Show simple item record

dc.contributor.authorLee, K A
dc.contributor.authorHautamäki, V
dc.contributor.authorKinnunen, T
dc.contributor.authorLarcher, A
dc.contributor.authorZhang, C
dc.contributor.authorNautsch, A
dc.contributor.authorStafylakis, T
dc.contributor.authorLiu, G
dc.contributor.authorRouvier, M
dc.contributor.authorRao, W
dc.contributor.authorAlegre, F
dc.contributor.authorMa, J
dc.contributor.authorMak, M W
dc.contributor.authorSarkar, A K
dc.contributor.authorDelgado, H
dc.contributor.authorSaeidi, R
dc.contributor.authorAronowitz, H
dc.contributor.authorSizov, A
dc.contributor.authorSun, H
dc.contributor.authorNguyen, T H
dc.contributor.authorSahidullah, Md
dc.contributor.authorVestman, V
dc.contributor.authorHalonen, M
dc.contributor.authorKanervisto, A
dc.contributor.authoret al.
dc.date.accessioned2017-10-06T06:03:03Z
dc.date.available2017-10-06T06:03:03Z
dc.date.issued2017
dc.identifier.urihttps://erepo.uef.fi/handle/123456789/4376
dc.description.abstractThe 2016 speaker recognition evaluation (SRE’16) is the latest edition in the series of benchmarking events conducted by the National Institute of Standards and Technology (NIST). I4U is a joint entry to SRE’16 as the result from the collaboration and active exchange of information among researchers from sixteen Institutes and Universities across 4 continents. The joint submission and several of its 32 sub-systems were among top-performing systems. A lot of efforts have been devoted to two major challenges, namely, unlabeled training data and dataset shift from Switchboard-Mixer to the new Call My Net dataset. This paper summarizes the lessons learned, presents our shared view from the sixteen research groups on recent advances, major paradigm shift, and common tool chain used in speaker recognition as we have witnessed in SRE’16. More importantly, we look into the intriguing question of fusing a large ensemble of sub-systems and the potential benefit of large-scale collaboration.en
dc.language.isoENen
dc.publisherISCA (the International Speech Communication Association)en
dc.relation.ispartofseriesProceedings of the 18th Annual Conference of the International Speech Communication Associationen
dc.relation.urihttp://dx.doi.org/10.21437/Interspeech.2017-203en
dc.rightsAll rights reserveden
dc.subjectspeaker recognition evaluationen
dc.subjectfusionen
dc.subjectbenchmarken
dc.subjectCall My Neten
dc.titleThe I4U Mega Fusion and Collaboration for NIST Speaker Recognition Evaluation 2016en
dc.description.versionpublished versionen
dc.contributor.departmentSchool of Computing, activitiesen
uef.solecris.id49978093en
dc.type.publicationconferenceObjecten
dc.rights.accessrights© ISCAen
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/647850/EU/Objective Control for TAlker VErification/OCTAVEen
dc.relation.doi10.21437/Interspeech.2017-203en
dc.description.reviewstatuspeerRevieweden
dc.format.pagerange1328-1332en
dc.relation.issn2308-457Xen
dc.rights.accesslevelopenAccessen
dc.type.okmA4en
dc.type.versioninfo:eu-repo/semantics/publishedVersionen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record