Novel temporal and spectral features derived from TEO for classification normal and dysphonic voices

Hemant A. Patil, Pallavi N. Baljekar, T. K. Basu

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

Abstract

In this paper, various temporal features (i.e., zero crossing rate and short-time energy) and spectral features (spectral flux and spectral centroid) have been derived from the Teager energy operator (TEO) profile of the speech waveform. The efficacy of these features has been analyzed for the classification of normal and dysphonic voices by comparing their performance with the features derived from the linear prediction (LP) residual and the speech waveform. In addition, the effectiveness of fusing these features with state-of-the-art Mel frequency cepstral coefficients (MFCC) feature-set has also been investigated to understand whether these features provide complementary results. The classifier that has been used is the 2nd order polynomial classifier, with experiments being carried out on a subset of the Massachusetts Eye and Ear Infirmary (MEEI) database.

Original languageEnglish
Title of host publicationFrontiers in Computer Education
Pages559-567
Number of pages9
DOIs
Publication statusPublished - 24-05-2012
Externally publishedYes
Event2011 International Conference on Frontiers in Computer Education, ICFCE 2011 - Macao, China
Duration: 01-12-201102-12-2011

Publication series

NameAdvances in Intelligent and Soft Computing
Volume133 AISC
ISSN (Print)1867-5662

Conference

Conference2011 International Conference on Frontiers in Computer Education, ICFCE 2011
CountryChina
CityMacao
Period01-12-1102-12-11

Fingerprint

Classifiers
Polynomials
Fluxes
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Patil, H. A., Baljekar, P. N., & Basu, T. K. (2012). Novel temporal and spectral features derived from TEO for classification normal and dysphonic voices. In Frontiers in Computer Education (pp. 559-567). (Advances in Intelligent and Soft Computing; Vol. 133 AISC). https://doi.org/10.1007/978-3-642-27552-4_76
Patil, Hemant A. ; Baljekar, Pallavi N. ; Basu, T. K. / Novel temporal and spectral features derived from TEO for classification normal and dysphonic voices. Frontiers in Computer Education. 2012. pp. 559-567 (Advances in Intelligent and Soft Computing).
@inproceedings{f580646e06d34fd694ddebb4ad44ed3a,
title = "Novel temporal and spectral features derived from TEO for classification normal and dysphonic voices",
abstract = "In this paper, various temporal features (i.e., zero crossing rate and short-time energy) and spectral features (spectral flux and spectral centroid) have been derived from the Teager energy operator (TEO) profile of the speech waveform. The efficacy of these features has been analyzed for the classification of normal and dysphonic voices by comparing their performance with the features derived from the linear prediction (LP) residual and the speech waveform. In addition, the effectiveness of fusing these features with state-of-the-art Mel frequency cepstral coefficients (MFCC) feature-set has also been investigated to understand whether these features provide complementary results. The classifier that has been used is the 2nd order polynomial classifier, with experiments being carried out on a subset of the Massachusetts Eye and Ear Infirmary (MEEI) database.",
author = "Patil, {Hemant A.} and Baljekar, {Pallavi N.} and Basu, {T. K.}",
year = "2012",
month = "5",
day = "24",
doi = "10.1007/978-3-642-27552-4_76",
language = "English",
isbn = "9783642275517",
series = "Advances in Intelligent and Soft Computing",
pages = "559--567",
booktitle = "Frontiers in Computer Education",

}

Patil, HA, Baljekar, PN & Basu, TK 2012, Novel temporal and spectral features derived from TEO for classification normal and dysphonic voices. in Frontiers in Computer Education. Advances in Intelligent and Soft Computing, vol. 133 AISC, pp. 559-567, 2011 International Conference on Frontiers in Computer Education, ICFCE 2011, Macao, China, 01-12-11. https://doi.org/10.1007/978-3-642-27552-4_76

Novel temporal and spectral features derived from TEO for classification normal and dysphonic voices. / Patil, Hemant A.; Baljekar, Pallavi N.; Basu, T. K.

Frontiers in Computer Education. 2012. p. 559-567 (Advances in Intelligent and Soft Computing; Vol. 133 AISC).

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

TY - GEN

T1 - Novel temporal and spectral features derived from TEO for classification normal and dysphonic voices

AU - Patil, Hemant A.

AU - Baljekar, Pallavi N.

AU - Basu, T. K.

PY - 2012/5/24

Y1 - 2012/5/24

N2 - In this paper, various temporal features (i.e., zero crossing rate and short-time energy) and spectral features (spectral flux and spectral centroid) have been derived from the Teager energy operator (TEO) profile of the speech waveform. The efficacy of these features has been analyzed for the classification of normal and dysphonic voices by comparing their performance with the features derived from the linear prediction (LP) residual and the speech waveform. In addition, the effectiveness of fusing these features with state-of-the-art Mel frequency cepstral coefficients (MFCC) feature-set has also been investigated to understand whether these features provide complementary results. The classifier that has been used is the 2nd order polynomial classifier, with experiments being carried out on a subset of the Massachusetts Eye and Ear Infirmary (MEEI) database.

AB - In this paper, various temporal features (i.e., zero crossing rate and short-time energy) and spectral features (spectral flux and spectral centroid) have been derived from the Teager energy operator (TEO) profile of the speech waveform. The efficacy of these features has been analyzed for the classification of normal and dysphonic voices by comparing their performance with the features derived from the linear prediction (LP) residual and the speech waveform. In addition, the effectiveness of fusing these features with state-of-the-art Mel frequency cepstral coefficients (MFCC) feature-set has also been investigated to understand whether these features provide complementary results. The classifier that has been used is the 2nd order polynomial classifier, with experiments being carried out on a subset of the Massachusetts Eye and Ear Infirmary (MEEI) database.

UR - http://www.scopus.com/inward/record.url?scp=84862081167&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862081167&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-27552-4_76

DO - 10.1007/978-3-642-27552-4_76

M3 - Conference contribution

SN - 9783642275517

T3 - Advances in Intelligent and Soft Computing

SP - 559

EP - 567

BT - Frontiers in Computer Education

ER -

Patil HA, Baljekar PN, Basu TK. Novel temporal and spectral features derived from TEO for classification normal and dysphonic voices. In Frontiers in Computer Education. 2012. p. 559-567. (Advances in Intelligent and Soft Computing). https://doi.org/10.1007/978-3-642-27552-4_76