Spectral envelope and periodic component in classification trees for pathological voice diagnostic

H. Cordeiro; J. Fonseca; C. Meneses

doi:10.1109/EMBC.2014.6944650

Spectral envelope and periodic component in classification trees for pathological voice diagnostic

H. Cordeiro, J. Fonseca, C. Meneses

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

10 Citations (Scopus)

Abstract

This work investigates the effectiveness of features from the spectral envelope such as the frequency and bandwidth of the first peak obtained from a 30^th order Linear Predictive Coefficients (LPC) to identify pathological voices. Other spectral features are also investigated and tested to improve the recognition rate. The value of the Relative Power of the Periodic Component is combined with spectral features, to diagnose pathological voices. Healthy voices and five vocal folds pathologies are tested. Decision Tree classifiers are used to evaluate which features have pathological voice information. Based on those results a simple Decision Tree was implemented and 94% of all the subjects in the database are correctly diagnosed.

Original language	English
Title of host publication	2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	4607-4610
Number of pages	4
ISBN (Electronic)	9781424479290
DOIs	https://doi.org/10.1109/EMBC.2014.6944650 https://doi.org/10.1109/EMBC.2014.6944650
Publication status	Published - 2 Nov 2014
Event	2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 - Chicago, United States Duration: 26 Aug 2014 → 30 Aug 2014

Conference

Conference	2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
Country	United States
City	Chicago
Period	26/08/14 → 30/08/14

Access to Document

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Spectral envelope and periodic component in classification trees for pathological voice diagnostic'. Together they form a unique fingerprint.

Cite this

Cordeiro, H., Fonseca, J., & Meneses, C. (2014). Spectral envelope and periodic component in classification trees for pathological voice diagnostic. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 (pp. 4607-4610). [6944650] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2014.6944650, https://doi.org/10.1109/EMBC.2014.6944650

@inproceedings{200121e8fe45405296ead3094c82c472,

title = "Spectral envelope and periodic component in classification trees for pathological voice diagnostic",

abstract = "This work investigates the effectiveness of features from the spectral envelope such as the frequency and bandwidth of the first peak obtained from a 30th order Linear Predictive Coefficients (LPC) to identify pathological voices. Other spectral features are also investigated and tested to improve the recognition rate. The value of the Relative Power of the Periodic Component is combined with spectral features, to diagnose pathological voices. Healthy voices and five vocal folds pathologies are tested. Decision Tree classifiers are used to evaluate which features have pathological voice information. Based on those results a simple Decision Tree was implemented and 94% of all the subjects in the database are correctly diagnosed.",

author = "H. Cordeiro and J. Fonseca and C. Meneses",

year = "2014",

month = nov,

day = "2",

doi = "10.1109/EMBC.2014.6944650",

language = "English",

pages = "4607--4610",

booktitle = "2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 ; Conference date: 26-08-2014 Through 30-08-2014",

}

Cordeiro, H, Fonseca, J & Meneses, C 2014, Spectral envelope and periodic component in classification trees for pathological voice diagnostic. in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014., 6944650, Institute of Electrical and Electronics Engineers Inc., pp. 4607-4610, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014, Chicago, United States, 26/08/14. https://doi.org/10.1109/EMBC.2014.6944650, https://doi.org/10.1109/EMBC.2014.6944650

Spectral envelope and periodic component in classification trees for pathological voice diagnostic. / Cordeiro, H.; Fonseca, J.; Meneses, C.

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 4607-4610 6944650.

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

TY - GEN

T1 - Spectral envelope and periodic component in classification trees for pathological voice diagnostic

AU - Cordeiro, H.

AU - Fonseca, J.

AU - Meneses, C.

PY - 2014/11/2

Y1 - 2014/11/2

N2 - This work investigates the effectiveness of features from the spectral envelope such as the frequency and bandwidth of the first peak obtained from a 30th order Linear Predictive Coefficients (LPC) to identify pathological voices. Other spectral features are also investigated and tested to improve the recognition rate. The value of the Relative Power of the Periodic Component is combined with spectral features, to diagnose pathological voices. Healthy voices and five vocal folds pathologies are tested. Decision Tree classifiers are used to evaluate which features have pathological voice information. Based on those results a simple Decision Tree was implemented and 94% of all the subjects in the database are correctly diagnosed.

AB - This work investigates the effectiveness of features from the spectral envelope such as the frequency and bandwidth of the first peak obtained from a 30th order Linear Predictive Coefficients (LPC) to identify pathological voices. Other spectral features are also investigated and tested to improve the recognition rate. The value of the Relative Power of the Periodic Component is combined with spectral features, to diagnose pathological voices. Healthy voices and five vocal folds pathologies are tested. Decision Tree classifiers are used to evaluate which features have pathological voice information. Based on those results a simple Decision Tree was implemented and 94% of all the subjects in the database are correctly diagnosed.

UR - http://www.scopus.com/inward/record.url?scp=84926644594&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2014.6944650

DO - 10.1109/EMBC.2014.6944650

M3 - Conference contribution

C2 - 25571018

SP - 4607

EP - 4610

BT - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014

Y2 - 26 August 2014 through 30 August 2014

ER -

Cordeiro H, Fonseca J, Meneses C. Spectral envelope and periodic component in classification trees for pathological voice diagnostic. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 4607-4610. 6944650 https://doi.org/10.1109/EMBC.2014.6944650, https://doi.org/10.1109/EMBC.2014.6944650