Dual supervised learning for non-native speech recognition.
Kacper RadzikowskiRobert NowakLe WangOsamu YoshiePublished in: EURASIP J. Audio Speech Music. Process. (2019)
Keyphrases
- speech recognition
- supervised learning
- language model
- hidden markov models
- unsupervised learning
- speech recognizer
- speech synthesis
- training data
- speech processing
- speech signal
- speech recognition systems
- noisy environments
- semi supervised
- training set
- speaker identification
- pattern recognition
- speech understanding
- machine learning
- automatic speech recognition
- speech recognition technology
- active learning
- keyword spotting
- speech recognizers
- speech retrieval
- learning algorithm
- speaker independent
- feature extraction