Pathological voice classification based on multi-domain features and deep hierarchical extreme learning machine
The Journal of the Acoustical Society of America · 01.01.2023 · 153 (1) · 423-435
DOI: 10.1121/10.0016869 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 19.01.2023. Verfasst von Junlang Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Southwest Jiaotong University, Chengdu, 610031, China. Hauptthemen laut MEDLINE: Deep Learning, Voice, Voice Disorders. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Sichuan Province Science and Technology Support Program.
Abstract (Originalsprache)
The intelligent data-driven screening of pathological voice signals is a non-invasive and real-time tool for computer-aided diagnosis that has attracted increasing attention from researchers and clinicians. In this paper, the authors propose multi-domain features and the hierarchical extreme learning machine (H-ELM) for the automatic identification of voice disorders. A sufficient number of sensitive features are first extracted from the original voice signal through multi-domain feature extraction (i.e., features of the time domain and the sample entropy based on ensemble empirical mode decomposition and gammatone frequency cepstral coefficients). To eliminate redundancy in high-dimensional features, neighborhood component analysis is then applied to filter out sensitive features from the high-dimensional feature vectors to improve the efficiency of network training and reduce overfitting. The sensitive features thus obtained are then used to train the H-ELM for pathological voice classification. The results of the experiments showed that the sensitivity, specificity, F1 score, and accuracy of the H-ELM were 99.37%, 98.61%, 99.37%, and 98.99%, respectively. Therefore, the proposed method is feasible for the initial classification of pathological voice signals.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Mechanical Engineering, Southwest Jiaotong University, Chengdu, 610031, China.
Förderung
- Sichuan Province Science and Technology Support Program
Zitieren
APA
Wang, J., Xu, H., Peng, X., Liu, J., & He, C. (2023). Pathological voice classification based on multi-domain features and deep hierarchical extreme learning machine. The Journal of the Acoustical Society of America, 153(1), 423-435. https://doi.org/10.1121/10.0016869
Vancouver
Wang J, Xu H, Peng X, Liu J, He C. Pathological voice classification based on multi-domain features and deep hierarchical extreme learning machine. The Journal of the Acoustical Society of America. 2023;153(1):423-435. doi:10.1121/10.0016869
BibTeX
@article{Wang2023,
author = {Wang, Junlang and Xu, Huoyao and Peng, Xiangyu and Liu, Jie and He, Chaoming},
title = {Pathological voice classification based on multi-domain features and deep hierarchical extreme learning machine},
journal = {The Journal of the Acoustical Society of America},
year = {2023},
volume = {153},
number = {1},
pages = {423--435},
doi = {10.1121/10.0016869}
}
EUVIMED