A Purely End-to-End System for Multi-speaker Speech Recognition.
Hiroshi SekiTakaaki HoriShinji WatanabeJonathan Le RouxJohn R. HersheyPublished in: ACL (1) (2018)
Keyphrases
- speech recognition
- end to end
- automatic speech recognition
- hidden markov models
- speaker identification
- language model
- speech signal
- speech processing
- speech synthesis
- speaker dependent
- noisy environments
- pattern recognition
- speech recognition systems
- congestion control
- speech recognition technology
- speech recognizer
- speaker diarization
- isolated word
- speaker adaptation
- acoustic models
- speaker recognition
- noisy speech
- speaker verification