{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:23:59Z","timestamp":1781713439846,"version":"3.54.5"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"China NSFC Projects","award":["62122050"],"award-info":[{"award-number":["62122050"]}]},{"name":"China NSFC Projects","award":["62071288"],"award-info":[{"award-number":["62071288"]}]},{"name":"Shanghai Municipal Science and Technology Commission Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2023.3331949","type":"journal-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T19:08:12Z","timestamp":1699643292000},"page":"529-541","source":"Crossref","is-referenced-by-count":36,"title":["Self-Supervised Learning With Cluster-Aware-DINO for High-Performance Robust Speaker Verification"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6319-6755","authenticated-orcid":false,"given":"Bing","family":"Han","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1293-8146","authenticated-orcid":false,"given":"Zhengyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering & MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-742"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref4","article-title":"But system description to voxceleb speaker recognition challenge 2019","author":"Zeinali","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746050"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747172"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2357"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362097"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref14","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.","author":"Baevski","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2842"},{"key":"ref19","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":"ref20","article-title":"Unsupervised representation learning for speaker recognition via contrastive equilibrium learning","author":"Mun","year":"2020"},{"key":"ref21","article-title":"Augmentation adversarial training for self-supervised speaker recognition","author":"Huh","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414713"},{"key":"ref26","article-title":"The idlab voxceleb speaker recognition challenge 2020 system description","author":"Thienpondt","year":"2020"},{"key":"ref27","article-title":"The JHU submission to voxsrc-21: Track 3","author":"Cho","year":"2021"},{"key":"ref28","article-title":"SNU-HIL system for the voxceleb speaker recognition challenge 2021","author":"Mun","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162078"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2765832"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3169977"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11141"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3198315"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3197315"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-126"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1202"},{"key":"ref40","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref42","article-title":"The dku-dukeece system for the self-supervision speaker verification task of the 2021 voxceleb speaker recognition challenge","author":"Cai","year":"2021"},{"key":"ref43","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref44","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref45","article-title":"In defense of pseudo-labeling: An uncertainty-aware pseudo-label selection framework for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rizve","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref47","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arazo","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref49","first-page":"896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2013"},{"key":"ref50","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980991"},{"key":"ref53","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00566"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-803"},{"key":"ref66","article-title":"Voxsrc 2020: The second voxceleb speaker recognition challenge","author":"Nagrani","year":"2020"},{"key":"ref67","article-title":"Voxsrc 2021: The third voxceleb speaker recognition challenge","author":"Brown","year":"2022"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10314722.pdf?arnumber=10314722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T01:13:06Z","timestamp":1703034786000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10314722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3331949","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}