DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser.
Peng ChenXiaobao WeiMing LuYitong ZhuNaiming YaoXingyu XiaoHui ChenPublished in: CoRR (2023)
Keyphrases
- facial animation
- speech recognition
- face recognition
- user modeling
- data driven
- feature points
- stereo vision
- automatic speech recognition
- facial expressions
- user profiling
- audio visual
- speech signal
- recognition engine
- face images
- emotion recognition
- speech synthesis
- spontaneous speech
- endpoint detection
- information retrieval
- recognition algorithm
- pose estimation
- noisy environments
- language acquisition
- context aware
- spoken language
- vocal tract
- recommender systems