A comparison of waveform fractal dimension techniques for voice pathology classification

Pallavi N. Baljekar, Hemant A. Patil

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

In this paper, an attempt is made to compare and analyze the various waveform fractal dimension techniques for voice pathology classification. Three methods of estimating the fractal dimension directly from the time-domain waveform have been compared. The methods used are Katz algorithm, Higuchi algorithm and the Hurst exponent calculated using the rescaled range (R/S) analysis. Furthermore, the effects of the window size, the base waveform used and score-level fusion with Mel frequency cepstral coefficients (MFCC) has also been evaluated. The features have been extracted from two different base waveforms, the speech signal and the Teager energy operator (TEO) phase of the speech signal. Experiments have been carried out on a subset of the Massachusetts Eye and Ear Infirmary (MEEI) database and classifier used is a 2 nd order polynomial classifier. A classification accuracy of 97.54 %was achieved on score-level fusion, an increase in performance by about 2 % as compared to MFCC alone.

Original languageEnglish
Title of host publication2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
Pages4461-4464
Number of pages4
DOIs
Publication statusPublished - 23-10-2012
Externally publishedYes
Event2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Kyoto, Japan
Duration: 25-03-201230-03-2012

Conference

Conference2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
CountryJapan
CityKyoto
Period25-03-1230-03-12

Fingerprint

Pathology
Fractal dimension
Classifiers
Fusion reactions
Polynomials
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Baljekar, P. N., & Patil, H. A. (2012). A comparison of waveform fractal dimension techniques for voice pathology classification. In 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings (pp. 4461-4464). [6288910] https://doi.org/10.1109/ICASSP.2012.6288910
Baljekar, Pallavi N. ; Patil, Hemant A. / A comparison of waveform fractal dimension techniques for voice pathology classification. 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings. 2012. pp. 4461-4464
@inproceedings{1436b27ffe98436ab87d3505ffddcef5,
title = "A comparison of waveform fractal dimension techniques for voice pathology classification",
abstract = "In this paper, an attempt is made to compare and analyze the various waveform fractal dimension techniques for voice pathology classification. Three methods of estimating the fractal dimension directly from the time-domain waveform have been compared. The methods used are Katz algorithm, Higuchi algorithm and the Hurst exponent calculated using the rescaled range (R/S) analysis. Furthermore, the effects of the window size, the base waveform used and score-level fusion with Mel frequency cepstral coefficients (MFCC) has also been evaluated. The features have been extracted from two different base waveforms, the speech signal and the Teager energy operator (TEO) phase of the speech signal. Experiments have been carried out on a subset of the Massachusetts Eye and Ear Infirmary (MEEI) database and classifier used is a 2 nd order polynomial classifier. A classification accuracy of 97.54 {\%}was achieved on score-level fusion, an increase in performance by about 2 {\%} as compared to MFCC alone.",
author = "Baljekar, {Pallavi N.} and Patil, {Hemant A.}",
year = "2012",
month = "10",
day = "23",
doi = "10.1109/ICASSP.2012.6288910",
language = "English",
isbn = "9781467300469",
pages = "4461--4464",
booktitle = "2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings",

}

Baljekar, PN & Patil, HA 2012, A comparison of waveform fractal dimension techniques for voice pathology classification. in 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings., 6288910, pp. 4461-4464, 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012, Kyoto, Japan, 25-03-12. https://doi.org/10.1109/ICASSP.2012.6288910

A comparison of waveform fractal dimension techniques for voice pathology classification. / Baljekar, Pallavi N.; Patil, Hemant A.

2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings. 2012. p. 4461-4464 6288910.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A comparison of waveform fractal dimension techniques for voice pathology classification

AU - Baljekar, Pallavi N.

AU - Patil, Hemant A.

PY - 2012/10/23

Y1 - 2012/10/23

N2 - In this paper, an attempt is made to compare and analyze the various waveform fractal dimension techniques for voice pathology classification. Three methods of estimating the fractal dimension directly from the time-domain waveform have been compared. The methods used are Katz algorithm, Higuchi algorithm and the Hurst exponent calculated using the rescaled range (R/S) analysis. Furthermore, the effects of the window size, the base waveform used and score-level fusion with Mel frequency cepstral coefficients (MFCC) has also been evaluated. The features have been extracted from two different base waveforms, the speech signal and the Teager energy operator (TEO) phase of the speech signal. Experiments have been carried out on a subset of the Massachusetts Eye and Ear Infirmary (MEEI) database and classifier used is a 2 nd order polynomial classifier. A classification accuracy of 97.54 %was achieved on score-level fusion, an increase in performance by about 2 % as compared to MFCC alone.

AB - In this paper, an attempt is made to compare and analyze the various waveform fractal dimension techniques for voice pathology classification. Three methods of estimating the fractal dimension directly from the time-domain waveform have been compared. The methods used are Katz algorithm, Higuchi algorithm and the Hurst exponent calculated using the rescaled range (R/S) analysis. Furthermore, the effects of the window size, the base waveform used and score-level fusion with Mel frequency cepstral coefficients (MFCC) has also been evaluated. The features have been extracted from two different base waveforms, the speech signal and the Teager energy operator (TEO) phase of the speech signal. Experiments have been carried out on a subset of the Massachusetts Eye and Ear Infirmary (MEEI) database and classifier used is a 2 nd order polynomial classifier. A classification accuracy of 97.54 %was achieved on score-level fusion, an increase in performance by about 2 % as compared to MFCC alone.

UR - http://www.scopus.com/inward/record.url?scp=84867598366&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867598366&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2012.6288910

DO - 10.1109/ICASSP.2012.6288910

M3 - Conference contribution

SN - 9781467300469

SP - 4461

EP - 4464

BT - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings

ER -

Baljekar PN, Patil HA. A comparison of waveform fractal dimension techniques for voice pathology classification. In 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings. 2012. p. 4461-4464. 6288910 https://doi.org/10.1109/ICASSP.2012.6288910