Cross-Speaker Emotion Disentangling and Transfer for End-to-End Speech Synthesis.
Tao LiXinsheng WangQicong XieZhichao WangLei XiePublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2022)
Keyphrases
- end to end
- speech synthesis
- speech recognition
- prosodic features
- vocal tract
- text to speech
- automatic speech recognition
- hidden markov models
- language model
- facial expressions
- multipath
- speech signal
- wireless ad hoc networks
- congestion control
- internet protocol
- ad hoc networks
- pattern recognition
- transport layer
- rate allocation
- high bandwidth
- scalable video
- application layer
- noisy environments
- text localization and recognition
- real world
- admission control
- face recognition
- information retrieval