian Networks (DBNs) have been widely studied in multi-modal speech recognition applications. Here, we introduce DBNs into an acoustically-driven talking face synthesis system. Three prototypes of DBNs, namely independent, coupled, and product HMMs were studied. Results showed that the DBN methods were more effective in this study than a multilinear regression baseline. Coupled and product HMMs performed similarly better than independent HMMs in terms of motion trajectory accuracy. Audio and visual speech asynchronies were represented differently for coupled HMMs versus product HMMs.
Jianxia Xue, Jonas Borgstrom, Jintao Jiang, Lynne
Added 11 Jun 2010
Updated 11 Jun 2010
Type Conference
Year 2006
Where ICMCS
Authors Jianxia Xue, Jonas Borgstrom, Jintao Jiang, Lynne E. Bernstein, Abeer Alwan
Comments (0)