Automatic voice pathology detection and classification using vocal tract area irregularity

Ghulam Muhammad, Ghadir Altuwaijri, Mansour Alsulaiman, Zulfiqar Ali, Tamer A. Mesallam, Mohamed Farahat, Khalid H. Malki, Ahmed Al-Nasheri

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

In this paper, an automatic voice pathology detection (VPD) system based on voice production theory is developed. More specifically, features are extracted from vocal tract area, which is connected to the glottis. Voice pathology is related to a vocal fold problem, and hence the vocal tract area which is connected to vocal folds or glottis should exhibit irregular patterns over frames in case of a sustained vowel for a pathological voice. This irregular pattern is quantified in the form of different moments across the frames to distinguish between normal and pathological voices. The proposed VPD system is evaluated on the Massachusetts Eye and Ear Infirmary (MEEI) database and Saarbrucken Voice Database (SVD) with sustained vowel samples. Vocal tract irregularity features and support vector machine classifier are used in the proposed system. The proposed system achieves 99.22% ± 0.01 accuracy on the MEEI database and 94.7% ± 0.21 accuracy on the SVD. The results indicate that vocal tract irregularity measures can be used effectively in automatic voice pathology detection.

LanguageEnglish
Pages309-317
Number of pages9
JournalBiocybernetics and Biomedical Engineering
Volume36
Issue number2
Early online date28 Jan 2016
Publication statusPublished - 31 Jan 2016

Fingerprint

Pathology
Support vector machines
Classifiers

Keywords

  • Support vector machine
  • Vocal tract area
  • Voice disorders
  • Voice pathology detection

Cite this

Muhammad, G., Altuwaijri, G., Alsulaiman, M., Ali, Z., Mesallam, T. A., Farahat, M., ... Al-Nasheri, A. (2016). Automatic voice pathology detection and classification using vocal tract area irregularity. Biocybernetics and Biomedical Engineering, 36(2), 309-317.
Muhammad, Ghulam ; Altuwaijri, Ghadir ; Alsulaiman, Mansour ; Ali, Zulfiqar ; Mesallam, Tamer A. ; Farahat, Mohamed ; Malki, Khalid H. ; Al-Nasheri, Ahmed. / Automatic voice pathology detection and classification using vocal tract area irregularity. In: Biocybernetics and Biomedical Engineering. 2016 ; Vol. 36, No. 2. pp. 309-317.
@article{5f87d459cee3465ba6c26fb259671db0,
title = "Automatic voice pathology detection and classification using vocal tract area irregularity",
abstract = "In this paper, an automatic voice pathology detection (VPD) system based on voice production theory is developed. More specifically, features are extracted from vocal tract area, which is connected to the glottis. Voice pathology is related to a vocal fold problem, and hence the vocal tract area which is connected to vocal folds or glottis should exhibit irregular patterns over frames in case of a sustained vowel for a pathological voice. This irregular pattern is quantified in the form of different moments across the frames to distinguish between normal and pathological voices. The proposed VPD system is evaluated on the Massachusetts Eye and Ear Infirmary (MEEI) database and Saarbrucken Voice Database (SVD) with sustained vowel samples. Vocal tract irregularity features and support vector machine classifier are used in the proposed system. The proposed system achieves 99.22{\%} ± 0.01 accuracy on the MEEI database and 94.7{\%} ± 0.21 accuracy on the SVD. The results indicate that vocal tract irregularity measures can be used effectively in automatic voice pathology detection.",
keywords = "Support vector machine, Vocal tract area, Voice disorders, Voice pathology detection",
author = "Ghulam Muhammad and Ghadir Altuwaijri and Mansour Alsulaiman and Zulfiqar Ali and Mesallam, {Tamer A.} and Mohamed Farahat and Malki, {Khalid H.} and Ahmed Al-Nasheri",
year = "2016",
month = "1",
day = "31",
language = "English",
volume = "36",
pages = "309--317",
journal = "Biocybernetics and Biomedical Engineering",
issn = "0208-5216",
publisher = "Elsevier",
number = "2",

}

Muhammad, G, Altuwaijri, G, Alsulaiman, M, Ali, Z, Mesallam, TA, Farahat, M, Malki, KH & Al-Nasheri, A 2016, 'Automatic voice pathology detection and classification using vocal tract area irregularity', Biocybernetics and Biomedical Engineering, vol. 36, no. 2, pp. 309-317.

Automatic voice pathology detection and classification using vocal tract area irregularity. / Muhammad, Ghulam; Altuwaijri, Ghadir; Alsulaiman, Mansour; Ali, Zulfiqar; Mesallam, Tamer A.; Farahat, Mohamed; Malki, Khalid H.; Al-Nasheri, Ahmed.

In: Biocybernetics and Biomedical Engineering, Vol. 36, No. 2, 31.01.2016, p. 309-317.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic voice pathology detection and classification using vocal tract area irregularity

AU - Muhammad, Ghulam

AU - Altuwaijri, Ghadir

AU - Alsulaiman, Mansour

AU - Ali, Zulfiqar

AU - Mesallam, Tamer A.

AU - Farahat, Mohamed

AU - Malki, Khalid H.

AU - Al-Nasheri, Ahmed

PY - 2016/1/31

Y1 - 2016/1/31

N2 - In this paper, an automatic voice pathology detection (VPD) system based on voice production theory is developed. More specifically, features are extracted from vocal tract area, which is connected to the glottis. Voice pathology is related to a vocal fold problem, and hence the vocal tract area which is connected to vocal folds or glottis should exhibit irregular patterns over frames in case of a sustained vowel for a pathological voice. This irregular pattern is quantified in the form of different moments across the frames to distinguish between normal and pathological voices. The proposed VPD system is evaluated on the Massachusetts Eye and Ear Infirmary (MEEI) database and Saarbrucken Voice Database (SVD) with sustained vowel samples. Vocal tract irregularity features and support vector machine classifier are used in the proposed system. The proposed system achieves 99.22% ± 0.01 accuracy on the MEEI database and 94.7% ± 0.21 accuracy on the SVD. The results indicate that vocal tract irregularity measures can be used effectively in automatic voice pathology detection.

AB - In this paper, an automatic voice pathology detection (VPD) system based on voice production theory is developed. More specifically, features are extracted from vocal tract area, which is connected to the glottis. Voice pathology is related to a vocal fold problem, and hence the vocal tract area which is connected to vocal folds or glottis should exhibit irregular patterns over frames in case of a sustained vowel for a pathological voice. This irregular pattern is quantified in the form of different moments across the frames to distinguish between normal and pathological voices. The proposed VPD system is evaluated on the Massachusetts Eye and Ear Infirmary (MEEI) database and Saarbrucken Voice Database (SVD) with sustained vowel samples. Vocal tract irregularity features and support vector machine classifier are used in the proposed system. The proposed system achieves 99.22% ± 0.01 accuracy on the MEEI database and 94.7% ± 0.21 accuracy on the SVD. The results indicate that vocal tract irregularity measures can be used effectively in automatic voice pathology detection.

KW - Support vector machine

KW - Vocal tract area

KW - Voice disorders

KW - Voice pathology detection

UR - http://www.scopus.com/inward/record.url?scp=84964720139&partnerID=8YFLogxK

M3 - Article

VL - 36

SP - 309

EP - 317

JO - Biocybernetics and Biomedical Engineering

T2 - Biocybernetics and Biomedical Engineering

JF - Biocybernetics and Biomedical Engineering

SN - 0208-5216

IS - 2

ER -

Muhammad G, Altuwaijri G, Alsulaiman M, Ali Z, Mesallam TA, Farahat M et al. Automatic voice pathology detection and classification using vocal tract area irregularity. Biocybernetics and Biomedical Engineering. 2016 Jan 31;36(2):309-317.