Acoustic Event Classification using spectral band selection and Non-Negative Matrix Factorization-based features

Simple item page
dc.contributor.advisorhttps://purl.org/pe-repo/ocde/ford#2.02.01es_PE
dc.contributor.authorLudeña Choez, Jimmy
dc.contributor.authorGallardo Antolín, Ascensión
dc.date.accessioned2019-01-29T22:19:53Z
dc.date.available2019-01-29T22:19:53Z
dc.date.issued2016
dc.description.abstractFeature extraction methods for sound events have been traditionally based on parametric representations specifically developed for speech signals, such as the well-known Mel Frequency Cepstrum Coefficients (MFCC). However, the discrimination capabilities of these features for Acoustic Event Classification (AEC) tasks could be enhanced by taking into account the spectro-temporal structure of acoustic event signals. In this paper, a new front-end for AEC which incorporates this specific information is proposed. It consists of two different stages: short-time feature extraction and temporal feature integration. The first module aims at providing a better spectral representation of the different acoustic events on a frame-by-frame basis, by means of the automatic selection of the optimal set of frequency bands from which cepstral-like features are extracted. The second stage is designed for capturing the most relevant temporal information in the short-time features, through the application of Non-Negative Matrix Factorization (NMF) on their periodograms computed over long audio segments. The whole front-end has been evaluated in clean and noisy conditions. Experiments show that the removal of certain frequency bands (which are mainly located in the medium region of the spectrum for clean conditions and in low frequencies for noisy environments) in the short-time feature computation process in conjunction with the NMF technique for temporal feature integration improves significantly the performance of a Support Vector Machine (SVM) based AEC system with respect to the use of conventional MFCCs. © 2015 Elsevier Ltd. All rights reserved.es_PE
dc.description.uriTrabajo de investigaciónes_PE
dc.identifier.doihttps://doi.org/10.1016/j.eswa.2015.10.018es_PE
dc.identifier.issn9574174es_PE
dc.identifier.urihttps://hdl.handle.net/20.500.12590/15835
dc.language.isoenges_PE
dc.publisherElsevier Ltdes_PE
dc.relation.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84946616129&doi=10.1016%2fj.eswa.2015.10.018&partnerID=40&md5=99b38cb7420d4d402bdc179cb63fec7des_PE
dc.rightsinfo:eu-repo/semantics/restrictedAccesses_PE
dc.sourceRepositorio Institucional - UCSPes_PE
dc.sourceUniversidad Católica San Pabloes_PE
dc.sourceScopuses_PE
dc.subjectExtractiones_PE
dc.subjectFactorizationes_PE
dc.subjectFeature extractiones_PE
dc.subjectFrequency bandses_PE
dc.subjectIntegrationes_PE
dc.subjectMatrix algebraes_PE
dc.subjectSpeech recognitiones_PE
dc.subjectSupport vector machineses_PE
dc.subjectAcoustic event classificationes_PE
dc.subjectFeature extraction methodses_PE
dc.subjectMel frequency cepstrum coefficientses_PE
dc.subjectMutual informationses_PE
dc.subjectNonnegative matrix factorizationes_PE
dc.subjectParametric representationses_PE
dc.subjectSpectral representationses_PE
dc.subjectTemporal feature integrationses_PE
dc.subjectClassification (of information)es_PE
dc.subject.ocdehttps://purl.org/pe-repo/ocde/ford#2.02.01es_PE
dc.titleAcoustic Event Classification using spectral band selection and Non-Negative Matrix Factorization-based featureses_PE
dc.typeinfo:eu-repo/semantics/article
Files
Collections
Artículos - Ingeniería Electrónica y de Telecomunicaciones