{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T02:10:34Z","timestamp":1767838234049,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["1816165"],"award-info":[{"award-number":["1816165"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/jstsp.2022.3197315","type":"journal-article","created":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T19:54:53Z","timestamp":1659988493000},"page":"1284-1295","source":"Crossref","is-referenced-by-count":18,"title":["Non-Contrastive Self-Supervised Learning for Utterance-Level Information Extraction From Speech"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0527-5391","authenticated-orcid":false,"given":"Jaejin","family":"Cho","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, and the Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9459-8426","authenticated-orcid":false,"given":"Jesus","family":"Villalba","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, and the Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3033-7005","authenticated-orcid":false,"given":"Laureano","family":"Moro-Velazquez","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, and the Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4489-5753","authenticated-orcid":false,"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, and the Center for Language and Speech Processing (CLSP), Johns Hopkins University, Baltimore, MD, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref3","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref4","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen","year":"2020"},{"key":"ref5","first-page":"21271","article-title":"Bootstrap your own latent - a new approach to self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Grill","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-349"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref14","first-page":"1876","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hsu","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2842"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2970"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054595"},{"key":"ref18","first-page":"1","article-title":"Augmentation adversarial training for unsupervised speaker recognition","volume-title":"Proc. NeurIPS Workshop","author":"Huh","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3307"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3481003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415077"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2587"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1850"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101026"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3134566"},{"key":"ref34","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tarvainen","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref37","article-title":"The IDLAB VoxCeleb speaker recognition challenge 2020 system description","author":"Thienpondt","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1220"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/4200690\/9923627\/9852303-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09852303.pdf?arnumber=9852303","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T04:33:45Z","timestamp":1709354025000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9852303\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":44,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3197315","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}