| | |
Summary: ACOUSTICALLY-DRIVEN TALKING FACE SYNTHESIS USING DYNAMIC BAYESIAN
NETWORKS
Jianxia Xue1
, Jonas Borgstrom1
, Jintao Jiang2
, Lynne E. Bernstein2
, Abeer Alwan1
1
University of California, Los Angeles, CA 90095, USA, {jxue, jonas, alwan}@ee.ucla.edu
2
House Ear Institute, Los Angeles, CA 90057, USA, {jjiang, lbernstein}@hei.org
ABSTRACT
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
|
