End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue.
Kentaro MitsuiTianyu ZhaoKei SawadaYukiya HonoYoshihiko NankakuKeiichi TokudaPublished in: INTERSPEECH (2022)
Keyphrases
- end to end
- text to speech
- wireless ad hoc networks
- admission control
- prosodic features
- high bandwidth
- speech synthesis
- congestion control
- text to speech synthesis
- scalable video
- conversational agents
- multipath
- rate allocation
- application layer
- speaker verification
- content delivery
- dialogue system
- programming tool
- hidden markov models