A unified approach to transfer learning of deep neural networks with applications to speaker adaptation in automatic speech recognition.
Zhen HuangSabato Marco SiniscalchiChin-Hui LeePublished in: Neurocomputing (2016)
Keyphrases
- transfer learning
- automatic speech recognition
- speaker adaptation
- neural network
- speech recognition
- hidden markov models
- speech signal
- pattern recognition
- reinforcement learning
- cross domain
- machine learning
- labeled data
- collaborative filtering
- maximum likelihood
- semi supervised learning
- noisy environments
- broadcast news
- machine learning algorithms
- text categorization
- active learning
- learning algorithm
- text mining
- acoustic features
- text classification
- language model
- speaker dependent
- cross lingual
- knowledge representation
- speaker independent