{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:20:32Z","timestamp":1778692832511,"version":"3.51.4"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876160"],"award-info":[{"award-number":["61876160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001405"],"award-info":[{"award-number":["62001405"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["20720210087"],"award-info":[{"award-number":["20720210087"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3169977","type":"journal-article","created":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T15:37:08Z","timestamp":1650987428000},"page":"1586-1599","source":"Crossref","is-referenced-by-count":9,"title":["When Speaker Recognition Meets Noisy Labels: Optimizations for Front-Ends and Back-Ends"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5021-2648","authenticated-orcid":false,"given":"Lin","family":"Li","sequence":"first","affiliation":[{"name":"XMU Speech Lab and the School of Electronic Science and Engineering, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-1843","authenticated-orcid":false,"given":"Fuchuan","family":"Tong","sequence":"additional","affiliation":[{"name":"XMU Speech Lab and the School of Electronic Science and Engineering, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7380-8690","authenticated-orcid":false,"given":"Qingyang","family":"Hong","sequence":"additional","affiliation":[{"name":"XMU Speech Lab and the School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101033"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101026"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref7","first-page":"194","article-title":"The speaker partitioning problem","volume-title":"Proc. Odyssey","author":"Brmmer","year":"2010"},{"key":"ref8","first-page":"14","article-title":"Bayesian speaker verification with heavy-tailed priors","volume-title":"Proc. Odyssey","author":"Kenny","year":"2010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3039573"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-53"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1351"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053585"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00365"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref22","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"Reed","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00582"},{"key":"ref24","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arazo","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00945"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152527"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_43"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2877939"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_38"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01150"},{"key":"ref31","first-page":"2712","article-title":"Using pre-training can improve model robustness and uncertainty","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hendrycks","year":"2019"},{"key":"ref32","first-page":"1","article-title":"Curriculum loss: Robust learning and generalization against label corruption","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lyu","year":"2020"},{"key":"ref33","first-page":"1","article-title":"Self: Learning to filter noisy labels with self-ensembling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nguyen","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1442"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1395"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746294"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-33"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3130980"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2021"},{"key":"ref40","article-title":"Switchboard-2 phase II","author":"Graff","year":"1999"},{"key":"ref41","article-title":"Switchboard-2 phase III","author":"Graff","year":"2002"},{"key":"ref42","article-title":"Switchboard cellular part 1 audio","author":"Graff","year":"2001"},{"key":"ref43","article-title":"Switchboard cellular part 2 audio","author":"Graff","year":"2004"},{"key":"ref44","article-title":"NIST SRE CTS superset: A large-scale dataset for telephony speaker recognition","author":"Sadjadi","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44415-3_47"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2014-39"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3004760"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682852"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016498"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-020-00183-3"},{"key":"ref52","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.22"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00906"},{"key":"ref55","first-page":"1558","article-title":"Learning discrete representations via information maximizing self-augmented training","volume-title":"Proc. Proc. Int. Conf. Mach. Learn.","author":"Hu","year":"2017"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2357"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023165"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2264"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.414"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2672557"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915322"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-458"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414676"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09763412.pdf?arnumber=9763412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T15:14:49Z","timestamp":1705936489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9763412\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3169977","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.17121863.v2","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.17121863.v1","asserted-by":"object"}]},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}