MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement.
Alexander RichardMichael ZollhöferYandong WenFernando De la TorreYaser SheikhPublished in: CoRR (2021)
Keyphrases
- facial animation
- facial expressions
- human faces
- speech recognition
- temporal coherence
- head motion
- active appearance models
- face model
- motion capture data
- motion capture
- speech signal
- face images
- stereo vision
- facial images
- automatic speech recognition
- three dimensional
- speaker identification
- speech synthesis
- affect sensing
- audio visual
- shape model
- human body
- pose estimation
- language acquisition
- gaussian mixture model
- virtual environment
- multi modal
- computer animation
- object recognition
- vocal tract
- computer vision