An unsupervised deep domain adaptation approach for robust speech recognition.
Sining SunBinbin ZhangLei XieYanning ZhangPublished in: Neurocomputing (2017)
Keyphrases
- speech recognition
- domain adaptation
- noisy environments
- semi supervised
- speech synthesis
- hidden markov models
- language model
- speech recognizer
- speech signal
- pattern recognition
- cross domain
- automatic speech recognition
- speaker identification
- speech recognition systems
- supervised learning
- semi supervised learning
- labeled data
- multiple sources
- neural network
- unsupervised learning
- feature extraction
- transfer learning
- training data
- sentiment classification
- image processing
- user profiles
- co training
- n gram
- text categorization
- computer vision
- machine learning