{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T21:53:42Z","timestamp":1792101222821,"version":"4.4.0"},"reference-count":34,"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":[{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12204509"],"award-info":[{"award-number":["12204509"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3377593","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T20:33:29Z","timestamp":1710794009000},"page":"880-884","source":"Crossref","is-referenced-by-count":9,"title":["Prototype Division for Self-Supervised Speaker Verification"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7376-0441","authenticated-orcid":false,"given":"Zhenduo","family":"Zhao","sequence":"first","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5650-6703","authenticated-orcid":false,"given":"Zhuo","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7387-509X","authenticated-orcid":false,"given":"Xueshuai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9567-9076","authenticated-orcid":false,"given":"Wenchao","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6838-5160","authenticated-orcid":false,"given":"Pengyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3197315"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747526"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268568"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096925"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00975"},{"key":"ref7","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Chen","year":"2020"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01549"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3198315"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1202"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3331949"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096915"},{"key":"ref15","article-title":"Ensemble distillation network: Learning robust speaker representations without supervision","author":"Chen","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022470"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref20","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref21","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Caron","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054017"},{"key":"ref24","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095051"},{"key":"ref28","article-title":"Augmentation adversarial training for self-supervised speaker recognition","author":"Huh","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref31","article-title":"Unsupervised representation learning for speaker recognition via contrastive equilibrium learning","author":"Mun","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-742"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10380231\/10472570.pdf?arnumber=10472570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T15:17:38Z","timestamp":1711984658000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10472570\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3377593","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}