Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos.
Alexander WaibelMoritz BehrFevziye Irem EyiokurDogucan YamanTuan-Nam NguyenCarlos MullovMehmet Arif DemirtasAlperen KantarciStefan ConstantinHazim Kemal EkenelPublished in: CoRR (2022)
Keyphrases
- facial features
- lip reading
- human faces
- video sequences
- machine translation
- video frames
- voice recognition
- face images
- video data
- video surveillance
- personal photos
- video dataset
- motion features
- video database
- video analysis
- video content
- face detection
- hidden markov models
- facial expression recognition
- video clips
- query translation
- event recognition
- facial images
- statistical machine translation
- facial expressions