Cross-speaker Emotion Transfer Based On Prosody Compensation for End-to-End Speech Synthesis.
Tao LiXinsheng WangQicong XieZhichao WangMingqi JiangLei XiePublished in: INTERSPEECH (2022)
Keyphrases
- end to end
- speech synthesis
- prosodic features
- speech recognition
- vocal tract
- text to speech
- automatic speech recognition
- wireless ad hoc networks
- admission control
- multipath
- congestion control
- hidden markov models
- language model
- pattern recognition
- facial expressions
- ad hoc networks
- high bandwidth
- real time
- emotion recognition
- application layer
- probabilistic model
- information retrieval