{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T21:32:58Z","timestamp":1781818378695,"version":"3.54.5"},"reference-count":69,"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":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 108-2221-E-006-103-MY3"],"award-info":[{"award-number":["MOST 108-2221-E-006-103-MY3"]}],"id":[{"id":"10.13039\/501100004663","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":[[2023]]},"DOI":"10.1109\/taslp.2023.3267833","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T18:12:02Z","timestamp":1681755122000},"page":"1745-1757","source":"Crossref","is-referenced-by-count":14,"title":["Decomposition and Reorganization of Phonetic Information for Speaker Embedding Learning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2123-1601","authenticated-orcid":false,"given":"Qian-Bei","family":"Hong","sequence":"first","affiliation":[{"name":"Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University and Academia Sinica, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3947-2123","authenticated-orcid":false,"given":"Chung-Hsien","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5071","authenticated-orcid":false,"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref57","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref12","first-page":"999","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"Proc Annu Conf Int Speech Commun Assoc INTERSPEECH"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-64"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404779"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413815"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462165"},{"key":"ref55","first-page":"1","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"maas","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref51","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref50","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref45","first-page":"2616","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc Annu Conf Int Speech Commun Assoc INTERSPEECH"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980452"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref49","first-page":"223","article-title":"The CMU Arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc ISCA Speech Synth Workshop"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288986"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-58"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659966"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3023101"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894527"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746220"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref37","first-page":"5100","article-title":"Analysis of DNN approaches to speaker identification","author":"matejka","year":"2016","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref36","article-title":"The IDLAB VoxCeleb speaker recognition challenge 2021 system description","author":"thienpondt","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065202"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1226"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053209"},{"key":"ref32","article-title":"BUT system description to VoxCeleb speaker recognition challenge 2019","author":"zeinali","year":"0","journal-title":"Proc VoxCeleb Challange Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2849577"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT49239.2020.9225641"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412155"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659595"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-81"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003826"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462169"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-019-0166-8"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054423"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3036"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413948"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1626"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref28","first-page":"27","article-title":"Speaker recognition via nonlinear discriminant features","author":"stoll","year":"2007","journal-title":"Proc Non-Linear Speech Process"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2323432"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2639323"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10103676.pdf?arnumber=10103676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:41:45Z","timestamp":1685382105000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10103676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3267833","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}