{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T13:06:00Z","timestamp":1768741560861,"version":"3.49.0"},"reference-count":50,"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":"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":"Global Korea Scholarship"}],"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.2022.3200915","type":"journal-article","created":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T15:57:32Z","timestamp":1661183852000},"page":"1253-1262","source":"Crossref","is-referenced-by-count":12,"title":["Augmentation Adversarial Training for Self-Supervised Speaker Representation Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9284-5945","authenticated-orcid":false,"given":"Jingu","family":"Kang","sequence":"first","affiliation":[{"name":"Inha University, Incheon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaesung","family":"Huh","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hee Soo","family":"Heo","sequence":"additional","affiliation":[{"name":"Naver Corporation, Seongnam-si, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7741-7275","authenticated-orcid":false,"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science, and Technology, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"NIST 2018 speaker recognition evaluation plan","year":"2020"},{"key":"ref2","article-title":"Few shot speaker recognition using deep neural networks","author":"Anand","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref4","first-page":"15535","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Bachman","year":"2019"},{"key":"ref5","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682611"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682064"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947437"},{"key":"ref9","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-49"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref19","first-page":"21271","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Grill","year":"2020"},{"key":"ref20","article-title":"Unified hypersphere embedding for speaker recognition","author":"Hajibabaei","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref23","first-page":"1641","article-title":"Semi-supervised contrastive learning with generalized contrastive loss and its application to speaker recognition","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Inoue","year":"2020"},{"key":"ref24","article-title":"Bayesian speaker verification with heavy-tailed priors","volume-title":"Proc. Speaker Odyssey","volume":"14","author":"Kenny","year":"2010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413948"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706570"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053323"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947436"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref35","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2380"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1454"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683616"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref40","first-page":"4080","article-title":"Prototypical networks for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Snell","year":"2017"},{"key":"ref41","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref45","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683393"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461423"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09864218.pdf?arnumber=9864218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:45:28Z","timestamp":1756154728000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9864218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":50,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3200915","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}