Towards robust voice pathology detection Investigation of supervised deep learning, gradient boosting, and anomaly detection approaches across four databases

Simple item page
dc.contributor.authorHarár, Pavolcs
dc.contributor.authorGaláž, Zoltáncs
dc.contributor.authorAlonso-Hernandez, Jesuscs
dc.contributor.authorMekyska, Jiřícs
dc.contributor.authorBurget, Radimcs
dc.contributor.authorSmékal, Zdeněkcs
dc.coverage.issue1cs
dc.coverage.volume1cs
dc.date.issued2020-10-02cs
dc.description.abstractAutomatic objective non-invasive detection of pathological voice based on computerized analysis of acoustic signals can play an important role in early diagnosis, progression tracking and even effective treatment of pathological voices. In search towards such a robust voice pathology detection system we investigated 3 distinct classifiers within supervised learning and anomaly detection paradigms. We conducted a set of experiments using a variety of input data such as raw waveforms, spectrograms, mel-frequency cepstral coefficients (MFCC) and conventional acoustic (dysphonic) features (AF). In comparison with previously published works, this article is the first to utilize combination of 4 different databases comprising normophonic and pathological recordings of sustained phonation of the vowel /a/ unrestricted to a subset of vocal pathologies. Furthermore, to our best knowledge, this article is the first to explore gradient boosted trees and deep learning for this application. The following best classification performances measured by F1 score on dedicated test set were achieved: XGBoost (0.733) using AF and MFCC, DenseNet (0.621) using MFCC, and Isolation Forest (0.610) using AF. Even though these results are of exploratory character, conducted experiments do show promising potential of gradient boosting and deep learning methods to robustly detect voice pathologies.en
dc.formattextcs
dc.format.extent15747-15757cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationNeural Computing and Applications. 2020, vol. 1, issue 1, p. 15747-15757.en
dc.identifier.doi10.1007/s00521-018-3464-7cs
dc.identifier.issn1433-3058cs
dc.identifier.orcid0000-0001-5206-1794cs
dc.identifier.orcid0000-0002-8978-351Xcs
dc.identifier.orcid0000-0002-6195-193Xcs
dc.identifier.orcid0000-0003-1849-5390cs
dc.identifier.orcid0000-0002-8483-5448cs
dc.identifier.other147134cs
dc.identifier.researcheridT-8761-2019cs
dc.identifier.researcheridK-4001-2015cs
dc.identifier.scopus56888706700cs
dc.identifier.scopus35746344400cs
dc.identifier.scopus23011250200cs
dc.identifier.scopus36855362600cs
dc.identifier.urihttp://hdl.handle.net/11012/156794
dc.language.isoencs
dc.publisherSpringercs
dc.relation.ispartofNeural Computing and Applicationscs
dc.relation.urihttps://link.springer.com/article/10.1007/s00521-018-3464-7cs
dc.rights(C) Springercs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1433-3058/cs
dc.subjectvoice patholgoy detectionen
dc.subjectdeep learningen
dc.subjectgradient boostingen
dc.subjectanomaly detectionen
dc.titleTowards robust voice pathology detection Investigation of supervised deep learning, gradient boosting, and anomaly detection approaches across four databasesen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionacceptedVersionen
sync.item.dbidVAV-147134en
sync.item.dbtypeVAVen
sync.item.insts2025.02.03 15:39:19en
sync.item.modts2025.01.17 15:37:45en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav telekomunikacícs
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. oddělení-TKO-SIXcs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
accepted_manusctript_acknowledged.pdf
Size:
684.4 KB
Format:
Adobe Portable Document Format
Description:
accepted_manusctript_acknowledged.pdf
Download
Collections
oddělení-TKO-SIX
Ústav telekomunikací