Hierarchical Classification and System Combination for Automatically Identifying Physiological and Neuromuscular Laryngeal Pathologies

• Published in: Journal of voice Vol. 31; no. 3; pp. 384.e9 - 384.e14
• Main Authors: Cordeiro, Hugo, Fonseca, José, Guimarães, Isabel, Meneses, Carlos
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.05.2017
• Subjects: Case-Control Studies; Continuous speech; Databases, Factual; Diagnosis, Computer-Assisted - methods; Edema - classification; Edema - diagnosis; Edema - pathology; Edema - physiopathology; Female; Hierarchical classification; Humans; Larynx pathology identification; Male; Otolaryngology; Pathologic voice identification; Pattern Recognition, Automated; Predictive Value of Tests; Signal Processing, Computer-Assisted; Speech Acoustics; Speech Production Measurement - methods; Support Vector Machine; Sustained vowel; Vocal Cord Paralysis - classification; Vocal Cord Paralysis - diagnosis; Vocal Cord Paralysis - pathology; Vocal Cord Paralysis - physiopathology; Vocal Cords - pathology; Vocal Cords - physiopathology; Voice Disorders - classification; Voice Disorders - diagnosis; Voice Disorders - pathology; Voice Disorders - physiopathology; Voice Quality; Sustained vowel; Continuous speech; Hierarchical classification; Pathologic voice identification; Larynx pathology identification
• ISSN: 0892-1997; 1873-4588
• DOI: 10.1016/j.jvoice.2016.09.003

Speech signal processing techniques have provided several contributions to pathologic voice identification, in which healthy and unhealthy voice samples are evaluated. A less common approach is to identify laryngeal pathologies, for which the use of a noninvasive method for pathologic voice identification is an important step forward for preliminary diagnosis. In this study, a hierarchical classifier and a combination of systems are used to improve the accuracy of a three-class identification system (healthy, physiological larynx pathologies, and neuromuscular larynx pathologies). Three main subject classes were considered: subjects with physiological larynx pathologies (vocal fold nodules and edemas: 59 samples), subjects with neuromuscular larynx pathologies (unilateral vocal fold paralysis: 59 samples), and healthy subjects (36 samples). The variables used in this study were a speech task (sustained vowel /a/ or continuous reading speech), features with or without perceptual information, and features with or without direct information about formants evaluated using single classifiers. A hierarchical classification system was designed based on this information. The resulting system combines an analysis of continuous speech by way of the commonly used sustained vowel /a/ to obtain spectral and perceptual speech features. It achieved an accuracy of 84.4%, which represents an improvement of approximately 9% compared with the stand-alone approach. For pathologic voice identification, the accuracy obtained was 98.7%, and the identification accuracy for the two pathology classes was 81.3%. Hierarchical classification and system combination create significant benefits and introduce a modular approach to the classification of larynx pathologies.