UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis.
Yi LeiShan YangXinsheng WangQicong XieJixun YaoLei XieDan SuPublished in: AAAI (2023)
Keyphrases
- end to end
- text to speech
- unified model
- speech synthesis
- prosodic features
- congestion control
- text to speech synthesis
- wireless ad hoc networks
- multipath
- programming tool
- admission control
- high bandwidth
- word processing
- ad hoc networks
- music information retrieval
- hidden markov models
- content delivery
- rate allocation
- application layer
- text localization and recognition