SYNTHE-SEES: Face Based Text-to-Speech for Virtual Speaker.
Jae Hyun ParkJoon-Gyu MaengTaejun BakYoung-Sun JooPublished in: ICASSP (2024)
Keyphrases
- text to speech
- prosodic features
- speech synthesis
- speaker verification
- text to speech synthesis
- visual speech
- virtual environment
- word processing
- face images
- speech recognition
- virtual reality
- augmented reality
- human faces
- programming tool
- english text
- virtual world
- face verification
- distance learning
- speaker recognition
- neural network
- facial expressions
- probabilistic model
- feature space
- high level