Combining acoustic features and medical data in deep learning networks for voice pathology classification.
Ioanna MiliaresiKyriakos PoutosAggelos PikrakisPublished in: EUSIPCO (2020)
Keyphrases
- medical data
- deep learning
- unsupervised learning
- acoustic features
- medical images
- pattern recognition
- machine learning
- classification accuracy
- data mining
- mel frequency cepstral coefficients
- image classification
- supervised learning
- support vector machine
- support vector
- decision trees
- automatic speech recognition
- feature selection
- neural network
- information retrieval systems
- feature vectors
- maximum likelihood
- speech recognition
- information retrieval