{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:26:28Z","timestamp":1770917188241,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AI Singapore Programme"},{"name":"AISG","award":["AISG-100E-2018-006"],"award-info":[{"award-number":["AISG-100E-2018-006"]}]},{"DOI":"10.13039\/501100005049","name":"Science and Engineering Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005049","id-type":"DOI","asserted-by":"publisher"}]},{"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":"National Robotics Program"},{"name":"Human-Robot Interaction Phase 1","award":["192 25 00054"],"award-info":[{"award-number":["192 25 00054"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3100682","type":"journal-article","created":{"date-parts":[[2021,7,29]],"date-time":"2021-07-29T20:19:03Z","timestamp":1627589943000},"page":"2696-2709","source":"Crossref","is-referenced-by-count":27,"title":["Target Speaker Verification With Selective Auditory Attention for Single and Multi-Talker Speech"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1584-6282","authenticated-orcid":false,"given":"Chenglin","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7237-0874","authenticated-orcid":false,"given":"Wei","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0135-4188","authenticated-orcid":false,"given":"Jibin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639586"},{"key":"ref33","first-page":"1","article-title":"Attention-based multi-task learning for speech-enhancement and speaker-identification in multi-speaker dialogue scenario","author":"peng","year":"2021","journal-title":"Proc IEEE Int Symp Circuits Syst"},{"key":"ref32","article-title":"Exploring multi-channel features for speaker verification with joint vad and speech enhancement","author":"kataria","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2986896"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1410"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2243436"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1205"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1397"},{"key":"ref2","article-title":"Bayesian speaker verification with heavy-tailed priors","volume":"14","author":"kenny","year":"2010","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462471"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1150"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683874"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2831456"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1144"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-981"},{"key":"ref40","article-title":"Universal speaker extraction in the presence and absence of target speakers for speech of one and two talkers","author":"borsdorf","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-945"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639163"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2346315"},{"key":"ref15","first-page":"433","article-title":"Personal vad: Speaker-conditioned voice activity detection","author":"ding","year":"2019","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref3","first-page":"249","article-title":"Analysis of i-vector length normalization in speaker recognition systems","author":"garcia-romero","year":"2011","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683760"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1197"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"2579","DOI":"10.21437\/Interspeech.2009-679","article-title":"Nist 2008 speaker recognition evaluation: Performance across telephone and room microphone channels","author":"martin","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref45","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"2726","DOI":"10.21437\/Interspeech.2010-722","article-title":"The nist 2010 speaker recognition evaluation","author":"martin","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref42","article-title":"Csr-i (wsj0) complete ldc93s6a","author":"garofolo","year":"1993","journal-title":"Philadelphia Linguistic Data Consortium"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415220"},{"key":"ref44","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"cosentino","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09502020.pdf?arnumber=9502020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,5]],"date-time":"2023-01-05T21:56:59Z","timestamp":1672955819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9502020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3100682","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}