{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T21:32:57Z","timestamp":1781818377040,"version":"3.54.5"},"reference-count":100,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Council Research Fund","award":["CR-2021-005"],"award-info":[{"award-number":["CR-2021-005"]}]},{"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":"Shenzhen Science and Technology Research Fund Fundamental Research Key Project","award":["JCYJ20220818103001002"],"award-info":[{"award-number":["JCYJ20220818103001002"]}]},{"name":"Internal Project Fund from Shenzhen Research Institute of Big Data","award":["T00120220002"],"award-info":[{"award-number":["T00120220002"]}]}],"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.2024.3385277","type":"journal-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T17:31:39Z","timestamp":1712943099000},"page":"2324-2337","source":"Crossref","is-referenced-by-count":25,"title":["<i>Golden Gemini<\/i> is All You Need: Finding the Sweet Spots for Speaker Verification"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3472-0703","authenticated-orcid":false,"given":"Tianchi","family":"Liu","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A*STAR), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9133-3000","authenticated-orcid":false,"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9903-0618","authenticated-orcid":false,"given":"Qiongqiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I<sup>2<\/sup>R), Agency for Science, Technology and Research (A*STAR), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.03.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947437"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3287733"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10055"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101258"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097032"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362097"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3091932"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3161155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref19","article-title":"BUT system description to VoxCeleb speaker recognition challenge 2019","author":"Zeinali","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3273417"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-484"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233231"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1294"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413948"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746294"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747384"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746688"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688031"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096814"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746050"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1446"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1570"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1513"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023305"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096659"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095051"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3143036"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-563"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-697"},{"key":"ref48","article-title":"SRC 2021: The third VoxCeleb speaker recognition challenge","author":"Brown","year":"2022"},{"key":"ref49","article-title":"SRC 2022: The fourth VoxCeleb speaker recognition challenge","author":"Huh","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","article-title":"ID R&D system description to VoxCeleb Speaker Recognition Challenge 2022","author":"Makarov","year":"2022"},{"key":"ref52","article-title":"The HCCL system for VoxCeleb speaker recognition challenge 2022","author":"Zhao"},{"key":"ref53","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":"ref54","article-title":"The SpeakIn system for VoxCeleb speaker recognition challenge","author":"Zhao","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3153258"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097239"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-574"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097232"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094752"},{"key":"ref62","first-page":"3927","article-title":"Is someone speaking? Exploring long-term temporal features for audio-visual active speaker detection","volume-title":"Proc. ACM Int. Conf. Multimedia","author":"Tao","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413832"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096449"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746820"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288417"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3251895"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413501"},{"key":"ref69","article-title":"The effectiveness of data augmentation in image classification using deep learning","author":"Perez","year":"2017"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853584"},{"key":"ref72","first-page":"50221","article-title":"Disentangling voice and content with self-supervision for speaker recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1818"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1994"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/5.628714"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318526"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref84","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref85","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1508"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref90","article-title":"Bayesian speaker verification with heavy-tailed priors","volume-title":"Proc. Process. Speaker Lang. Recognit. Workshop","author":"Kenny","year":"2010"},{"key":"ref91","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref92","first-page":"1567","article-title":"Analysis of score normalization in multilingual speaker recognition","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Matjka","year":"2017"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097019"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746247"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414676"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095415"},{"key":"ref98","article-title":"DS-TDNN: Dual-stream time-delay neural network with global-aware filter for speaker verification","author":"Li","year":"2023"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-402"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-777"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10497864.pdf?arnumber=10497864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T04:25:01Z","timestamp":1713587101000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10497864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3385277","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}