Real-Time End-to-End Monaural Multi-Speaker Speech Recognition.
Song LiBeibei OuyangFuchuan TongDexin LiaoLin LiQingyang HongPublished in: Interspeech (2021)
Keyphrases
- speech recognition
- end to end
- real time
- automatic speech recognition
- text localization and recognition
- hidden markov models
- language model
- speech processing
- speech recognizer
- speaker identification
- speech recognition technology
- speech synthesis
- pattern recognition
- speaker dependent
- speech signal
- congestion control
- speaker independent
- speaker recognition
- speaker diarization
- noisy environments
- speech recognition systems
- cepstral coefficients
- isolated word