A Parametric Approach for Classification of Distortions in Pathological Voices

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

In biomedical acoustics, distortion in voice signals, commonly pre- sent 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, na- mely 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 clas- sifiers, namely support vector machines and probabilistic LDA clas- sify 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 di- rectly use acoustic features for distortion classification.
Close

Details

In biomedical acoustics, distortion in voice signals, commonly pre- sent 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, na- mely 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 clas- sifiers, namely support vector machines and probabilistic LDA clas- sify 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 di- rectly use acoustic features for distortion classification.
Original languageEnglish
Title of host publication2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublisherIEEE
Publication date2018
ISBN (Print)978-1-5386-4659-5
ISBN (Electronic)978-1-5386-4658-8
DOI
Publication statusPublished - 2018
Publication categoryResearch
Peer-reviewedYes
Event2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Calgary, Canada
Duration: 15 Apr 201820 Apr 2018
https://2018.ieeeicassp.org/

Conference

Conference2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
LandCanada
ByCalgary
Periode15/04/201820/04/2018
Internetadresse

Map

Download statistics

No data available
ID: 279628637