Layer-wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition.
Xun GongYizhou LuZhikai ZhouYanmin QianPublished in: CoRR (2022)
Keyphrases
- speech recognition
- end to end
- application layer
- speaker adaptation
- hidden markov models
- speech processing
- language model
- speech synthesis
- speech recognizer
- automatic speech recognition
- noisy environments
- congestion control
- speech signal
- speaker identification
- pattern recognition
- speech recognition technology
- speaker independent
- speech retrieval
- speech recognizers
- speaker dependent
- speech recognition systems
- multimedia
- information retrieval
- neural network