Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation.
Elizabeth SaleskyMatthias SperberAlan W. BlackPublished in: CoRR (2019)
Keyphrases
- end to end
- speech recognition
- speech synthesis
- automatic speech recognition
- automatic speech recognition systems
- speech signal
- text to speech
- hidden markov models
- phoneme recognition
- speaker dependent
- broadcast news
- congestion control
- wireless ad hoc networks
- admission control
- rate allocation
- speech sounds
- application layer
- high bandwidth
- content delivery
- internet protocol
- multipath
- ad hoc networks
- bit rate
- real time