Show simple item record

dc.contributor.authorButko, Taras
dc.contributor.authorNadeu Camprubí, Climent
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2011-03-25T13:44:51Z
dc.date.available2011-03-25T13:44:51Z
dc.date.issued2010
dc.identifier.citationButko, T.; Nadeu Camprubí, C. A fast one-pass-training feature selection technique for GMM-based acoustic event detection with audio-visual data. A: Annual Conference of the International Speech Communication Association. "Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)". 2010, p. 2338-2341. ISBN 1990-9772.
dc.identifier.isbn1990-9772
dc.identifier.urihttp://hdl.handle.net/2117/12069
dc.description.abstractAcoustic event detection becomes a difficult task, even for a small number of events, in scenarios where events are produced rather spontaneously and often overlap in time. In this work, we aim to improve the detection rate by means of feature selection. Using a one-against-all detection approach, a new fast one-pass-training algorithm, and an associated highly-precise metric are developed. Choosing a different subset of multimodal features for each acoustic event class, the results obtained from audiovisual data collected in the UPC multimodal room show an improvement in average detection rate with respect to using the whole set of features.
dc.format.extent4 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic
dc.subject.lcshAcoustic emission -- Mathematical models
dc.titleA fast one-pass-training feature selection technique for GMM-based acoustic event detection with audio-visual data
dc.typeConference report
dc.subject.lemacEsdeveniments sonors -- Models matemàtics
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://www.isca-speech.org/archive/interspeech_2010/i10_2338.html
dc.rights.accessOpen Access
local.identifier.drac5327946
dc.description.versionPreprint
local.citation.contributorAnnual Conference of the International Speech Communication Association
local.citation.publicationNameProceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)
local.citation.startingPage2338
local.citation.endingPage2341


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder