SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory.
Se Jin ParkMinsu KimJoanna HongJeongsoo ChoiYong Man RoPublished in: AAAI (2022)
Keyphrases
- lip reading
- mouth region
- visual speech
- facial features
- audio visual speech recognition
- hidden markov models
- human faces
- head tracking
- memory usage
- visual speech recognition
- localization method
- expression recognition
- facial expressions
- principal component analysis
- multimedia
- generation process
- limited memory
- data sets
- recognition algorithm
- facial images
- memory requirements
- face detection