The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016

dc.contributorAalto Universityen
dc.contributor.authorLee, K. A.en_US
dc.contributor.authorHautamäki, V.en_US
dc.contributor.authorKinnunen, T.en_US
dc.contributor.authorLarcher, A.en_US
dc.contributor.authorZhang, C.en_US
dc.contributor.authorNautsch, A.en_US
dc.contributor.authorStafylakis, T.en_US
dc.contributor.authorRouvier, M.en_US
dc.contributor.authorRao, W.en_US
dc.contributor.authorAlegre, F.en_US
dc.contributor.authorMa, J.en_US
dc.contributor.authorMak, M. W.en_US
dc.contributor.authorSarkar, A. K.en_US
dc.contributor.authorDelgado, H.en_US
dc.contributor.authorSaeidi, R.en_US
dc.contributor.authorAronowitz, H.en_US
dc.contributor.authorSizov, A.en_US
dc.contributor.authorSun, H.en_US
dc.contributor.authorNguyen, T. H.en_US
dc.contributor.authorWang, G.en_US
dc.contributor.authorMa, B.en_US
dc.contributor.authorVestman, V.en_US
dc.contributor.authorSahidullah, M.en_US
dc.contributor.authorHalonen, M.en_US
dc.contributor.authorKanervisto, A.en_US
dc.contributor.authorLe Lan, G.en_US
dc.contributor.authorBahmaninezhad, F.en_US
dc.contributor.authorIsadskiy, S.en_US
dc.contributor.authorRathgeb, C.en_US
dc.contributor.authorBusch, C.en_US
dc.contributor.authorTzimiropoulos, G.en_US
dc.contributor.authorQian, Q.en_US
dc.contributor.authorWang, Z.en_US
dc.contributor.authorZhao, Q.en_US
dc.contributor.authorWang, Tianzhouen_US
dc.contributor.authorLi, H.en_US
dc.contributor.authorXue, J.en_US
dc.contributor.authorZhu, S.en_US
dc.contributor.authorJin, R.en_US
dc.contributor.authorZhao, T.en_US
dc.contributor.authorBousquet, P. M.en_US
dc.contributor.authorAjili, M.en_US
dc.contributor.authorKheder, W. B.en_US
dc.contributor.authorMatrouf, D.en_US
dc.contributor.authorLim, Z. H.en_US
dc.contributor.authorXu, C.en_US
dc.contributor.authorXu, H.en_US
dc.contributor.authorXiao, X.en_US
dc.contributor.authorChng, E. S.en_US
dc.contributor.authorFauve, B.en_US
dc.contributor.authorSriskandaraja, K.en_US
dc.contributor.authorSethu, V.en_US
dc.contributor.authorThomsen, D. A.L.en_US
dc.contributor.authorTan, Z. H.en_US
dc.contributor.authorTodisco, M.en_US
dc.contributor.authorEvans, N.en_US
dc.contributor.authorLi, Haizhouen_US
dc.contributor.authorHansen, J. H.L.en_US
dc.contributor.authorBonastre, J. F.en_US
dc.contributor.authorAmbikairajah, E.en_US
dc.contributor.authorLiu, Gangen_US
dc.contributor.authorLin, Weiweien_US
dc.contributor.departmentAgency for Science, Technology and Researchen_US
dc.contributor.departmentUniversity of Eastern Finlanden_US
dc.contributor.departmentUniversité du Maineen_US
dc.contributor.departmentUniversity of Texas at Austinen_US
dc.contributor.departmentDarmstadt University of Applied Sciencesen_US
dc.contributor.departmentUniversity of Nottinghamen_US
dc.contributor.departmentAvignon Universitéen_US
dc.contributor.departmentNanyang Technological Universityen_US
dc.contributor.departmentUniversity of New South Walesen_US
dc.contributor.departmentHong Kong Polytechnic Universityen_US
dc.contributor.departmentAalborg Universityen_US
dc.contributor.departmentDept Signal Process and Acousten_US
dc.contributor.departmentAlibaba Group Inc.en_US
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.description.versionPeer revieweden
dc.identifier.citationLee , K A , Hautamäki , V , Kinnunen , T , Larcher , A , Zhang , C , Nautsch , A , Stafylakis , T , Rouvier , M , Rao , W , Alegre , F , Ma , J , Mak , M W , Sarkar , A K , Delgado , H , Saeidi , R , Aronowitz , H , Sizov , A , Sun , H , Nguyen , T H , Wang , G , Ma , B , Vestman , V , Sahidullah , M , Halonen , M , Kanervisto , A , Le Lan , G , Bahmaninezhad , F , Isadskiy , S , Rathgeb , C , Busch , C , Tzimiropoulos , G , Qian , Q , Wang , Z , Zhao , Q , Wang , T , Li , H , Xue , J , Zhu , S , Jin , R , Zhao , T , Bousquet , P M , Ajili , M , Kheder , W B , Matrouf , D , Lim , Z H , Xu , C , Xu , H , Xiao , X , Chng , E S , Fauve , B , Sriskandaraja , K , Sethu , V , Thomsen , D A L , Tan , Z H , Todisco , M , Evans , N , Li , H , Hansen , J H L , Bonastre , J F , Ambikairajah , E , Liu , G & Lin , W 2017 , The I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016 . in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH . vol. 2017-August , Interspeech: Annual Conference of the International Speech Communication Association , International Speech Communication Association (ISCA) , pp. 1328-1332 , Interspeech , Stockholm , Sweden , 20/08/2017 .
dc.identifier.otherPURE UUID: dc8f905f-5c5e-45ca-b1f3-867d15aba2ceen_US
dc.identifier.otherPURE ITEMURL:
dc.identifier.otherPURE LINK:
dc.identifier.otherPURE FILEURL:
dc.relation.ispartofseriesProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECHen
dc.relation.ispartofseriesVolume 2017-Augusten
dc.relation.ispartofseriesInterspeech: Annual Conference of the International Speech Communication Associationen
dc.subject.keywordCall My Neten_US
dc.subject.keywordSpeaker recognition evaluationen_US
dc.titleThe I4U mega fusion and collaboration for NIST speaker recognition evaluation 2016en
dc.typeConference article in proceedingsfi