Environmental sound recognition using short-time feature aggregation
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Roma Trepat, Gerard
- dc.contributor.author Herrera Boyer, Perfecto, 1964-
- dc.contributor.author Nogueira, Waldo
- dc.date.accessioned 2020-09-02T07:09:37Z
- dc.date.available 2020-09-02T07:09:37Z
- dc.date.issued 2018
- dc.description.abstract Recognition of environmental sound is usually based on two main architectures, depending on whether the model is trained with frame-level features or with aggregated descriptions of acoustic scenes or events. The former architecture is appropriate for applications where target categories are known in advance, while the later affords a less supervised approach. In this paper, we propose a framework for environmental sound recognition based on blind segmentation and feature aggregation. We describe a new set of descriptors, based on Recurrence Quantification Analysis (RQA), which can be extracted from the similarity matrix of a time series of audio descriptors. We analyze their usefulness for recognition of acoustic scenes and events in addition to standard feature aggregation. Our results show the potential of non-linear time series analysis techniques for dealing with environmental sounds.en
- dc.description.sponsorship This work has been suported by the DFG cluster of excellence EXC 1077/1“Hearing4all”.en
- dc.format.mimetype application/pdf
- dc.identifier.citation Roma G, Herrera P, Nogueira W. Environmental sound recognition using short-time feature aggregation. J Intell Inf Syst. 2018;51:457-75. DOI: 10.1007/s10844-017-0481-4
- dc.identifier.doi http://dx.doi.org/10.1007/s10844-017-0481-4
- dc.identifier.issn 0925-9902
- dc.identifier.uri http://hdl.handle.net/10230/45243
- dc.language.iso eng
- dc.publisher Springer
- dc.relation.ispartof Journal of Intelligent Information Systems. 2018;51:457-75.
- dc.rights © Springer The final publication is available at Springer via http://dx.doi.org/10.1007/s10844-017-0481-4
- dc.rights.accessRights info:eu-repo/semantics/openAccess
- dc.subject.keyword Audio databasesen
- dc.subject.keyword Event detectionen
- dc.subject.keyword Environmental sound recognitionen
- dc.subject.keyword Audio featuresen
- dc.subject.keyword Recurrence quantification analysisen
- dc.subject.keyword Pattern recognitionen
- dc.title Environmental sound recognition using short-time feature aggregationen
- dc.type info:eu-repo/semantics/article
- dc.type.version info:eu-repo/semantics/acceptedVersion