Towards end-to-end speech recognition with transfer learning.
Chu-Xiong QinDan QuLian-hai ZhangPublished in: EURASIP J. Audio Speech Music. Process. (2018)
Keyphrases
- end to end
- transfer learning
- speech recognition
- hidden markov models
- knowledge transfer
- reinforcement learning
- pattern recognition
- labeled data
- speech synthesis
- speech recognition systems
- language model
- automatic speech recognition
- speech signal
- machine learning
- text categorization
- cross domain
- active learning
- collaborative filtering
- speaker identification
- text classification
- speech recognizer
- transfer knowledge
- semi supervised learning
- machine learning algorithms
- text mining
- supervised learning
- learning algorithm
- information retrieval
- cross lingual
- domain specific
- natural language
- computer vision