Cycle-consistency Training for End-to-end Speech Recognition.
Takaaki HoriRamón Fernandez AstudilloTomoki HayashiYu ZhangShinji WatanabeJonathan Le RouxPublished in: ICASSP (2019)
Keyphrases
- end to end
- speech recognition
- wall street journal corpus
- isolated word
- hidden markov models
- automatic speech recognition
- acoustic models
- language model
- speech processing
- speech signal
- speech recognizer
- pattern recognition
- speech synthesis
- congestion control
- speech recognition technology
- speech recognizers
- speech recognition systems
- speaker dependent
- speaker independent
- noisy environments
- machine learning
- speech retrieval
- text localization and recognition