{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:44Z","timestamp":1775230064376,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"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":"Science of Learning Programme","award":["NRF2016-SOL002-011"],"award-info":[{"award-number":["NRF2016-SOL002-011"]}]},{"name":"Centre for Research and Development in Learning"},{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","award":["JHU IO 90071537"],"award-info":[{"award-number":["JHU IO 90071537"]}],"id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2120435"],"award-info":[{"award-number":["2120435"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/jstsp.2022.3201445","type":"journal-article","created":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T19:30:34Z","timestamp":1661369434000},"page":"1296-1307","source":"Crossref","is-referenced-by-count":21,"title":["Efficient Self-Supervised Learning Representations for Spoken Language Identification"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3998-9229","authenticated-orcid":false,"given":"Hexin","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7449-5726","authenticated-orcid":false,"given":"Leibny Paola Garcia","family":"Perera","sequence":"additional","affiliation":[{"name":"CLSP and HLT-COE, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0708-4791","authenticated-orcid":false,"given":"Andy W. H.","family":"Khong","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suzy J.","family":"Styles","sequence":"additional","affiliation":[{"name":"Psychology, School of Social Sciences, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5976-0897","authenticated-orcid":false,"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"CLSP and HLT-COE, Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2237151"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003870"},{"key":"ref3","article-title":"Multilingual speech recognition using knowledge transfer across learning processes","author":"Lahiri","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-328"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682386"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1256"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683313"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.1996.481450"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/79.317925"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2014-45"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref15","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1310"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref20","first-page":"27826","article-title":"Unsupervised speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref23","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747667"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-82"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616048"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref31","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref32","first-page":"69","article-title":"The fisher corpus: A resource for the next generations of speech-to-text","volume-title":"Proc. Lang. Resour. Eval. Conf.","volume":"4","author":"Cieri","year":"2004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-69"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023321"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref37","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. Lang. Resour. Eval. Conf.","author":"Ardila","year":"2019"},{"key":"ref38","first-page":"16","article-title":"Speech recognition and keyword spotting for low-resource languages: BABEL project research at CUED","volume-title":"Proc. Int. Workshop Spoken Lang. Tech. Under-Resourced Lang.","author":"Gales","year":"2014"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref40","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref42","first-page":"16","article-title":"NIST 2007 language recognition evaluation","volume-title":"Proc. Odyssey Speaker Lang. Recognit. Workshop","author":"Martin","year":"2008"},{"key":"ref43","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ioffe","year":"2015"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/4200690\/9923627\/9866521-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09866521.pdf?arnumber=9866521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:35:13Z","timestamp":1706790913000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9866521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":44,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3201445","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}