A Speech-Driven 3-D Lip Synthesis with Realistic Dynamics in Mandarin Chinese.
Changwei LiangXiaosheng PanJiangping KongPublished in: ISAIMS (2020)
Keyphrases
- facial animation
- motion synthesis
- facial expressions
- facial motion
- data driven
- real life
- speech recognition
- real time
- audio visual
- dynamic model
- human faces
- dynamical systems
- facial features
- automatic speech recognition
- real world
- noisy environments
- text to speech
- program synthesis
- visual speech
- lip reading
- speech signal
- dialogue system
- human motion
- spoken language
- non stationary
- multi modal
- audio signals
- natural language
- video sequences
- face recognition
- multimedia
- visual speech recognition
- information retrieval