Investigation of self-supervised pre-trained models for classification of voice quality from speech and neck surface accelerometer signals.
Sudarsana Reddy KadiriFarhad JavanmardiPaavo AlkuPublished in: Comput. Speech Lang. (2024)
Keyphrases
- acoustic signals
- pre trained
- decision trees
- speech recognition
- probabilistic model
- machine learning
- fundamental frequency
- statistical model
- signal processing
- feature vectors
- feature extraction
- three dimensional
- active learning
- viewpoint
- text classification
- training examples
- feature space
- feature selection
- neural network