Significant pathological voice discrimination by computing posterior distribution of balanced accuracy. (March 2022)

• Record Type: Journal Article
• Authors: Pakravan, Mansooreh; Jahed, Mehran
• Is Part Of: Biomedical signal processing and control. Volume 73(2022)
• Publication Date: 2022-03
• Subjects: Glottal waveform -- Kernel principal component analysis -- Naïve Bayes classifier -- Fisher linear discriminant -- Posterior distribution of balanced accuracy; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.103410
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Parametric statistical tests to investigate balanced accuracy in discriminating pathological and normal voices. Signal modeling and processing methods to obtain a suitable glottal waveform for each voice. Extraction of six discriminating features through Kernel Principal Component Analysis (KPCA) Modeling the posterior distribution of the balanced accuracy to calculate the p-value of the average of the cross-validation results. Significant improved performance in discrimination of pathological voices. Abstract: The ability to speak lucidly plays a key role in social relations. Consequently, the role of the larynx is quite important, and timely diagnosis of laryngeal diseases has proved to be crucial. In this study, a simple computational model for inverse of speech production model is employed to extract the glottal waveform using speech signal. This waveform has useful information about vocal folds performance in terms of providing evidence for distinguishing pathological disorders. Furthermore, obtaining the significance of classification results is important, because it leads to reliable inferences. This study utilizes the sustained vowel sound /a/ and a well-referenced database, namely MEEI. In this work, after extraction of six discriminating features by using appropriate signal modeling and processing methods and upon change of the feature space by using Kernel Principal Component Analysis (KPCA), a classifier consisting of Naïve Bayes and Fisher Linear Discriminant, is exerted on the feature sets. Regarding voice pathology detection, the proposed approach achieved a significant classification balanced accuracy 93.6 % ± 0.03 with p-value < 0.01 for normal and abnormal classification using the Beta distribution model for the posterior distribution of the average of the cross-validation results. The proposed features are also compared with some conventional features in this field. The results show significant improved performance for the proposed features in discriminating different types of pathological voices.