Vocal fold disorder detection based on continuous speech by using MFCC and GMM

Zulfiqar Ali, Mansour Alsulaiman, Ghulam Muhammad, Irraivan Elamvazuthi, Tamer A. Mesallam

Research output: Contribution to conferencePaper

15 Citations (Scopus)

Abstract

Vocal fold voice disorder detection with a sustained vowel is well investigated by research community during recent years. The detection of voice disorder with a sustained vowel is a comparatively easier task than detection with continuous speech. The speech signal remains stationary in case of sustained vowel but it varies over time in continuous time. This is the reason; voice detection by using continuous speech is challenging and demands more investigation. Moreover, detection with continuous speech is more realistic because people use it in their daily conversation but sustained vowel is not used in everyday talks. An accurate voice assessment can provide unique and complementary information for the diagnosis, and can be used in the treatment plan. In this paper, vocal fold disorders, cyst, polyp, nodules, paralysis, and sulcus, are detected using continuous speech. Mel-frequency cepstral coefficients (MFCC) are used with Gaussian mixture model (GMM) to build an automatic detection system capable of differentiating normal and pathological voices. The detection rate of the developed detection system with continuous speech is 91.66%.

LanguageEnglish
Pages292-297
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2013
Event2013 7th IEEE GCC Conference and Exhibition, GCC 2013 - Doha, Qatar
Duration: 17 Nov 201320 Nov 2013

Conference

Conference2013 7th IEEE GCC Conference and Exhibition, GCC 2013
CountryQatar
CityDoha
Period17/11/1320/11/13

Keywords

  • continuous speech
  • GMM
  • MFCC
  • pathology detection
  • Voice disorder

Cite this

Ali, Z., Alsulaiman, M., Muhammad, G., Elamvazuthi, I., & Mesallam, T. A. (2013). Vocal fold disorder detection based on continuous speech by using MFCC and GMM. 292-297. Paper presented at 2013 7th IEEE GCC Conference and Exhibition, GCC 2013, Doha, Qatar. https://doi.org/10.1109/IEEEGCC.2013.6705792
Ali, Zulfiqar ; Alsulaiman, Mansour ; Muhammad, Ghulam ; Elamvazuthi, Irraivan ; Mesallam, Tamer A. / Vocal fold disorder detection based on continuous speech by using MFCC and GMM. Paper presented at 2013 7th IEEE GCC Conference and Exhibition, GCC 2013, Doha, Qatar.6 p.
@conference{163a60e6ff9f4078b0cebc88b54b6313,
title = "Vocal fold disorder detection based on continuous speech by using MFCC and GMM",
abstract = "Vocal fold voice disorder detection with a sustained vowel is well investigated by research community during recent years. The detection of voice disorder with a sustained vowel is a comparatively easier task than detection with continuous speech. The speech signal remains stationary in case of sustained vowel but it varies over time in continuous time. This is the reason; voice detection by using continuous speech is challenging and demands more investigation. Moreover, detection with continuous speech is more realistic because people use it in their daily conversation but sustained vowel is not used in everyday talks. An accurate voice assessment can provide unique and complementary information for the diagnosis, and can be used in the treatment plan. In this paper, vocal fold disorders, cyst, polyp, nodules, paralysis, and sulcus, are detected using continuous speech. Mel-frequency cepstral coefficients (MFCC) are used with Gaussian mixture model (GMM) to build an automatic detection system capable of differentiating normal and pathological voices. The detection rate of the developed detection system with continuous speech is 91.66{\%}.",
keywords = "continuous speech, GMM, MFCC, pathology detection, Voice disorder",
author = "Zulfiqar Ali and Mansour Alsulaiman and Ghulam Muhammad and Irraivan Elamvazuthi and Mesallam, {Tamer A.}",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/IEEEGCC.2013.6705792",
language = "English",
pages = "292--297",
note = "2013 7th IEEE GCC Conference and Exhibition, GCC 2013 ; Conference date: 17-11-2013 Through 20-11-2013",

}

Ali, Z, Alsulaiman, M, Muhammad, G, Elamvazuthi, I & Mesallam, TA 2013, 'Vocal fold disorder detection based on continuous speech by using MFCC and GMM' Paper presented at 2013 7th IEEE GCC Conference and Exhibition, GCC 2013, Doha, Qatar, 17/11/13 - 20/11/13, pp. 292-297. https://doi.org/10.1109/IEEEGCC.2013.6705792

Vocal fold disorder detection based on continuous speech by using MFCC and GMM. / Ali, Zulfiqar; Alsulaiman, Mansour; Muhammad, Ghulam; Elamvazuthi, Irraivan; Mesallam, Tamer A.

2013. 292-297 Paper presented at 2013 7th IEEE GCC Conference and Exhibition, GCC 2013, Doha, Qatar.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Vocal fold disorder detection based on continuous speech by using MFCC and GMM

AU - Ali, Zulfiqar

AU - Alsulaiman, Mansour

AU - Muhammad, Ghulam

AU - Elamvazuthi, Irraivan

AU - Mesallam, Tamer A.

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Vocal fold voice disorder detection with a sustained vowel is well investigated by research community during recent years. The detection of voice disorder with a sustained vowel is a comparatively easier task than detection with continuous speech. The speech signal remains stationary in case of sustained vowel but it varies over time in continuous time. This is the reason; voice detection by using continuous speech is challenging and demands more investigation. Moreover, detection with continuous speech is more realistic because people use it in their daily conversation but sustained vowel is not used in everyday talks. An accurate voice assessment can provide unique and complementary information for the diagnosis, and can be used in the treatment plan. In this paper, vocal fold disorders, cyst, polyp, nodules, paralysis, and sulcus, are detected using continuous speech. Mel-frequency cepstral coefficients (MFCC) are used with Gaussian mixture model (GMM) to build an automatic detection system capable of differentiating normal and pathological voices. The detection rate of the developed detection system with continuous speech is 91.66%.

AB - Vocal fold voice disorder detection with a sustained vowel is well investigated by research community during recent years. The detection of voice disorder with a sustained vowel is a comparatively easier task than detection with continuous speech. The speech signal remains stationary in case of sustained vowel but it varies over time in continuous time. This is the reason; voice detection by using continuous speech is challenging and demands more investigation. Moreover, detection with continuous speech is more realistic because people use it in their daily conversation but sustained vowel is not used in everyday talks. An accurate voice assessment can provide unique and complementary information for the diagnosis, and can be used in the treatment plan. In this paper, vocal fold disorders, cyst, polyp, nodules, paralysis, and sulcus, are detected using continuous speech. Mel-frequency cepstral coefficients (MFCC) are used with Gaussian mixture model (GMM) to build an automatic detection system capable of differentiating normal and pathological voices. The detection rate of the developed detection system with continuous speech is 91.66%.

KW - continuous speech

KW - GMM

KW - MFCC

KW - pathology detection

KW - Voice disorder

UR - http://www.scopus.com/inward/record.url?scp=84893540587&partnerID=8YFLogxK

U2 - 10.1109/IEEEGCC.2013.6705792

DO - 10.1109/IEEEGCC.2013.6705792

M3 - Paper

SP - 292

EP - 297

ER -

Ali Z, Alsulaiman M, Muhammad G, Elamvazuthi I, Mesallam TA. Vocal fold disorder detection based on continuous speech by using MFCC and GMM. 2013. Paper presented at 2013 7th IEEE GCC Conference and Exhibition, GCC 2013, Doha, Qatar. https://doi.org/10.1109/IEEEGCC.2013.6705792