{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:37:55Z","timestamp":1776883075025,"version":"3.51.2"},"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF CCRI Project","award":["2016725"],"award-info":[{"award-number":["2016725"]}]},{"name":"University of Texas at Dallas from the Distinguished University Chair in Telecommunications Engineering"}],"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.2023.3284521","type":"journal-article","created":{"date-parts":[[2023,6,15]],"date-time":"2023-06-15T17:29:35Z","timestamp":1686850175000},"page":"2668-2679","source":"Crossref","is-referenced-by-count":9,"title":["Attention and DCT Based Global Context Modeling for Text-Independent Speaker Recognition"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4734-6256","authenticated-orcid":false,"given":"Wei","family":"Xia","sequence":"first","affiliation":[{"name":"Center for Robust Speech Systems, Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1382-9929","authenticated-orcid":false,"given":"John H. L.","family":"Hansen","sequence":"additional","affiliation":[{"name":"Center for Robust Speech Systems, Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Bayesian speaker verification with heavy-tailed priors","author":"kenny","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00358"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00082"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2430"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01132"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01235"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref11","first-page":"4828","article-title":"Full-covariance UBM and heavy-tailed PLDA in i-vector speaker verification","author":"mat?jka","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref55","first-page":"1","article-title":"On using CNN with DCT based image data","volume":"2","author":"ulicny","year":"0","journal-title":"Proc Ir Mach Vis Image Process Conf"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461587"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900182"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-356"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref46","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1860"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054440"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1845"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688243"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref9","first-page":"1","article-title":"Alexa, are you listening? Privacy perceptions, concerns and privacy-seeking behaviors with smart speakers","author":"lau","year":"0","journal-title":"Proc ACM Hum - Comput Interact"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2871183"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688225"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2961"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1121\/1.5137269"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1852"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1050"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1982"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2177"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682259"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3155286"},{"key":"ref2","first-page":"3317","article-title":"Joint application of speech and speaker recognition for automation and security in smart home","author":"lee","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2470216"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3130975"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2738"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1626"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref67","first-page":"1","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/BigDataSecurity-HPSC-IDS49724.2020.00028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref63","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221042"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref65","article-title":"Clova baseline system for the VoxCeleb speaker recognition challenge 2020","author":"heo","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2831456"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2616"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10153697.pdf?arnumber=10153697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T18:23:54Z","timestamp":1691432634000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10153697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3284521","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}