Please use this identifier to cite or link to this item:
Title: Impact of noise on the performance of automatic systems for vocal fold lesions detection
Authors: Madruga Escalona, Mario
Campos Roca, Yolanda
Pérez Sánchez, Carlos Javier
Keywords: Reinke’s edema;Voice disorders;Noise robustness;Acoustic features;Computer aided diagnosis;Nodules;Características acústicas;Diagnóstico asistido por computadora;Edema de Reinke;Nódulos;Robustez de ruido;Trastornos de la voz
Issue Date: 2021
Publisher: Elsevier
Abstract: Automatic voice condition analysis systems have been developed to automatically discriminate pathological voices from healthy ones in the context of two disorders related to exudative lesions of Reinke’s space: nodules and Reinke’s edema. The systems are based on acoustic features, extracted from sustained vowel recordings. Reduced subsets of features have been obtained from a larger set by a feature selection algorithm based on Whale Optimization in combination with Support Vector Machine classification. Robustness of the proposed systems is assessed by adding noise of two different types (synthetic white noise and actual noise recorded in a clinical environment) to corrupt the speech signals. Two speech databases were used for this investigation: the Massachusetts Eye and Ear Infirmary (MEEI) database and a second one specifically collected in Hospital San Pedro de Alcántara (Cáceres, Spain) for the scope of this work (UEX-Voice database). The results show that the prediction performance of the detection systems appreciably decrease when moving from MEEI to a database recorded in more realistic conditions. For both pathologies, the prediction performance declines under noisy conditions, being the effect of white noise more pronounced than the effect of noise recorded in the clinical environment.
DOI: 10.1016/j.bbe.2021.07.001
Appears in Collections:DMATE - Artículos
DTCYC - Artículos

Files in This Item:
File Description SizeFormat 
10.1016j.bbe.2021.07.001.pdf1,77 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons