A Parametric Approach for Classification of Distortions in Pathological Voices

Amir Hossein Poorjam, Max A Little, Jesper Rindom Jensen, Mads Græsbøll Christensen

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

Abstract

In biomedical acoustics, distortion in voice signals, commonly present during acquisition and transmission, adversely affects acoustic features extracted from pathological voice. Information on the type of distortion can help in compensating for its effects. This paper proposes a new approach to detecting four major types of commonly encountered distortion in remote analysis of pathological voice, namely background noise, reverberation, clipping and coding. In this approach, by applying factor analysis to Gaussian mixture model mean supervectors, distortions in variable-duration recordings are modeled by fixed-length, low-dimensional channel vectors. Then, linear discriminant analysis (LDA) is used to remove the remaining nuisance effects in the channel vectors. Finally, two different classifiers, namely support vector machines and probabilistic LDA classify the different types of distortion. Experimental results obtained using Parkinson's voices, as an example of pathological voice, show 11.4% relative improvement in performance over systems which directly use acoustic features for distortion classification.
Original languageEnglish
Title of host publication2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
Pages286-290
ISBN (Electronic)978-1-5386-4658-8
ISBN (Print) 978-1-5386-4659-5
DOIs
Publication statusPublished - 13 Sep 2018
Event2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Calgary, Canada
Duration: 15 Apr 201820 Apr 2018

Publication series

Name2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
ISSN (Electronic)2379-190X

Conference

Conference2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
CountryCanada
CityCalgary
Period15/04/1820/04/18

Fingerprint

Discriminant analysis
Acoustic distortion
Acoustics
Reverberation
Factor analysis
Acoustic noise
Support vector machines
Classifiers

Bibliographical note

© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Cite this

Poorjam, A. H., Little, M. A., Jensen, J. R., & Christensen, M. G. (2018). A Parametric Approach for Classification of Distortions in Pathological Voices. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 286-290). (2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)). IEEE. https://doi.org/10.1109/ICASSP.2018.8461316
Poorjam, Amir Hossein ; Little, Max A ; Jensen, Jesper Rindom ; Christensen, Mads Græsbøll. / A Parametric Approach for Classification of Distortions in Pathological Voices. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018. pp. 286-290 (2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)).
@inproceedings{0a87ea7e2492470b8e4830b3b55f93f7,
title = "A Parametric Approach for Classification of Distortions in Pathological Voices",
abstract = "In biomedical acoustics, distortion in voice signals, commonly present during acquisition and transmission, adversely affects acoustic features extracted from pathological voice. Information on the type of distortion can help in compensating for its effects. This paper proposes a new approach to detecting four major types of commonly encountered distortion in remote analysis of pathological voice, namely background noise, reverberation, clipping and coding. In this approach, by applying factor analysis to Gaussian mixture model mean supervectors, distortions in variable-duration recordings are modeled by fixed-length, low-dimensional channel vectors. Then, linear discriminant analysis (LDA) is used to remove the remaining nuisance effects in the channel vectors. Finally, two different classifiers, namely support vector machines and probabilistic LDA classify the different types of distortion. Experimental results obtained using Parkinson's voices, as an example of pathological voice, show 11.4{\%} relative improvement in performance over systems which directly use acoustic features for distortion classification.",
author = "Poorjam, {Amir Hossein} and Little, {Max A} and Jensen, {Jesper Rindom} and Christensen, {Mads Gr{\ae}sb{\o}ll}",
note = "{\circledC} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2018",
month = "9",
day = "13",
doi = "10.1109/ICASSP.2018.8461316",
language = "English",
isbn = "978-1-5386-4659-5",
series = "2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
publisher = "IEEE",
pages = "286--290",
booktitle = "2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
address = "United States",

}

Poorjam, AH, Little, MA, Jensen, JR & Christensen, MG 2018, A Parametric Approach for Classification of Distortions in Pathological Voices. in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp. 286-290, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Canada, 15/04/18. https://doi.org/10.1109/ICASSP.2018.8461316

A Parametric Approach for Classification of Distortions in Pathological Voices. / Poorjam, Amir Hossein; Little, Max A; Jensen, Jesper Rindom; Christensen, Mads Græsbøll.

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2018. p. 286-290 (2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)).

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

TY - GEN

T1 - A Parametric Approach for Classification of Distortions in Pathological Voices

AU - Poorjam, Amir Hossein

AU - Little, Max A

AU - Jensen, Jesper Rindom

AU - Christensen, Mads Græsbøll

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2018/9/13

Y1 - 2018/9/13

N2 - In biomedical acoustics, distortion in voice signals, commonly present during acquisition and transmission, adversely affects acoustic features extracted from pathological voice. Information on the type of distortion can help in compensating for its effects. This paper proposes a new approach to detecting four major types of commonly encountered distortion in remote analysis of pathological voice, namely background noise, reverberation, clipping and coding. In this approach, by applying factor analysis to Gaussian mixture model mean supervectors, distortions in variable-duration recordings are modeled by fixed-length, low-dimensional channel vectors. Then, linear discriminant analysis (LDA) is used to remove the remaining nuisance effects in the channel vectors. Finally, two different classifiers, namely support vector machines and probabilistic LDA classify the different types of distortion. Experimental results obtained using Parkinson's voices, as an example of pathological voice, show 11.4% relative improvement in performance over systems which directly use acoustic features for distortion classification.

AB - In biomedical acoustics, distortion in voice signals, commonly present during acquisition and transmission, adversely affects acoustic features extracted from pathological voice. Information on the type of distortion can help in compensating for its effects. This paper proposes a new approach to detecting four major types of commonly encountered distortion in remote analysis of pathological voice, namely background noise, reverberation, clipping and coding. In this approach, by applying factor analysis to Gaussian mixture model mean supervectors, distortions in variable-duration recordings are modeled by fixed-length, low-dimensional channel vectors. Then, linear discriminant analysis (LDA) is used to remove the remaining nuisance effects in the channel vectors. Finally, two different classifiers, namely support vector machines and probabilistic LDA classify the different types of distortion. Experimental results obtained using Parkinson's voices, as an example of pathological voice, show 11.4% relative improvement in performance over systems which directly use acoustic features for distortion classification.

UR - https://ieeexplore.ieee.org/document/8461316/?tp=&arnumber=8461316&contentType=Conferences&dld=YXN0b24uYWMudWs%3D&source=SEARCHALERT

U2 - 10.1109/ICASSP.2018.8461316

DO - 10.1109/ICASSP.2018.8461316

M3 - Conference contribution

SN - 978-1-5386-4659-5

T3 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

SP - 286

EP - 290

BT - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

ER -

Poorjam AH, Little MA, Jensen JR, Christensen MG. A Parametric Approach for Classification of Distortions in Pathological Voices. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE. 2018. p. 286-290. (2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)). https://doi.org/10.1109/ICASSP.2018.8461316