{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T17:13:25Z","timestamp":1767978805806,"version":"3.49.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Huawei Noah's Ark Lab"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271432"],"award-info":[{"award-number":["62271432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Internal Project Fund from Shenzhen Research Institute of Big Data","award":["T00120220002"],"award-info":[{"award-number":["T00120220002"]}]},{"name":"Human-Robot Collaborative AI for Advanced Manufacturing and Engineering","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]},{"name":"Science, Technology and Research, Singapore"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3268568","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T21:14:55Z","timestamp":1682025295000},"page":"1706-1719","source":"Crossref","is-referenced-by-count":12,"title":["Self-Supervised Training of Speaker Encoder With Multi-Modal Diverse Positive Pairs"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0021-5661","authenticated-orcid":false,"given":"Ruijie","family":"Tao","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9133-3000","authenticated-orcid":false,"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"Singapore Institute of Technology, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1332-3357","authenticated-orcid":false,"given":"Rohan Kumar","family":"Das","sequence":"additional","affiliation":[{"name":"Fortemedia, Singapore"}]},{"given":"Ville","family":"Hautam\u00e4ki","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101058"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659567"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414713"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413351"},{"key":"ref17","article-title":"Augmentation adversarial training for unsupervised speaker recognition","volume-title":"Proc. Workshop Self-Supervised Learn. Speech Audio Process.","author":"Huh","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_16"},{"key":"ref21","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3057230"},{"key":"ref23","first-page":"605","article-title":"HLT-NUS submission for 2019 NIST multimedia speaker recognition evaluation","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Das","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref25","article-title":"The phonexia voxceleb speaker recognition challenge 2021 system description","author":"Slavek","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1602"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023277"},{"key":"ref36","article-title":"Unsupervised representation learning for speaker recognition via contrastive equilibrium learning","author":"Mun","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747526"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414973"},{"key":"ref39","article-title":"The IDLAB VoxCeleb speaker recognition challenge 2020 system description","author":"Thienpondt","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3197315"},{"key":"ref41","article-title":"Self-supervised curriculum learning for speaker verification","author":"Heo","year":"2022"},{"key":"ref42","article-title":"Raw waveform speaker verification for supervised and self-supervised learning","author":"Jung","year":"2022"},{"key":"ref43","article-title":"VoxSRC 2021: The third voxceleb speaker recognition challenge","author":"Brown","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747162"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref46","article-title":"NIST 2021 speaker recognition evaluation plan","author":"Sadjadi","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414260"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-49"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-37"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162078"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref57","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref58","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Berthelot","year":"2019"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"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","first-page":"1641","article-title":"Semi-supervised contrastive learning with generalized contrastive loss and its application to speaker recognition","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Inoue","year":"2020"},{"key":"ref66","article-title":"HLT-NUS submission for 2020 NIST conversational telephone speech SRE","author":"Das","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1570"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-803"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10106039.pdf?arnumber=10106039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T03:20:04Z","timestamp":1709263204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10106039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3268568","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}