Detection of Speech Impairments Using Cepstrum, Auditory Spectrogram and Wavelet Time Scattering Domain Features

• Published in: IEEE access Vol. 8; pp. 96162 - 96172
• Main Authors: Lauraitis, Andrius, Maskeliunas, Rytis, Damasevicius, Robertas, Krilavicius, Tomas
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applications programs; Central nervous system; decision support; Decision support systems; deep learning; digital health; Entropy; Feature extraction; Internet of Medical Things; Mel frequency cepstral coefficient; mobile app; Mobile computing; Neural impairment; Neural networks; Scattering; Spectrograms; Speech; speech processing; Support vector machines; Task analysis; Voice recorders; Wavelet analysis; wavelet scattering; Wavelet transforms
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.2995737

We adopt Bidirectional Long Short-Term Memory (BiLSTM) neural network and Wavelet Scattering Transform with Support Vector Machine (WST-SVM) classifier for detecting speech impairments of patients at the early stage of central nervous system disorders (CNSD). The study includes 339 voice samples collected from 15 subjects: 7 patients with early stage CNSD (3 Huntington, 1 Parkinson, 1 cerebral palsy, 1 post stroke, 1 early dementia), other 8 subjects were healthy. Speech data is collected using voice recorder from Neural Impairment Test Suite (NITS) mobile app. Features are extracted from pitch contours, Mel-frequency cepstral coefficients (MFCC), Gammatone cepstral coefficients (GTCC), Gabor (analytic Morlet) wavelet and auditory spectrograms. 94.50% (BiLSTM) and 96.3% (WST-SVM) accuracy is achieved for solving healthy vs. impaired classification problem. The developed method can be applied for automated CNSD patient health state monitoring and clinical decision support systems as well as a part of Internet of Medical Things (IoMT).