{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:45:51Z","timestamp":1753602351016,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639564","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"1044-1051","source":"Crossref","is-referenced-by-count":7,"title":["Teacher-Student Training for Text-Independent Speaker Recognition"],"prefix":"10.1109","author":[{"given":"Raymond W. M.","family":"Ng","sequence":"first","affiliation":[]},{"given":"Xuechen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Pawel","family":"Swietojanski","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"NIPS"},{"key":"ref33","article-title":"Discriminatively trained probablistic linear discriminant analysis for speaker verification","author":"burget","year":"2011","journal-title":"Proc ICASSP"},{"key":"ref32","article-title":"Bayesian speaker verification with heavy-tailed priors","author":"kenny","year":"2010","journal-title":"Proc Speaker Odyssey"},{"key":"ref31","article-title":"EM for probabilistic LDA","author":"brummer","year":"2010","journal-title":"Tech Rep"},{"key":"ref30","article-title":"The speaker in the wild (SITW) speaker recognition database","author":"mclaren","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref37","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"8","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-981"},{"year":"2016","key":"ref35","article-title":"The speaker in the wild (sitw) speaker recognition challenge"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-504","article-title":"The DET curve in assessment of detection task performance","author":"martin","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref10","article-title":"End-to-end text-dependent speaker verification","author":"heighold","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref11","article-title":"End-to-end attention based text-dependent speaker verification","author":"chen","year":"2016","journal-title":"Proc IEEE SLT"},{"key":"ref12","article-title":"Deep speaker: an end-to-end neural speaker embeeding system","author":"li","year":"2017","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1608","article-title":"End-to-end text-independent speaker verification with triplet loss on short utterances","author":"zhang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref16","article-title":"Learning small-size dnn with output-distribution-based criteria","author":"li","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref17","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953163"},{"key":"ref19","article-title":"Sequence student-teacher training of deep neural networks","author":"wong","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707744"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-128","article-title":"Using I-vector space model for emotion recognition","author":"xia","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.260362"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref1","article-title":"Text-dependent speaker recognition using PLDA with uncertainty propagration","author":"stafylakis","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref22","article-title":"Parallel training of deep neural networks with natural gradient and parameter averaging","author":"povey","year":"0","journal-title":"CoRR"},{"key":"ref21","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref24","article-title":"Cosine similarity scoring without score normalization techniques","author":"deha","year":"2010","journal-title":"Proc Speaker Odyssey"},{"key":"ref23","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"Deep Learning and Representation Learning Workshop NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430116"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-329","article-title":"Language recognition in ivectors space","author":"mart\u00ednez","year":"2011","journal-title":"Proc INTERSPEECH"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639564.pdf?arnumber=8639564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,11]],"date-time":"2022-09-11T22:19:38Z","timestamp":1662934778000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639564\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639564","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}