Voice pathology detection with MDVP parameters using Arabic voice pathology database

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

Research output: Contribution to conferencePaper

5 Citations (Scopus)

Abstract

This paper investigates the use of MultiDimensional Voice Program (MDVP) parameters to automatically detect voice pathology in Arabic voice pathology database (AVPD). MDVP parameters are very popular among the physician / clinician to detect voice pathology; however, MDVP is a commercial software. AVPD is a newly developed speech database designed to suit a wide range of experiments in the field of automatic voice pathology detection, classification, and automatic speech recognition. This paper is the first step to evaluate MDVP parameters in AVPD using sustained vowel /a/. The experimental results demonstrate that some of the acoustic features show an excellent ability to discriminate between normal and pathological voices. The overall best accuracy is 81.33% by using SVM classifier.

Conference

Conference5th National Symposium on Information Technology: Towards New Smart World, NSITNSW 2015
CountrySaudi Arabia
CityRiyadh
Period17/02/1519/02/15

Fingerprint

Pathology
Speech recognition
Classifiers
Acoustics

Keywords

  • AVPD
  • MDVP
  • MEEI
  • SVM
  • voice pathology detection

Cite this

Al-Nasheri, A., Ali, Z., Muhammad, G., Alsulaiman, M., Almalki, K. H., Mesallam, T. A., & Farahat, M. (2015). Voice pathology detection with MDVP parameters using Arabic voice pathology database. 1-5. Paper presented at 5th National Symposium on Information Technology: Towards New Smart World, NSITNSW 2015, Riyadh, Saudi Arabia. https://doi.org/10.1109/NSITNSW.2015.7176431
Al-Nasheri, Ahmed ; Ali, Zulfiqar ; Muhammad, Ghulam ; Alsulaiman, Mansour ; Almalki, Khalid H. ; Mesallam, Tamer A. ; Farahat, Mohamed. / Voice pathology detection with MDVP parameters using Arabic voice pathology database. Paper presented at 5th National Symposium on Information Technology: Towards New Smart World, NSITNSW 2015, Riyadh, Saudi Arabia.5 p.
@conference{0cd0bd5fb0094a10b28f6a5158e4f394,
title = "Voice pathology detection with MDVP parameters using Arabic voice pathology database",
abstract = "This paper investigates the use of MultiDimensional Voice Program (MDVP) parameters to automatically detect voice pathology in Arabic voice pathology database (AVPD). MDVP parameters are very popular among the physician / clinician to detect voice pathology; however, MDVP is a commercial software. AVPD is a newly developed speech database designed to suit a wide range of experiments in the field of automatic voice pathology detection, classification, and automatic speech recognition. This paper is the first step to evaluate MDVP parameters in AVPD using sustained vowel /a/. The experimental results demonstrate that some of the acoustic features show an excellent ability to discriminate between normal and pathological voices. The overall best accuracy is 81.33{\%} by using SVM classifier.",
keywords = "AVPD, MDVP, MEEI, SVM, voice pathology detection",
author = "Ahmed Al-Nasheri and Zulfiqar Ali and Ghulam Muhammad and Mansour Alsulaiman and Almalki, {Khalid H.} and Mesallam, {Tamer A.} and Mohamed Farahat",
year = "2015",
month = "8",
day = "6",
doi = "10.1109/NSITNSW.2015.7176431",
language = "English",
pages = "1--5",
note = "5th National Symposium on Information Technology: Towards New Smart World, NSITNSW 2015 ; Conference date: 17-02-2015 Through 19-02-2015",

}

Al-Nasheri, A, Ali, Z, Muhammad, G, Alsulaiman, M, Almalki, KH, Mesallam, TA & Farahat, M 2015, 'Voice pathology detection with MDVP parameters using Arabic voice pathology database' Paper presented at 5th National Symposium on Information Technology: Towards New Smart World, NSITNSW 2015, Riyadh, Saudi Arabia, 17/02/15 - 19/02/15, pp. 1-5. https://doi.org/10.1109/NSITNSW.2015.7176431

Voice pathology detection with MDVP parameters using Arabic voice pathology database. / Al-Nasheri, Ahmed; Ali, Zulfiqar; Muhammad, Ghulam; Alsulaiman, Mansour; Almalki, Khalid H.; Mesallam, Tamer A.; Farahat, Mohamed.

2015. 1-5 Paper presented at 5th National Symposium on Information Technology: Towards New Smart World, NSITNSW 2015, Riyadh, Saudi Arabia.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Voice pathology detection with MDVP parameters using Arabic voice pathology database

AU - Al-Nasheri, Ahmed

AU - Ali, Zulfiqar

AU - Muhammad, Ghulam

AU - Alsulaiman, Mansour

AU - Almalki, Khalid H.

AU - Mesallam, Tamer A.

AU - Farahat, Mohamed

PY - 2015/8/6

Y1 - 2015/8/6

N2 - This paper investigates the use of MultiDimensional Voice Program (MDVP) parameters to automatically detect voice pathology in Arabic voice pathology database (AVPD). MDVP parameters are very popular among the physician / clinician to detect voice pathology; however, MDVP is a commercial software. AVPD is a newly developed speech database designed to suit a wide range of experiments in the field of automatic voice pathology detection, classification, and automatic speech recognition. This paper is the first step to evaluate MDVP parameters in AVPD using sustained vowel /a/. The experimental results demonstrate that some of the acoustic features show an excellent ability to discriminate between normal and pathological voices. The overall best accuracy is 81.33% by using SVM classifier.

AB - This paper investigates the use of MultiDimensional Voice Program (MDVP) parameters to automatically detect voice pathology in Arabic voice pathology database (AVPD). MDVP parameters are very popular among the physician / clinician to detect voice pathology; however, MDVP is a commercial software. AVPD is a newly developed speech database designed to suit a wide range of experiments in the field of automatic voice pathology detection, classification, and automatic speech recognition. This paper is the first step to evaluate MDVP parameters in AVPD using sustained vowel /a/. The experimental results demonstrate that some of the acoustic features show an excellent ability to discriminate between normal and pathological voices. The overall best accuracy is 81.33% by using SVM classifier.

KW - AVPD

KW - MDVP

KW - MEEI

KW - SVM

KW - voice pathology detection

UR - http://www.scopus.com/inward/record.url?scp=84964033974&partnerID=8YFLogxK

U2 - 10.1109/NSITNSW.2015.7176431

DO - 10.1109/NSITNSW.2015.7176431

M3 - Paper

SP - 1

EP - 5

ER -

Al-Nasheri A, Ali Z, Muhammad G, Alsulaiman M, Almalki KH, Mesallam TA et al. Voice pathology detection with MDVP parameters using Arabic voice pathology database. 2015. Paper presented at 5th National Symposium on Information Technology: Towards New Smart World, NSITNSW 2015, Riyadh, Saudi Arabia. https://doi.org/10.1109/NSITNSW.2015.7176431