Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition.
Xiaoyu YangQiujia LiChao ZhangPhilip C. WoodlandPublished in: CoRR (2023)
Keyphrases
- end to end
- speech recognition
- hidden markov models
- language model
- pattern recognition
- speech recognizer
- acoustic models
- speech synthesis
- speech recognition technology
- probabilistic model
- speech signal
- speech recognizers
- automatic speech recognition
- noisy environments
- speaker dependent
- speaker identification
- congestion control
- speech processing
- speech recognition systems
- machine learning
- mobile devices
- computer vision