{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:54:26Z","timestamp":1763621666792,"version":"3.37.3"},"reference-count":81,"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":[{"name":"2023 Research Fund of the University of Seoul"}],"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.2024.3381005","type":"journal-article","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T18:09:36Z","timestamp":1711130976000},"page":"2269-2282","source":"Crossref","is-referenced-by-count":3,"title":["FA-ExU-Net: The Simultaneous Training of an Embedding Extractor and Enhancement Model for a Speaker Verification System Robust to Short Noisy Utterances"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6468-1368","authenticated-orcid":false,"given":"Ju-ho","family":"Kim","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Seoul, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7977-2789","authenticated-orcid":false,"given":"Jungwoo","family":"Heo","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Seoul, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6022-7674","authenticated-orcid":false,"given":"Hyun-seo","family":"Shin","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Seoul, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6671-5004","authenticated-orcid":false,"given":"Chan-yeong","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Seoul, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3657-0665","authenticated-orcid":false,"given":"Ha-Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Seoul, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865704310024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3206541"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-155"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.365379"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659966"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref10","article-title":"Bayesian speaker verification with heavy-tailed priors","volume-title":"Proc. Odyssey Speaker Lang. Recognit. Workshop","author":"Kenny","year":"2010"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854362"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1575"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413564"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1857"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11270"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053871"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2240"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1489"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1980022.1980160"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472647"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846281"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1496"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"article-title":"MUSAN: A music, speech, and noise corpus","year":"2015","author":"Snyder","key":"ref34"},{"key":"ref35","first-page":"1","article-title":"Factor analysis modelling for speaker verification with short utterances","volume-title":"Proc. Odyssey: Speaker Lang. Recognit. Workshop","author":"Vogt","year":"2008"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.01.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004029"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1564"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054036"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-020-09711-0"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3025941"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288811"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462365"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053407"},{"key":"ref45","first-page":"213","article-title":"Feature warping for robust speaker verification","volume-title":"Proc. Odyssey: Speaker Recognit. Workshop","author":"Pelecanos","year":"2001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-25"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1978"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICNSC.2008.4525324"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-26"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2872"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1704"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.106"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682712"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1454"},{"article-title":"On the convergence of adam and beyond","year":"2019","author":"Reddi","key":"ref61"},{"article-title":"SGDR: Stochastic gradient descent with warm restarts","year":"2016","author":"Loshchilov","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10932"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3161155"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101426"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.09.014"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746529"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746456"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746294"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1163"},{"key":"ref73","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383579"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1283"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10350"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747778"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-29"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10478124.pdf?arnumber=10478124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T06:40:33Z","timestamp":1712904033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10478124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3381005","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}