Face-Dubbing++: LIP-Synchronous, Voice Preserving Translation Of Videos.
Alexander WaibelMoritz BehrDogucan YamanFevziye Irem EyiokurTuan-Nam NguyenCarlos MullovMehmet Arif DemirtasAlperen KantarciStefan ConstantinHazim Kemal EkenelPublished in: ICASSP Workshops (2023)
Keyphrases
- facial features
- lip reading
- human faces
- video sequences
- voice recognition
- facial expressions
- machine translation
- video content
- facial images
- motion features
- mouth region
- video database
- video frames
- face images
- recognition algorithm
- video analysis
- video clips
- video surveillance
- expression recognition
- head tracking
- key frames