Analysis and interpretation of joint source separation and sound event detection in domestic environments

Simple item page
dc.contributor.authorde Benito Gorron, Diegocs
dc.contributor.authorŽmolíková, Kateřinacs
dc.contributor.authorTorre Toledano, Doroteocs
dc.coverage.issue7cs
dc.coverage.volume19cs
dc.date.accessioned2025-06-16T12:57:29Z
dc.date.available2025-06-16T12:57:29Z
dc.date.issued2024-07-05cs
dc.description.abstractIn recent years, the relation between Sound Event Detection (SED) and Source Separation (SSep) has received a growing interest, in particular, with the aim to enhance the performance of SED by leveraging the synergies between both tasks. In this paper, we present a detailed description of JSS (Joint Source Separation and Sound Event Detection), our joint-training scheme for SSep and SED, and we measure its performance in the DCASE Challenge for SED in domestic environments. Our experiments demonstrate that JSS can improve SED performance, in terms of Polyphonic Sound Detection Score (PSDS), even without additional training data. Additionally, we conduct a thorough analysis of JSS's effectiveness across different event classes and in scenarios with severe event overlap, where it is expected to yield further improvements. Furthermore, we introduce an objective measure to assess the diversity of event predictions across the estimated sources, shedding light on how different training strategies impact the separation of sound events. Finally, we provide graphical examples of the Source Separation and Sound Event Detection steps, aiming to facilitate the interpretation of the JSS methods.en
dc.formattextcs
dc.format.extent1-30cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationPLOS ONE. 2024, vol. 19, issue 7, p. 1-30.en
dc.identifier.doi10.1371/journal.pone.0303994cs
dc.identifier.issn1932-6203cs
dc.identifier.orcid0000-0003-4438-8580cs
dc.identifier.other197551cs
dc.identifier.researcheridACB-9902-2022cs
dc.identifier.scopus57189593906cs
dc.identifier.urihttps://hdl.handle.net/11012/252544
dc.language.isoencs
dc.publisherPUBLIC LIBRARY SCIENCEcs
dc.relation.ispartofPLOS ONEcs
dc.relation.urihttps://journals.plos.org/plosone/article?id=10.1371/journal.pone.0303994cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1932-6203/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectarticleen
dc.subjectdiagnosisen
dc.subjecthumanen
dc.subjectpredictionen
dc.subjectsounden
dc.subjectsound detectionen
dc.subjectalgorithmen
dc.titleAnalysis and interpretation of joint source separation and sound event detection in domestic environmentsen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-197551en
sync.item.dbtypeVAVen
sync.item.insts2025.06.16 14:57:29en
sync.item.modts2025.06.16 14:33:03en
thesis.grantorVysoké učení technické v Brně. Fakulta informačních technologií. Ústav počítačové grafiky a multimédiícs
thesis.grantorVysoké učení technické v Brně. . Universidad Autónoma de Madridcs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
journal.pone.0303994.pdf
Size:
14.7 MB
Format:
Adobe Portable Document Format
Description:
file journal.pone.0303994.pdf
Download
Collections
Ústav počítačové grafiky a multimédií