Classification of normal and pathological voices using TEO phase and Mel cepstral features

Hemant A. Patil; Pallavi N. Baljekar

doi:10.1109/SPCOM.2012.6289991

Classification of normal and pathological voices using TEO phase and Mel cepstral features

Hemant A. Patil, Pallavi N. Baljekar

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

9 Citations (Scopus)

Abstract

In this paper, a new feature-set, viz., Teager Energy Operator (TEO) phase has been proposed for automatic classification of normal vs. pathological voices. Development of TEO phase has been motivated from recently proposed linear prediction (LP) residual phase for speaker recognition. Classification was performed using a discriminatively-trained 2 ^nd order polynomial classifier on a subset of the Massachusetts Ear and Eye Infirmary (MEEI) database. Score-level fusion of TEO phase and state-of-the-art Mel frequency cepstral coefficients (MFCC) gave reduction in equal error rate (EER) by 1.86 % than EER of MFCC alone. Proposed TEO phase feature set is also evaluated under degraded conditions using the NOISEX-92 database for the case of additive car noise.

Original language	English
Title of host publication	2012 International Conference on Signal Processing and Communications, SPCOM 2012
DOIs	https://doi.org/10.1109/SPCOM.2012.6289991
Publication status	Published - 26-10-2012
Externally published	Yes
Event	2012 9th International Conference on Signal Processing and Communications, SPCOM 2012 - Bangalore, India Duration: 22-07-2012 → 25-07-2012

Conference

Conference	2012 9th International Conference on Signal Processing and Communications, SPCOM 2012
Country/Territory	India
City	Bangalore
Period	22-07-12 → 25-07-12

All Science Journal Classification (ASJC) codes

Signal Processing
Communication

Access to Document

10.1109/SPCOM.2012.6289991

Cite this

@inproceedings{ddae02c3abee4b71a618a22360dc3f57,

title = "Classification of normal and pathological voices using TEO phase and Mel cepstral features",

abstract = "In this paper, a new feature-set, viz., Teager Energy Operator (TEO) phase has been proposed for automatic classification of normal vs. pathological voices. Development of TEO phase has been motivated from recently proposed linear prediction (LP) residual phase for speaker recognition. Classification was performed using a discriminatively-trained 2 nd order polynomial classifier on a subset of the Massachusetts Ear and Eye Infirmary (MEEI) database. Score-level fusion of TEO phase and state-of-the-art Mel frequency cepstral coefficients (MFCC) gave reduction in equal error rate (EER) by 1.86 % than EER of MFCC alone. Proposed TEO phase feature set is also evaluated under degraded conditions using the NOISEX-92 database for the case of additive car noise.",

author = "Patil, {Hemant A.} and Baljekar, {Pallavi N.}",

year = "2012",

month = oct,

day = "26",

doi = "10.1109/SPCOM.2012.6289991",

language = "English",

isbn = "9781467320122",

booktitle = "2012 International Conference on Signal Processing and Communications, SPCOM 2012",

note = "2012 9th International Conference on Signal Processing and Communications, SPCOM 2012 ; Conference date: 22-07-2012 Through 25-07-2012",

}

Patil, HA & Baljekar, PN 2012, Classification of normal and pathological voices using TEO phase and Mel cepstral features. in 2012 International Conference on Signal Processing and Communications, SPCOM 2012., 6289991, 2012 9th International Conference on Signal Processing and Communications, SPCOM 2012, Bangalore, India, 22-07-12. https://doi.org/10.1109/SPCOM.2012.6289991

TY - GEN

T1 - Classification of normal and pathological voices using TEO phase and Mel cepstral features

AU - Patil, Hemant A.

AU - Baljekar, Pallavi N.

PY - 2012/10/26

Y1 - 2012/10/26

N2 - In this paper, a new feature-set, viz., Teager Energy Operator (TEO) phase has been proposed for automatic classification of normal vs. pathological voices. Development of TEO phase has been motivated from recently proposed linear prediction (LP) residual phase for speaker recognition. Classification was performed using a discriminatively-trained 2 nd order polynomial classifier on a subset of the Massachusetts Ear and Eye Infirmary (MEEI) database. Score-level fusion of TEO phase and state-of-the-art Mel frequency cepstral coefficients (MFCC) gave reduction in equal error rate (EER) by 1.86 % than EER of MFCC alone. Proposed TEO phase feature set is also evaluated under degraded conditions using the NOISEX-92 database for the case of additive car noise.

AB - In this paper, a new feature-set, viz., Teager Energy Operator (TEO) phase has been proposed for automatic classification of normal vs. pathological voices. Development of TEO phase has been motivated from recently proposed linear prediction (LP) residual phase for speaker recognition. Classification was performed using a discriminatively-trained 2 nd order polynomial classifier on a subset of the Massachusetts Ear and Eye Infirmary (MEEI) database. Score-level fusion of TEO phase and state-of-the-art Mel frequency cepstral coefficients (MFCC) gave reduction in equal error rate (EER) by 1.86 % than EER of MFCC alone. Proposed TEO phase feature set is also evaluated under degraded conditions using the NOISEX-92 database for the case of additive car noise.

UR - http://www.scopus.com/inward/record.url?scp=84867736577&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867736577&partnerID=8YFLogxK

U2 - 10.1109/SPCOM.2012.6289991

DO - 10.1109/SPCOM.2012.6289991

M3 - Conference contribution

AN - SCOPUS:84867736577

SN - 9781467320122

BT - 2012 International Conference on Signal Processing and Communications, SPCOM 2012

T2 - 2012 9th International Conference on Signal Processing and Communications, SPCOM 2012

Y2 - 22 July 2012 through 25 July 2012

ER -

Classification of normal and pathological voices using TEO phase and Mel cepstral features

Abstract

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this