{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:45:02Z","timestamp":1753602302553,"version":"3.37.3"},"reference-count":41,"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":[{"name":"JST CREST","award":["JPMJCR18A6","JPMJCR20D3"],"award-info":[{"award-number":["JPMJCR18A6","JPMJCR20D3"]}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["309629"],"award-info":[{"award-number":["309629"]}],"id":[{"id":"10.13039\/501100002341","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.2021.3138681","type":"journal-article","created":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T21:22:55Z","timestamp":1640726575000},"page":"477-488","source":"Crossref","is-referenced-by-count":6,"title":["Optimizing Tandem Speaker Verification and Anti-Spoofing Systems"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7479-4574","authenticated-orcid":false,"given":"Anssi","family":"Kanervisto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ville","family":"Hautamaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomi","family":"Kinnunen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3955","authenticated-orcid":false,"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(95)00009-D"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3009494"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846308"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1148020.1148022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2651377"},{"volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","year":"2006","author":"Bishop","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2550"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref13","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i18.17893"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-22"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101032"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/89.365379"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.08.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-44"},{"key":"ref21","article-title":"But system description to voxceleb speaker recognition challenge 2019","volume-title":"Proc. VoxSRC Challenge Workshop","author":"Zeinali","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref24","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"2000"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref25"},{"key":"ref26","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref27","first-page":"8026","article-title":"Pytorch: An Imperative Style, High-Performance Deep Learning Library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke","year":"2019"},{"article-title":"Measuring, refining and calibrating speaker and language information extracted from speech","year":"2010","author":"Brummer","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101258"},{"article-title":"A comparison of linear and non-linear calibrations for speaker recognition","year":"2014","author":"Brmmer","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-702"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201259"},{"article-title":"MUSAN: A music, speech, and noise corpus","year":"2015","author":"Snyder","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-29"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44415-3_47"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1768"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-9"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09664367.pdf?arnumber=9664367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T21:59:50Z","timestamp":1705183190000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9664367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3138681","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2022]]}}}