Analysis of Vocal Disorders using Cobweb Clustering

Various methods have been researched with acoustic tests for diagnosing and evaluating voice disorder. The acoustic method of voice evaluation has been widely studied with the acoustic analyzer. However, it is necessary to visit a hospital equipped with an expensive acoustic analyzer. To solve this...

Full description

Saved in:
Bibliographic Details
Published in2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) pp. 120 - 123
Main Authors Lee, Keonsoo, Kim, Hyun-Woo, Moon, Chanki, Nam, Yunyoung
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.02.2019
Subjects
Acoustic measurements
Acoustics
Clustering
Clustering methods
Cobweb
HNR
Hospitals
Jitter
Shimmer
Vocal Disorder
Online AccessGet full text

Cover

More Information
Summary:Various methods have been researched with acoustic tests for diagnosing and evaluating voice disorder. The acoustic method of voice evaluation has been widely studied with the acoustic analyzer. However, it is necessary to visit a hospital equipped with an expensive acoustic analyzer. To solve this problem, we propose a smartphone-based acoustic analyzer. In this paper, three different acoustic indicators were measured, using Jitter, Shimmer, and NHR. Based on the acoustic indicators, experiments were conducted on healthy and unhealthy subjects to evaluate voice quality. The collected data set is clustered using cobweb clustering method. The risk of vocal disorders can be predicted by measuring the distance and direction between the centroids.
DOI:10.1109/ICAIIC.2019.8669011