Hearing Faces: Target Speaker Text-to-Speech Synthesis from a Face.
Björn PlüsterCornelius WeberLeyuan QuStefan WermterPublished in: ASRU (2021)
Keyphrases
- text to speech synthesis
- human faces
- face images
- face identification
- face analysis
- expression recognition
- face recognition systems
- face tracking
- facial features
- face detector
- face matching
- face recognition
- recognizing faces
- face detection
- recognize faces
- orl database
- speech recognition
- face model
- facial expressions
- text to speech
- sign language
- face verification
- face detection and recognition
- face space
- facial pose
- detecting faces
- lighting conditions
- personal photos
- morphable face model
- frontal face
- face recognition algorithms
- partially occluded
- target tracking
- audio visual
- facial expression recognition
- face databases
- frontal view
- speaker recognition
- speaker verification
- morphable model
- detection method
- hidden markov models
- training set