Semi-Supervised End-to-End Speech Recognition.
Shigeki KaritaShinji WatanabeTomoharu IwataAtsunori OgawaMarc DelcroixPublished in: INTERSPEECH (2018)
Keyphrases
- end to end
- speech recognition
- semi supervised
- hidden markov models
- language model
- pattern recognition
- automatic speech recognition
- speech signal
- speech processing
- speech synthesis
- speech recognizer
- noisy environments
- congestion control
- speech recognition systems
- active learning
- speaker identification
- speech recognition technology
- speech recognizers
- co training
- face recognition
- text localization and recognition