Variable rate speech animation synthesis
暂无分享,去创建一个
Speech animation has traditionally been achieved by two main approaches: image-based methods [Ezzat et al. 2002] and key-framing methods [Cohen and Massaro 1993]. Both approaches require large databases that include many images or 3D shapes with facial expressions and speech lip shapes.
[1] Tomaso Poggio,et al. Trainable Videorealistic Speech Animation , 2004, FGR.
[2] Michael M. Cohen,et al. Modeling Coarticulation in Synthetic Visual Speech , 1993 .
[3] Demetri Terzopoulos,et al. Realistic modeling for facial animation , 1995, SIGGRAPH.