Lanczos kernel based spectrogram image features for sound classification

dc.authoridFINDIK, OGUZ/0000-0001-5069-6470
dc.authoridOzer, Ilyas/0000-0003-2112-5497
dc.authoridOZER, ZEYNEP/0000-0001-8654-0902
dc.contributor.authorOzer, Ilyas
dc.contributor.authorOzer, Zeynep
dc.contributor.authorFindik, Oguz
dc.date.accessioned2024-09-29T16:00:36Z
dc.date.available2024-09-29T16:00:36Z
dc.date.issued2017
dc.departmentKarabük Üniversitesien_US
dc.description8th International Conference on Advances in Information Technology (IAIT) -- DEC 19-22, 2016 -- Macau, PEOPLES R CHINAen_US
dc.description.abstractAutomatic sound recognition (ASR) is a prominently emerging research area in recent years Recognition of sound events automatically through the computers in the complex audio environment is quite useful for machine hearing, acoustic surveillance and multimedia retrieval applications. Although a lot of features such as mel-frequency cepstral coefficients in ASR tasks provide very good results in noiseless environments, noisy conditions in the real world reduce success rates in a remarkable way. On the other hand, it was reported that spectrogram image features showed much better classification performance at low signal noise ratio values in many studies. In this article, it was proposed the preparation of feature vector after the images are reduced in size by applying the resizing process to spectrogram images with Lanczos kernel. Classification performance was compared by using deep artificial neural networks in different noise levels and although the feature vector was reduced, parallel values with results in the literature were obtained in the noiseless environment. It has remained slightly below the current state-of-the-art techniques using spectrogram features while better results compared to other commonly used features such as MFCC were obtained under the noisy conditions. (C) 2017 The Authors. Published by Elsevier B.V.en_US
dc.identifier.doi10.1016/j.procs.2017.06.020
dc.identifier.endpage144en_US
dc.identifier.issn1877-0509
dc.identifier.scopus2-s2.0-85029370577en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage137en_US
dc.identifier.urihttps://doi.org/10.1016/j.procs.2017.06.020
dc.identifier.urihttps://hdl.handle.net/20.500.14619/5227
dc.identifier.volume111en_US
dc.identifier.wosWOS:000418465800019en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevier Science Bven_US
dc.relation.ispartof8th International Conference On Advances in Information Technologyen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectMachine hearingen_US
dc.subjectautomatic sound recognitionen_US
dc.subjectspectrogram image featuresen_US
dc.subjectdeep neural networken_US
dc.titleLanczos kernel based spectrogram image features for sound classificationen_US
dc.typeConference Objecten_US

Dosyalar