Voice Aging with Audio-Visual Style Transfer.
Justin WilsonSunyeong ParkSeunghye J. WilsonMing C. LinPublished in: CoRR (2021)
Keyphrases
- audio visual
- emotion recognition
- multi modal
- visual information
- multimedia
- person authentication
- multi stream
- visual data
- temporal context
- transfer learning
- computer vision
- speaker verification
- audio visual speech recognition
- audio features
- low level
- domain knowledge
- mobile devices
- feature extraction
- text to speech
- face recognition
- three dimensional
- multimodal fusion