Controllable Emotion Transfer For End-to-End Speech Synthesis.
Tao LiShan YangLiumeng XueLei XiePublished in: CoRR (2020)
Keyphrases
- end to end
- speech synthesis
- speech recognition
- text to speech
- prosodic features
- vocal tract
- congestion control
- ad hoc networks
- admission control
- facial expressions
- high bandwidth
- content delivery
- emotion recognition
- wireless ad hoc networks
- multipath
- machine learning
- application layer
- internet protocol
- rate allocation
- scalable video
- hidden markov models
- emotional state
- video streams
- image quality
- pattern recognition
- feature extraction