Comparison of Telephone Recordings and Professional Microphone Recordings for Early Detection of Parkinson's Disease, Using Mel-Frequency Cepstral Coefficients with Gaussian Mixture Models.
Laetitia JeancolasGraziella MangoneJean-Christophe CorvolMarie VidailhetStéphane LehéricyBadr-Eddine BenkelfatHabib BenaliDijana Petrovska-DelacrétazPublished in: INTERSPEECH (2019)
Keyphrases
- mel frequency cepstral coefficients
- gaussian mixture model
- acoustic features
- early detection
- automatic speech recognition
- speaker recognition
- speaker diarization
- speaker identification
- linear predictive
- speech signal
- mixture model
- speech recognition
- visual features
- speaker verification
- music information retrieval
- breast cancer
- feature vectors
- audio features
- em algorithm
- lung cancer
- feature space
- expectation maximization
- multi modal
- maximum likelihood
- feature set
- visual information
- bayesian information criterion
- broadcast news
- feature selection
- image classification
- feature extraction
- decision trees
- image processing