Show simple item record

dc.contributor.authorMporas, Iosif
dc.contributor.authorTheodorou, Theodoros
dc.contributor.authorFakotakis, Nikos
dc.date.accessioned2017-02-09T14:52:02Z
dc.date.available2017-02-09T14:52:02Z
dc.date.issued2017-04-07
dc.identifier.citationMporas , I , Theodorou , T & Fakotakis , N 2017 , ' Data-Driven Audio Feature Space Clustering for Automatic Sound Recognition in Radio Broadcast News ' , International Journal on Artificial Intelligence Tools , vol. 26 , no. 2 , 1750005 . https://doi.org/10.1142/S0218213017500051
dc.identifier.issn0218-2130
dc.identifier.otherPURE: 10688210
dc.identifier.otherPURE UUID: bb35b894-c07b-4a6d-8da3-44e9ed6dff08
dc.identifier.otherScopus: 85017160553
dc.identifier.urihttp://hdl.handle.net/2299/17617
dc.descriptionThis is an Open Access article published by World Scientific Publishing Company. It is distributed under the terms of the Creative Commons Attribution 4.0 (CC-BY) License. Further distribution of this work is permitted, provided the original work is properly cited. T. Theodorou, I. Mpoas, A. Lazaridis, N. Fakotakis, 'Data-Driven Audio Feature Space Clustering for Automatic Sound Recognition in Radio Broadcast News', International Journal on Artificial Intelligence Tools, Vol. 26 (2), April 2017, 1750005 (13 pages), DOI: 10.1142/S021821301750005. © The Author(s).
dc.description.abstractIn this paper we describe an automatic sound recognition scheme for radio broadcast news based on principal component clustering with respect to the discrimination ability of the principal components. Specifically, streams of broadcast news transmissions, labeled based on the audio event, are decomposed using a large set of audio descriptors and project into the principal component space. A data-driven algorithm clusters the relevance of the components. The component subspaces are used by sound type classifier. This methodology showed that the k-nearest neighbor and the artificial intelligent network provide good results. Also, this methodology showed that discarding unnecessary dimension works in favor on the outcome, as it hardly deteriorates the effectiveness of the algorithms.en
dc.format.extent13
dc.language.isoeng
dc.relation.ispartofInternational Journal on Artificial Intelligence Tools
dc.rights/dk/atira/pure/core/openaccesspermission/open
dc.subjectsound recognitiion
dc.subjectaudio features
dc.subjectfeature subspace selection
dc.titleData-Driven Audio Feature Space Clustering for Automatic Sound Recognition in Radio Broadcast Newsen
dc.contributor.institutionSchool of Engineering and Technology
dc.contributor.institutionCentre for Engineering Research
dc.contributor.institutionInformation Engineering and Processing Architectures
dc.contributor.institutionBioEngineering
dc.contributor.institutionCommunications and Intelligent Systems
dc.description.statusPeer reviewed
dc.relation.schoolSchool of Engineering and Technology
dc.description.versiontypeFinal Published version
dcterms.dateAccepted2016-11-17
rioxxterms.versionVoR
rioxxterms.versionofrecordhttps://doi.org/10.1142/S0218213017500051
rioxxterms.licenseref.urihttp://creativecommons.org/licenses/by/4.0/
rioxxterms.typeJournal Article/Review
herts.preservation.rarelyaccessedtrue
herts.rights.accesstypeopenAccess


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record