Testing the Limits of Representation Mixing for Pronunciation Correction in End-to-End Speech Synthesis.
Jason FongJason TaylorSimon KingPublished in: INTERSPEECH (2020)
Keyphrases
- end to end
- speech synthesis
- speech recognition
- high bandwidth
- vocal tract
- congestion control
- ad hoc networks
- wireless ad hoc networks
- prosodic features
- admission control
- multipath
- real time
- hidden markov models
- text to speech
- pattern recognition
- transport layer
- information retrieval
- content delivery
- application layer
- automatic speech recognition
- scalable video
- computer vision