Representation transfer learning from deep end-to-end speech recognition networks for the classification of health states from speech.
Benjamin SertolliZhao RenBjörn W. SchullerNicholas CumminsPublished in: Comput. Speech Lang. (2021)
Keyphrases
- speech recognition
- end to end
- transfer learning
- pattern recognition
- speech signal
- speech synthesis
- text classification
- automatic speech recognition
- speech processing
- speech recognizer
- machine learning
- language model
- speech recognition technology
- speech recognition systems
- speaker identification
- hidden markov models
- machine learning algorithms
- noisy environments
- labeled data
- classification accuracy
- active learning
- isolated word
- collaborative filtering
- feature extraction
- cross domain
- model selection
- reinforcement learning
- text mining
- supervised learning
- feature space
- high dimensional
- learning algorithm
- speech recognizers
- speaker dependent
- speaker diarization
- training set
- unsupervised learning
- speaker recognition
- broadcast news
- cross lingual