Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator.
Lingwei MengJiawen KangMingyu CuiHaibin WuXixin WuHelen MengPublished in: CoRR (2023)
Keyphrases
- speech recognition
- speaker identification
- speaker diarization
- hidden markov models
- speech synthesis
- speech understanding
- speech recognizer
- speech signal
- speech processing
- language model
- automatic speech recognition
- pattern recognition
- handwriting recognition
- speech recognition technology
- noisy environments
- speech recognizers
- keyword spotting
- speech recognition systems
- word error rate
- machine learning
- feature extraction
- speaker adaptation
- cepstral coefficients
- speaker dependent
- information retrieval