End-to-End Multilingual Multi-Speaker Speech Recognition.
Hiroshi SekiTakaaki HoriShinji WatanabeJonathan Le RouxJohn R. HersheyPublished in: INTERSPEECH (2019)
Keyphrases
- speech recognition
- end to end
- automatic speech recognition
- hidden markov models
- language model
- speech signal
- speech synthesis
- speaker identification
- speaker dependent
- pattern recognition
- speech recognizer
- speech recognition technology
- speaker diarization
- congestion control
- speech processing
- speech recognition systems
- noisy environments
- speaker independent
- acoustic models
- speaker adaptation
- language independent
- speech retrieval
- machine learning
- cross language
- cepstral coefficients
- computer vision