{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T22:33:17Z","timestamp":1787610797166,"version":"build-2736575974"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2018,5,1]],"date-time":"2018-05-01T00:00:00Z","timestamp":1525132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","award":["FA8750-15-1-0205"],"award-info":[{"award-number":["FA8750-15-1-0205"]}],"id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University of Texas at Dallas from the Distinguished University Chair in Telecommunications Engineering held by J. H. L. Hansen"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/taslp.2018.2797420","type":"journal-article","created":{"date-parts":[[2018,1,24]],"date-time":"2018-01-24T19:22:25Z","timestamp":1516821745000},"page":"873-882","source":"Crossref","is-referenced-by-count":34,"title":["Language\/Dialect Recognition Based on Unsupervised Deep Learning"],"prefix":"10.1109","volume":"26","author":[{"given":"Qian","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1382-9929","authenticated-orcid":false,"given":"John H. L.","family":"Hansen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref32","first-page":"165","article-title":"The 2009 NIST language recognition evaluation","author":"martin","year":"2010","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref31","first-page":"30","article-title":"Arabic dialect identification - ‘Is the secret in the silence?’ and other observations","author":"bo?il","year":"2012","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref30","first-page":"2934","article-title":"Automatic dialect detection in arabic broadcast speech","author":"ali","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078629"},{"key":"ref35","first-page":"2867","article-title":"Speaker adaptation using the i-vector technique for bottleneck features","author":"cardinal","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref34","article-title":"Focal multi-classtools for evaluation, calibration and fusion of, and decision-making with, multi-class statistical pattern recognition scores","author":"br\u00fcmmer","year":"2007"},{"key":"ref10","first-page":"757","article-title":"Language identification using Gaussian mixture model tokenization","author":"torres-carrasquillo","year":"2002","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref12","first-page":"861","article-title":"Language recognition in iVectors space","author":"mart?nez","year":"2011","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ODYSSEY.2006.248100"},{"key":"ref14","first-page":"213","article-title":"Identification of British English regional accents using fusion of i-vector and multi-accent phonotactic systems","year":"2016","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"293","DOI":"10.21437\/Odyssey.2014-44","article-title":"Deep neural networks for extracting baum-welch statistics for speaker recognition","author":"kenny","year":"2014","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref18","first-page":"152","article-title":"Robust langauge recognition based on diverse feature","author":"zhang","year":"2014","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"299","DOI":"10.21437\/Odyssey.2014-45","article-title":"Neural network bottleneck features for language identification","author":"matejka","year":"2014","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2237903"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.04.010"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472744"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-014-9268-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352154"},{"key":"ref29","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recogn Understand ASRU '09"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854362"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078605"},{"key":"ref7","first-page":"1105","article-title":"Speech recognition on code-switching among the chinese dialects","volume":"1","author":"lyu","year":"2006","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process Proc"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639093"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960592"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289008"},{"key":"ref20","first-page":"1","article-title":"Language id-based training of multilingual stacked bottleneck features","author":"zhang","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-624"},{"key":"ref24","article-title":"Adversarial autoencoders","author":"makhzani","year":"2015"},{"key":"ref23","article-title":"Stochastic gradient vb and the variational auto-encoder","author":"kingma","year":"2014","journal-title":"Sec Int Conf Lear Rep ICLR Talk Slides"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075885"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045184"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8318423\/08268099.pdf?arnumber=8268099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T04:08:35Z","timestamp":1660363715000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8268099\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":36,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2797420","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5]]}}}