{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T07:35:37Z","timestamp":1767771337163,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747667","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6877-6881","source":"Crossref","is-referenced-by-count":25,"title":["Improved Language Identification Through Cross-Lingual Self-Supervised Learning"],"prefix":"10.1109","author":[{"given":"Andros","family":"Tjandra","sequence":"first","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diptanu Gon","family":"Choudhury","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kritika","family":"Singh","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexis","family":"Conneau","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexei","family":"Baevski","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Assaf","family":"Sela","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yatharth","family":"Saraf","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Auli","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"10524","article-title":"On layer normalization in the transformer architecture","author":"xiong","year":"2020","journal-title":"ICML"},{"key":"ref32","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-2019"},{"key":"ref31","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"ICLRE"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification.","author":"snyder","year":"2017","journal-title":"InterSpeech"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICASSP.2009.4960588"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP.2013.6639348"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1007\/s12046-011-0050-4"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/SLT.2018.8639655"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP.2018.8461972"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.21437\/Interspeech.2019-2858"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP.2019.8682674"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Interspeech.2020-2831"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/TSA.1996.481450"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICASSP.2014.6854622"},{"key":"ref28","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"ICLRE"},{"key":"ref4","article-title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","author":"synnaeve","year":"2020","journal-title":"Proc of ICML workshop on Self-supervision in Audio and Speech (SAS)"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/TPAMI.2010.57"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref29","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2017","journal-title":"ICLRE"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref8","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.21437\/Interspeech.2018-2341"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.21437\/Interspeech.2020-3015"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP.2010.5495646"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref20","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"Proc of NIPS"},{"key":"ref22","article-title":"Exploring wav2vec 2.0 on speaker verification and language identification","author":"fan","year":"2020","journal-title":"2012 arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref24","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020","journal-title":"arXiv preprint arXiv 2010 10504"},{"key":"ref23","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020","journal-title":"arXiv preprint arXiv 2006 13823"},{"key":"ref26","first-page":"arxiv?1607","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"ArXiv e-prints"},{"key":"ref25","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Neural Information Processing Systems 2017"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747667.pdf?arnumber=9747667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:31Z","timestamp":1660594291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747667","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}