Talking Face Generation

5 benchmarks110 papers

Talking face generation aims to synthesize a sequence of face images that correspond to given speech semantics

<span style="color:grey; opacity: 0.6">( Image credit: Talking Face Generation by Adversarially Disentangled Audio-Visual Representation )</span>

Benchmarks

Talking Face Generation on CREMA-D

Talking Face Generation on LRW