Dysarthric Severity Categorization Based on Speech Intelligibility: A Hybrid Approach

• Published in: Circuits, systems, and signal processing Vol. 43; no. 11; pp. 7044 - 7063
• Main Authors: M, Vidya, S, Ganesh Vaidyanathan
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2024; Springer Nature B.V
• Subjects: Accuracy; Acoustics; Artificial neural networks; Circuits and Systems; Classification; Communication; Dysarthria; Electrical Engineering; Electronics and Microelectronics; Engineering; Fourier transforms; Gaussian process; Instrumentation; Intelligibility; Neural networks; Probabilistic models; Signal classification; Signal processing; Signal,Image and Speech Processing; Speech disorders; Speech recognition; Speech therapy; Support vector machines; Voice recognition; Hybrid; Deep neural network; Feed forward neural network; Gaussian mixture model; Mel frequency cepstral coefficients
• ISSN: 0278-081X; 1531-5878
• DOI: 10.1007/s00034-024-02770-7

The intelligibility of speech is a primary component to assess the severity level of Dysarthria, a speech disorder, which is caused not only due to weakness in vocal motor muscles but also difficulty in controlling its movements. Prior information about the severity of Dysarthria, aids the therapist during the rehabilitation process. This paper introduces a novel hybrid architecture comprising Gaussian Mixture Model and Neural Network (GMM-NN) for categorizing Dysarthric severity into four classes based on speech intelligibility. Mel Frequency Cepstral Coefficients (MFCC) extracted from the segmented speech signals are used to train the classifier. The proposed model produced a 1.9% improvement in accuracy when compared to the baseline Gaussian Mixture Model (GMM). The Gaussian Mixture Model Deep Neural Network (GMM-DNN) and Gaussian Mixture Model Feed Forward Neural Network (GMM-FFNN) architectures showed an accuracy of 96.7% and 96.42% with F1 scores of 0.9649, 0.9604 respectively.