Cross-speaker Emotion Transfer Based On Prosody Compensation for End-to-End Speech Synthesis.
Tao LiXinsheng WangQicong XieZhichao WangMingqi JiangLei XiePublished in: CoRR (2022)
Keyphrases
- end to end
- speech synthesis
- prosodic features
- speech recognition
- vocal tract
- text to speech
- emotion recognition
- speaker verification
- automatic speech recognition
- ad hoc networks
- wireless ad hoc networks
- congestion control
- admission control
- language model
- facial expressions
- hidden markov models
- pattern recognition
- high bandwidth
- audio visual
- multipath
- content delivery
- speech signal
- internet protocol
- noisy environments
- application layer
- scalable video
- machine learning
- emotional state
- face recognition
- computer vision