Faces that Speak: Jointly Synthesising Talking Face and Speech from Text.
Youngjoon JangJi-Hoon KimJunseok AhnDoyeop KwakHongsun YangYooncheol JuIlhwan KimByeong-Yeol KimJoon Son ChungPublished in: CoRR (2024)
Keyphrases
- human faces
- face images
- face identification
- face analysis
- recognition engine
- text to speech
- facial features
- face matching
- face recognition
- multi lingual
- text to speech synthesis
- text retrieval
- information retrieval
- text recognition
- face tracking
- english text
- speech recognition
- lexical features
- expression recognition
- news video
- text input
- face detection
- face space
- face recognition systems
- partially occluded
- broadcast news
- facial expressions
- facial images
- face detector
- facial animation
- lighting conditions
- recognize faces
- line drawings
- spontaneous speech
- morphable face model
- recognizing faces
- orl database
- face detection and recognition
- personal photos
- face databases
- speech synthesis
- facial expression recognition
- speech signal
- pose variations
- face recognition algorithms
- face model
- conversational speech
- detecting faces
- frontal view
- spoken documents
- complex background