The automatic assessment of the severity of dysphonia

Abstract

Perceptual evaluation of the patient's voice is the most commonly used method in everyday clinical practice. We propose an automatic approach for the prediction of severity of some types of organic and functional dysphonia. By means of an unsupervised learning method, we have demonstrated that acoustic parameters measured on different phonetic classes are suitable for modelling the four grade assessments of the specialists (RBH subjective scale from 0 to 3). In this study, the overall hoarseness H was examined. Four specialists were asked to determine the severity of dysphonia. A k-means cluster analysis was performed for the decision of each specialist separately; the average accuracy of the four-grade classification was 0.46. The four-grade classification has been surprisingly close to the subjective judgements. Moreover, automatic estimation of severity of dysphonia was also determined. Linear regression and RBF kernel regression models were compared. The average rating of the four specialists were used as target in the experiments. Low RMSE and high correlation measures were obtained between the automatically predicted severity and perceptual assessments. The best RMS value of H was 0.45 for the model with RBF kernel, however, a simpler linear model provided the highest correlation value of 0.85, using only eight acoustic parameters.

Multitask and Transfer Learning Approach for Joint Classification and Severity Estimation of Dysphonia

“…The [25] study predicted dysphonic speech severity from sustained vowels’ time and spectral features using step-wise multiple regression, yielding mean \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $R$\end{document} of 0.880 and mean \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} $R^{2}$\end{document} of 0.775. Continuous speech samples were used for automated dysphonia severity assessment, achieving 89% accuracy and a root mean square error (RMSE) of 0.49 for binary classification and severity estimation, respectively [26] …”

“…The [25] study predicted dysphonic speech severity from sustained vowels' time and spectral features using step-wise multiple regression, yielding mean R of 0.880 and mean R 2 of 0.775. Continuous speech samples were used for automated dysphonia severity assessment, achieving 89% accuracy and a root mean square error (RMSE) of 0.49 for binary classification and severity estimation, respectively [26] Deep learning techniques, like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNNs), have gained traction in analyzing pathological speech due to their impressive performance in diverse domains such as image recognition [27], natural language processing [28] and speech recognition [29]. Several studies have been conducted in the research area of voice disorder.…”

Nutritional Biomarkers as Predictors of Dysphonia Severity in Patients with Ischemic Stroke

“…Several motor, sensory, cognitive, and communication disorders occur after ischemic stroke, and among them, dysphonia is an important problem that is easily overlooked in terms of the functional outcome of ischemic rehabilitation and the quality of life of patients. Dysphonia refers to changes in voice, such as hoarseness or pitch quality [ 2 ]. Dysphonia is common after an ischemic stroke and occurs in approximately 20% of patients [ 3 ].…”

Severity Estimation of Depression Using Convolutional Neural Network

“…Speech is such a biomarker. It can indicate not only depression but also many other illnesses, such as Parkinson's disease [6] or dysphonia [7]. Speech provides an opportunity to develop effective, non-invasive diagnostic tools that can assist professionals in their work [8,9].…”