Self-Supervised Learning with Bi-Label Masked Speech Prediction for Streaming Multi-Talker Speech Recognition.
Zili HuangZhuo ChenNaoyuki KandaJian WuYiming WangJinyu LiTakuya YoshiokaXiaofei WangPeidong WangPublished in: ICASSP (2023)
Keyphrases
- speech recognition
- speech synthesis
- hidden markov models
- speech signal
- automatic speech recognition
- pattern recognition
- speech processing
- speech recognition systems
- speaker identification
- speech recognition technology
- recognition engine
- language model
- information retrieval
- speech recognizer
- noisy environments
- linear prediction
- probabilistic model
- computer based instruction
- speech enhancement
- feature extraction
- speaker independent
- speech recognition errors
- machine learning
- speech recognizers
- isolated word