Automatic voice disorder classification using vowel formants

Ghulam Muhammad, Mansour Alsulaiman, Awais Mahmood, Zulfiqar Ali

Research output: Contribution to conferencePaper

17 Citations (Scopus)

Abstract

In this paper, we propose an automatic voice disorder classification system using first two formants of vowels. Five types of voice disorder, namely, cyst, GERD, paralysis, polyp and sulcus, are used in the experiments. Spoken Arabic digits from the voice disordered people are recorded for input. First formant and second formant are extracted from the vowels [Fatha] and [Kasra], which are present in Arabic digits. These four features are then used to classify the voice disorder using two types of classification methods: vector quantization (VQ) and neural networks. In the experiments, neural network performs better than VQ. For female and male speakers, the classification rates are 67.86% and 52.5%, respectively, using neural networks. The best classification rate, which is 78.72%, is obtained for female sulcus disorder.

Conference

Conference2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011
CountrySpain
CityBarcelona
Period11/07/1115/07/11

Fingerprint

Vector quantization
Neural networks
Experiments

Keywords

  • Arabic digit
  • Arabic vowel
  • automatic classification of voice disorder
  • neural network

Cite this

Muhammad, G., Alsulaiman, M., Mahmood, A., & Ali, Z. (2011). Automatic voice disorder classification using vowel formants. 1-6. Paper presented at 2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011, Barcelona, Spain. https://doi.org/10.1109/ICME.2011.6012187
Muhammad, Ghulam ; Alsulaiman, Mansour ; Mahmood, Awais ; Ali, Zulfiqar. / Automatic voice disorder classification using vowel formants. Paper presented at 2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011, Barcelona, Spain.6 p.
@conference{3f3fdcc47705496884eed458747aa906,
title = "Automatic voice disorder classification using vowel formants",
abstract = "In this paper, we propose an automatic voice disorder classification system using first two formants of vowels. Five types of voice disorder, namely, cyst, GERD, paralysis, polyp and sulcus, are used in the experiments. Spoken Arabic digits from the voice disordered people are recorded for input. First formant and second formant are extracted from the vowels [Fatha] and [Kasra], which are present in Arabic digits. These four features are then used to classify the voice disorder using two types of classification methods: vector quantization (VQ) and neural networks. In the experiments, neural network performs better than VQ. For female and male speakers, the classification rates are 67.86{\%} and 52.5{\%}, respectively, using neural networks. The best classification rate, which is 78.72{\%}, is obtained for female sulcus disorder.",
keywords = "Arabic digit, Arabic vowel, automatic classification of voice disorder, neural network",
author = "Ghulam Muhammad and Mansour Alsulaiman and Awais Mahmood and Zulfiqar Ali",
year = "2011",
month = "11",
day = "7",
doi = "10.1109/ICME.2011.6012187",
language = "English",
pages = "1--6",
note = "2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011 ; Conference date: 11-07-2011 Through 15-07-2011",

}

Muhammad, G, Alsulaiman, M, Mahmood, A & Ali, Z 2011, 'Automatic voice disorder classification using vowel formants' Paper presented at 2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011, Barcelona, Spain, 11/07/11 - 15/07/11, pp. 1-6. https://doi.org/10.1109/ICME.2011.6012187

Automatic voice disorder classification using vowel formants. / Muhammad, Ghulam; Alsulaiman, Mansour; Mahmood, Awais; Ali, Zulfiqar.

2011. 1-6 Paper presented at 2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011, Barcelona, Spain.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Automatic voice disorder classification using vowel formants

AU - Muhammad, Ghulam

AU - Alsulaiman, Mansour

AU - Mahmood, Awais

AU - Ali, Zulfiqar

PY - 2011/11/7

Y1 - 2011/11/7

N2 - In this paper, we propose an automatic voice disorder classification system using first two formants of vowels. Five types of voice disorder, namely, cyst, GERD, paralysis, polyp and sulcus, are used in the experiments. Spoken Arabic digits from the voice disordered people are recorded for input. First formant and second formant are extracted from the vowels [Fatha] and [Kasra], which are present in Arabic digits. These four features are then used to classify the voice disorder using two types of classification methods: vector quantization (VQ) and neural networks. In the experiments, neural network performs better than VQ. For female and male speakers, the classification rates are 67.86% and 52.5%, respectively, using neural networks. The best classification rate, which is 78.72%, is obtained for female sulcus disorder.

AB - In this paper, we propose an automatic voice disorder classification system using first two formants of vowels. Five types of voice disorder, namely, cyst, GERD, paralysis, polyp and sulcus, are used in the experiments. Spoken Arabic digits from the voice disordered people are recorded for input. First formant and second formant are extracted from the vowels [Fatha] and [Kasra], which are present in Arabic digits. These four features are then used to classify the voice disorder using two types of classification methods: vector quantization (VQ) and neural networks. In the experiments, neural network performs better than VQ. For female and male speakers, the classification rates are 67.86% and 52.5%, respectively, using neural networks. The best classification rate, which is 78.72%, is obtained for female sulcus disorder.

KW - Arabic digit

KW - Arabic vowel

KW - automatic classification of voice disorder

KW - neural network

UR - http://www.scopus.com/inward/record.url?scp=80155183981&partnerID=8YFLogxK

U2 - 10.1109/ICME.2011.6012187

DO - 10.1109/ICME.2011.6012187

M3 - Paper

SP - 1

EP - 6

ER -

Muhammad G, Alsulaiman M, Mahmood A, Ali Z. Automatic voice disorder classification using vowel formants. 2011. Paper presented at 2011 12th IEEE International Conference on Multimedia and Expo, ICME 2011, Barcelona, Spain. https://doi.org/10.1109/ICME.2011.6012187