Voice intensity based gender classification by using Simpson's rule with SVM

Mansour Alsulaiman, Zulfiqar Ali, Ghulam Muhammad

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

The proposed technique measures the voice intensity of an utterance by calculating area under the curve. The curve is obtained by normalizing the cubic polynomial fitted through the peaks. These peaks are found from each frame of the utterance when it is divided into segments of 20 milliseconds. The Simpson's rule is used to calculate area under the curve and SVM uses this area to classify the genders. The use of one dimensional feature, area of utterance, is an evidence for the time and computational efficiency of this technique. The aspects observed in this paper, for the validity of the technique, are: it works for different natural languages, independent of recording equipment, any text can be used for the classification, and its biasness when different number of male and female speakers are used for the training of the system. A promising classification rate of 98.27% is achieved.

Conference

Conference2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012
CountryAustria
CityVienna
Period11/04/1213/04/12

Fingerprint

Computational efficiency
Polynomials

Keywords

  • Area under the curve
  • Simpson's Rule
  • SVM
  • TIMIT
  • Voice Intensity

Cite this

Alsulaiman, M., Ali, Z., & Muhammad, G. (2012). Voice intensity based gender classification by using Simpson's rule with SVM. 552-555. Paper presented at 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012, Vienna, Austria.
Alsulaiman, Mansour ; Ali, Zulfiqar ; Muhammad, Ghulam. / Voice intensity based gender classification by using Simpson's rule with SVM. Paper presented at 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012, Vienna, Austria.4 p.
@conference{eb24da4561db41f3b4ca3ec6fa73100a,
title = "Voice intensity based gender classification by using Simpson's rule with SVM",
abstract = "The proposed technique measures the voice intensity of an utterance by calculating area under the curve. The curve is obtained by normalizing the cubic polynomial fitted through the peaks. These peaks are found from each frame of the utterance when it is divided into segments of 20 milliseconds. The Simpson's rule is used to calculate area under the curve and SVM uses this area to classify the genders. The use of one dimensional feature, area of utterance, is an evidence for the time and computational efficiency of this technique. The aspects observed in this paper, for the validity of the technique, are: it works for different natural languages, independent of recording equipment, any text can be used for the classification, and its biasness when different number of male and female speakers are used for the training of the system. A promising classification rate of 98.27{\%} is achieved.",
keywords = "Area under the curve, Simpson's Rule, SVM, TIMIT, Voice Intensity",
author = "Mansour Alsulaiman and Zulfiqar Ali and Ghulam Muhammad",
year = "2012",
month = "6",
day = "1",
language = "English",
pages = "552--555",
note = "2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012 ; Conference date: 11-04-2012 Through 13-04-2012",

}

Alsulaiman, M, Ali, Z & Muhammad, G 2012, 'Voice intensity based gender classification by using Simpson's rule with SVM' Paper presented at 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012, Vienna, Austria, 11/04/12 - 13/04/12, pp. 552-555.

Voice intensity based gender classification by using Simpson's rule with SVM. / Alsulaiman, Mansour; Ali, Zulfiqar; Muhammad, Ghulam.

2012. 552-555 Paper presented at 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012, Vienna, Austria.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Voice intensity based gender classification by using Simpson's rule with SVM

AU - Alsulaiman, Mansour

AU - Ali, Zulfiqar

AU - Muhammad, Ghulam

PY - 2012/6/1

Y1 - 2012/6/1

N2 - The proposed technique measures the voice intensity of an utterance by calculating area under the curve. The curve is obtained by normalizing the cubic polynomial fitted through the peaks. These peaks are found from each frame of the utterance when it is divided into segments of 20 milliseconds. The Simpson's rule is used to calculate area under the curve and SVM uses this area to classify the genders. The use of one dimensional feature, area of utterance, is an evidence for the time and computational efficiency of this technique. The aspects observed in this paper, for the validity of the technique, are: it works for different natural languages, independent of recording equipment, any text can be used for the classification, and its biasness when different number of male and female speakers are used for the training of the system. A promising classification rate of 98.27% is achieved.

AB - The proposed technique measures the voice intensity of an utterance by calculating area under the curve. The curve is obtained by normalizing the cubic polynomial fitted through the peaks. These peaks are found from each frame of the utterance when it is divided into segments of 20 milliseconds. The Simpson's rule is used to calculate area under the curve and SVM uses this area to classify the genders. The use of one dimensional feature, area of utterance, is an evidence for the time and computational efficiency of this technique. The aspects observed in this paper, for the validity of the technique, are: it works for different natural languages, independent of recording equipment, any text can be used for the classification, and its biasness when different number of male and female speakers are used for the training of the system. A promising classification rate of 98.27% is achieved.

KW - Area under the curve

KW - Simpson's Rule

KW - SVM

KW - TIMIT

KW - Voice Intensity

UR - http://www.scopus.com/inward/record.url?scp=84863967017&partnerID=8YFLogxK

M3 - Paper

SP - 552

EP - 555

ER -

Alsulaiman M, Ali Z, Muhammad G. Voice intensity based gender classification by using Simpson's rule with SVM. 2012. Paper presented at 2012 19th International Conference on Systems, Signals and Image Processing, IWSSIP 2012, Vienna, Austria.