FAT-HuBERT: Front-end Adaptive Training of Hidden-unit BERT for Distortion-Invariant Robust Speech Recognition.
Dongning YangWei WangYanmin QianPublished in: CoRR (2023)
Keyphrases
- speech recognition
- noisy environments
- wall street journal corpus
- isolated word
- hidden markov models
- speech synthesis
- speech understanding
- language model
- speech processing
- speech recognizer
- speech signal
- pattern recognition
- acoustic models
- speaker identification
- automatic speech recognition
- speaker independent
- speech recognition technology
- keyword spotting
- speech recognition systems
- speaker dependent
- speech retrieval
- speech recognizers
- machine learning
- speech recognition errors
- image processing
- information retrieval