{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T21:36:02Z","timestamp":1777930562483,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"iSocioBot project"},{"name":"Danish Council for Independent Research-Technology and Production Sciences","award":["1335-00162"],"award-info":[{"award-number":["1335-00162"]}]},{"name":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge MA, USA"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/taslp.2019.2915322","type":"journal-article","created":{"date-parts":[[2019,5,8]],"date-time":"2019-05-08T00:52:43Z","timestamp":1557276763000},"page":"1267-1279","source":"Crossref","is-referenced-by-count":20,"title":["Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification"],"prefix":"10.1109","volume":"27","author":[{"given":"Achintya Kumar","family":"Sarkar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6856-8928","authenticated-orcid":false,"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suwon","family":"Shon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Glass","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2579","article-title":"Visualizing high-dimensional data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref38","year":"2016","journal-title":"The reddots challenge Towards characterizing speakers from short utterances"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553469"},{"key":"ref32","article-title":"Unsupervised feature learning from temporal data","author":"goroshin","year":"0","journal-title":"Proc Workshop Int Conf Learn Represent"},{"key":"ref31","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","first-page":"2996","article-title":"The reddots data collection for speaker recognition","author":"lee","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref36","first-page":"413","article-title":"Multilingual tandem bottleneck feature for language identification","author":"geng","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref35","article-title":"Time-contrastive learning based DNN bottleneck features for text-dependent speaker verification","author":"sarkar","year":"2017","journal-title":"Proc NIPS 2017 Time Series Workshop"},{"key":"ref34","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.06.008"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1584"},{"key":"ref29","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"hsu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref1","first-page":"3772","article-title":"Unsupervised feature extraction by time-contrastive learning and nonlinear ICA","author":"hyvarinen","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1422"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2323432"},{"key":"ref24","first-page":"1858","article-title":"Unsupervised learning of spoken language with visual context","author":"harwath","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1182"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"ref51","author":"young","year":"2006","journal-title":"The HTK Book"},{"key":"ref56","first-page":"1895","article-title":"The DET curve in assessment of detection task performance","author":"martin","year":"0","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref55","first-page":"25","article-title":"Mixture of PLDA models in i-vector space for gender-independent speaker recognition","author":"senoussaoui","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511996504"},{"key":"ref53","first-page":"157","article-title":"Variance-spectra based normalization for i-vector standard and probabilistic linear discriminant analysis","author":"bousquet","year":"0","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846262"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.07.010"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178885"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1769"},{"key":"ref16","first-page":"2008","article-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification","author":"michelsanti","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461423"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref4","first-page":"1492","article-title":"Adversarial network bottleneck features for noise robust speaker verification","author":"yu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref3","first-page":"1327","article-title":"Tandem deep features for text-dependent speaker verification","author":"fu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404844"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.07.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref7","first-page":"2484","article-title":"Augmenting short-term cepstral features with long-term discriminative features for speaker verification of telephone data","author":"do","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref49","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume":"1","author":"macqueen","year":"0","journal-title":"Proc 5th Berkeley Symp Math Statist Probability"},{"key":"ref9","first-page":"105","article-title":"Bottleneck features for speaker recognition","author":"yaman","year":"0","journal-title":"Proc Odyssey"},{"key":"ref46","article-title":"Sequence prediction with neural segmental models","author":"tang","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2752462"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846309"},{"key":"ref47","author":"garofolo","year":"1993","journal-title":"TIMIT Acoust -Phonet Continuous Speech Corpus"},{"key":"ref42","article-title":"An introduction to computational networks and the computational network toolkit","author":"yu","year":"2014"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.03.001"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660023"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8716764\/08708955.pdf?arnumber=8708955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:13:26Z","timestamp":1657746806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8708955\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":56,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2915322","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}