{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T10:40:27Z","timestamp":1778668827703,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"China NSFC project","award":["61603252"],"award-info":[{"award-number":["61603252"]}]},{"name":"China NSFC project","award":["U1736202"],"award-info":[{"award-number":["U1736202"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1109\/taslp.2019.2928128","type":"journal-article","created":{"date-parts":[[2019,7,11]],"date-time":"2019-07-11T20:07:08Z","timestamp":1562875628000},"page":"1686-1696","source":"Crossref","is-referenced-by-count":33,"title":["Discriminative Neural Embedding Learning for Short-Duration Text-Independent Speaker Verification"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1523-9631","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zili","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-9826","authenticated-orcid":false,"given":"Kai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-452"},{"key":"ref32","first-page":"1136","article-title":"Locally-connected and convolutional neural networks for small footprint speaker recognition","author":"chen","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853888"},{"key":"ref30","first-page":"214","article-title":"Non-linear PLDA for i-vector speaker verification","author":"novoselov","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref37","article-title":"Generalized end-to-end loss for speaker verification","author":"wan","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846261"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462025"},{"key":"ref34","first-page":"5359","article-title":"Attention-based models for text-dependent speaker verification","author":"chowdhury","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-31"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462508"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-430"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref20","first-page":"185","article-title":"Multi-task learning for text-dependent speaker verification","author":"chen","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1125"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref23","first-page":"2","article-title":"Deep neural network based text-dependent speaker recognition: Preliminary results","author":"bhattacharya","year":"2016","journal-title":"Proc Odyssey"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1608"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2765832"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02698-1_20"},{"key":"ref55","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-458"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462620"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref11","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/34.598228"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref13","first-page":"293","article-title":"Deep neural networks for extracting Baum-Welch statistics for speaker recognition","author":"kenny","year":"0","journal-title":"Proc Odyssey"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.07.003"},{"key":"ref16","first-page":"1327","article-title":"Tandem deep features for text-dependent speaker verification","author":"fu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","first-page":"1151","article-title":"Investigation of bottleneck features and multilingual deep neural networks for speaker verification","author":"tian","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref18","article-title":"A unified deep neural network for speaker and language recognition","author":"richardson","year":"2015","journal-title":"arXiv 1504 00923"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415306"},{"key":"ref4","article-title":"Joint factor analysis of speaker and session variability: Theory and algorithms","author":"kenny","year":"2005"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659966"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref8","first-page":"1","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461747"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref46","first-page":"33","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref45","first-page":"249","article-title":"Analysis of i-vector length normalization in speaker recognition systems","author":"garcia-romero","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref42","first-page":"34","article-title":"The speaker partitioning problem","author":"br\u00fcmmer","year":"0","journal-title":"Proc Odyssey"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-25"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref43","first-page":"14","article-title":"Bayesian speaker verification with heavy-tailed priors","author":"kenny","year":"0","journal-title":"Proc Odyssey"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8784423\/08759958.pdf?arnumber=8759958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:05:11Z","timestamp":1657746311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8759958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":56,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2928128","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}