NMF-based temporal feature integration for acoustic event classification

dc.contributor.authorLudeña Choez, Jimmy Diestin
dc.contributor.authorGallardo Antolín, Ascensión
dc.date.accessioned2019-01-29T22:19:55Z
dc.date.available2019-01-29T22:19:55Z
dc.date.issued2013
dc.description.abstractIn this paper, we propose a new front-end for Acoustic Event Classification tasks (AEC) based on the combination of the temporal feature integration technique called Filter Bank Coefficients (FC) and Non-Negative Matrix Factorization (NMF). FC aims to capture the dynamic structure in the short-term features by means of the summarization of the periodogram of each short-term feature dimension in several frequency bands using a predefined filter bank. As the commonly used filter bank has been devised for other tasks (such as music genre classification), it can be suboptimal for AEC. In order to overcome this drawback, we propose an unsupervised method based on NMF for learning the filters which collect the most relevant temporal information in the short-time features for AEC. The experiments show that the features obtained with this method achieve significant improvements in the classification performance of a Support Vector Machine (SVM) based AEC system in comparison with the baseline FC features. Copyright © 2013 ISCA.es_PE
dc.description.uriTrabajo de investigaciónes_PE
dc.identifier.issn2308457Xes_PE
dc.identifier.urihttps://hdl.handle.net/20.500.12590/15878
dc.language.isoenges_PE
dc.publisherInternational Speech and Communication Associationes_PE
dc.relation.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84906264286&partnerID=40&md5=d8c5924415a4fb87e1b53f9ae9b60552es_PE
dc.rightsinfo:eu-repo/semantics/restrictedAccesses_PE
dc.sourceRepositorio Institucional - UCSPes_PE
dc.sourceUniversidad Católica San Pabloes_PE
dc.sourceScopuses_PE
dc.subjectFactorizationes_PE
dc.subjectFrequency bandses_PE
dc.subjectIntegrationes_PE
dc.subjectSupport vector machineses_PE
dc.subjectAcoustic event classificationes_PE
dc.subjectClassification performancees_PE
dc.subjectFilter-bank coefficientses_PE
dc.subjectMusic genre classificationes_PE
dc.subjectNonnegative matrix factorizationes_PE
dc.subjectTemporal feature integrationses_PE
dc.subjectTemporal informationes_PE
dc.subjectUnsupervised methodes_PE
dc.subjectFilter bankses_PE
dc.subject.ocdehttps://purl.org/pe-repo/ocde/ford#2.02.01es_PE
dc.titleNMF-based temporal feature integration for acoustic event classificationes_PE
dc.typeinfo:eu-repo/semantics/conferenceObject
Files