On Using the UA-Speech and Torgo Databases to Validate Automatic Dysarthric Speech Classification Approaches.
Guilherme SchuParvaneh JanbakhshiIna KodrasiPublished in: ICASSP (2023)
Keyphrases
- speech music discrimination
- databases
- speech recognition
- speech signal
- classification accuracy
- automatic speech recognition
- machine learning
- machine learning methods
- automatic classification
- text classification
- classification schemes
- pattern recognition
- machine learning algorithms
- recognition engine
- spoken language
- text to speech
- neural networks and support vector machines
- speech corpus
- audio visual
- data sets
- classification method
- decision trees
- gaussian mixture model
- classification scheme
- semi automatic
- support vector machine
- acoustic signals
- feature extraction
- speaker recognition
- statistical classification
- spectral features
- data mining
- database systems
- speech recognition systems
- monte carlo methods
- feature vectors
- probabilistic model
- knowledge discovery
- emotion recognition
- noisy environments
- classification algorithm
- classification models