DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder.
Chenpeng DuQi ChenTianyu HeXu TanXie ChenKai YuSheng ZhaoJiang BianPublished in: ACM Multimedia (2023)
Keyphrases
- high fidelity
- recognition engine
- real time
- medical image compression
- speech recognition
- high quality
- face images
- automatic speech recognition
- audio visual
- facial expressions
- human faces
- video conferencing
- real environment
- intelligent agents
- online learning
- anisotropic diffusion
- speech signal
- facial animation
- image analysis