Voice pathology detection by using the deep network architecture

dc.contributor.authorAnkishan, Haydar
dc.contributor.authorInam, Sitki Cagdas
dc.contributor.orcID0000-0002-6240-2545en_US
dc.date.accessioned2022-09-07T11:07:55Z
dc.date.available2022-09-07T11:07:55Z
dc.date.issued2021
dc.description.abstractPathological voice disorders are among the conditions affecting negatively our daily life. The aim of this study is to introduce the new feature vector in the hybrid axis and multi-model in order to diagnose these disorders with more conventional methods. Two different databases are used, and the results are compared with the previous studies. Here, two types of fusion models (feature and decision level fusion) are used to increase the classification accuracy of the multi-model. The experimental results show that the proposed multi-model gives the highest classification accuracies with decision level fusion (DLF). Inspecting the results obtained from two databases, the highest accuracy rate (99.58%) is obtained with DLF. It is also seen from the experiments that the proposed feature vector helps to classify pathological data successfully, depending on their pathological conditions. Together with the proposed multi-model, both LSTM and CNN are found to be similarly successful in the classification of data in multi-model architecture. (C) 2021 Elsevier B.V. All rights reserved.en_US
dc.identifier.issn1568-4946en_US
dc.identifier.scopus2-s2.0-85103686412en_US
dc.identifier.urihttp://hdl.handle.net/11727/7557
dc.identifier.volume106en_US
dc.identifier.wos000663384000001en_US
dc.language.isoengen_US
dc.relation.isversionof10.1016/j.asoc.2021.107310en_US
dc.relation.journalAPPLIED SOFT COMPUTINGen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergien_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectVoice disordersen_US
dc.subjectHybrid feature vectoren_US
dc.subjectVoice pathology detectionen_US
dc.subjectDeep network architectureen_US
dc.titleVoice pathology detection by using the deep network architectureen_US
dc.typearticleen_US

Files

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: