Exploring Effective Distillation of Self-Supervised Speech Models for Automatic Speech Recognition.
Yujin WangChangli TangZiyang MaZhisheng ZhengXie ChenWei-Qiang ZhangPublished in: CoRR (2022)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- word error rate
- broadcast news
- hidden markov models
- acoustic models
- speech retrieval
- conversational speech
- noisy environments
- spontaneous speech
- speech recognizer
- speech sounds
- recognition errors
- word recognition
- bayesian networks
- phoneme recognition
- spoken words
- acoustic features
- speaker adaptation
- language processing