Multiple-Hypothesis CTC-Based Semi-Supervised Adaptation of End-to-End Speech Recognition.
Cong-Thanh DoRama DoddipatlaThomas HainPublished in: ICASSP (2021)
Keyphrases
- end to end
- speech recognition
- multiple hypothesis
- semi supervised
- speaker adaptation
- particle filter
- language model
- hidden markov models
- speech synthesis
- automatic speech recognition
- semi supervised learning
- speech recognizer
- speech processing
- speech signal
- congestion control
- labeled data
- unlabeled data
- pattern recognition
- noisy environments
- speech recognition systems
- co training
- active learning
- speaker identification
- speech recognition technology
- speech recognizers
- isolated word
- text classification
- dynamic programming
- neural network