Semi-supervised End-to-end Speech Recognition Using Text-to-speech and Autoencoders.
Shigeki KaritaShinji WatanabeTomoharu IwataMarc DelcroixAtsunori OgawaTomohiro NakataniPublished in: ICASSP (2019)
Keyphrases
- end to end
- text to speech
- semi supervised
- speech synthesis
- text to speech synthesis
- prosodic features
- denoising
- wireless ad hoc networks
- congestion control
- programming tool
- active learning
- word processing
- pairwise
- admission control
- rate allocation
- high bandwidth
- english text
- multipath
- transport layer
- ad hoc networks
- content delivery
- speech recognition
- writing skills
- real world