Learning Noise Invariant Features Through Transfer Learning For Robust End-to-End Speech Recognition.
Shucong ZhangCong-Thanh DoRama DoddipatlaSteve RenalsPublished in: ICASSP (2020)
Keyphrases
- end to end
- speech recognition
- transfer learning
- noisy environments
- invariant features
- knowledge transfer
- transfer knowledge
- reinforcement learning
- learning algorithm
- supervised learning
- language model
- active learning
- learning process
- text classification
- speech signal
- unsupervised learning
- machine learning algorithms
- hidden markov models
- pattern recognition
- text categorization
- training data
- previously learned
- data mining