{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T11:24:48Z","timestamp":1743161088910,"version":"3.37.3"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003600","name":"Korean National Police Agency","doi-asserted-by":"publisher","award":["PR01-02-040-17"],"award-info":[{"award-number":["PR01-02-040-17"]}],"id":[{"id":"10.13039\/501100003600","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3137190","type":"journal-article","created":{"date-parts":[[2021,12,21]],"date-time":"2021-12-21T20:55:15Z","timestamp":1640120115000},"page":"167615-167627","source":"Crossref","is-referenced-by-count":4,"title":["Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-Supervised Speaker Verification"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2554-8294","authenticated-orcid":false,"given":"Sung Hwan","family":"Mun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8086-5009","authenticated-orcid":false,"given":"Min Hyun","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongjune","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jihwan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0568-4902","authenticated-orcid":false,"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00700"},{"key":"ref38","first-page":"1","article-title":"Modeling uncertainty with hedged instance embedding","author":"oh","year":"2019","journal-title":"Proc ICLR"},{"key":"ref33","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","author":"wang","year":"2020","journal-title":"Proc ICML"},{"key":"ref32","first-page":"1822","article-title":"A geometric characterization of maximum Rényi entropy distributions","author":"vignat","year":"2006","journal-title":"Proc IEEE Int Symp Inf Theory"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462935"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.402"},{"key":"ref37","first-page":"1","article-title":"Deep Gaussian embedding of graphs: Unsupervised inductive learning via ranking","author":"bojchevski","year":"2018","journal-title":"Proc ICLR"},{"key":"ref36","first-page":"1","article-title":"Word representations via Gaussian embedding","author":"vilnis","year":"2015","journal-title":"Proc ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84808-2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1090\/S0894-0347-06-00546-7"},{"key":"ref28","first-page":"1","article-title":"Bootstrapped representation learning on graphs","author":"thakoor","year":"2021","journal-title":"Proc Workshop Geometrical Topolog Represent Learn (ICLR)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.123"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref20","first-page":"1","article-title":"Augmentation adversarial training for unsupervised speaker recognition","author":"huh","year":"2020","journal-title":"Proc Workshop S elf-Upervised Lean Speech Audio Process (NeurIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref24","first-page":"1","article-title":"Contrastive learning with hard negative samples","author":"robinson","year":"2021","journal-title":"Proc ICLR"},{"key":"ref23","first-page":"1","article-title":"What makes for good views for contrastive learning","author":"tian","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref26","first-page":"3875","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"2020","journal-title":"Proc NeuIPS"},{"key":"ref25","first-page":"3875","article-title":"Bootstrap latent-predictive representations for multitask reinforcement learning","author":"guo","year":"2020","journal-title":"Proc ICML"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"ref40","article-title":"Fast and reliable probabilistic face embeddings in the wild","author":"chen","year":"2021","journal-title":"arXiv 2102 04075"},{"key":"ref12","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref13","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref15","article-title":"A theoretical analysis of contrastive unsupervised representation learning","author":"arora","year":"2019","journal-title":"arXiv 1902 09229"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2842"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2380"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2921890"},{"key":"ref19","first-page":"1641","article-title":"Semi-supervised contrastive learning with generalized contrastive loss and its application to speaker recognition","author":"inoue","year":"2020","journal-title":"Proc APSIPA"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1982"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref46","article-title":"Momentum contrast speaker representation learning","author":"lee","year":"2020","journal-title":"arXiv 2010 11457"},{"key":"ref45","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref42","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"arXiv 1510 08484 [cs]"},{"key":"ref41","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref44","first-page":"1","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"Proc CVPR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09656847.pdf?arnumber=9656847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T21:15:05Z","timestamp":1648502105000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9656847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3137190","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}