{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T05:07:36Z","timestamp":1782623256895,"version":"3.54.5"},"reference-count":82,"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":"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1836219"],"award-info":[{"award-number":["U1836219"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China"}],"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.2022.3184480","type":"journal-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T20:32:44Z","timestamp":1655757164000},"page":"1227-1241","source":"Crossref","is-referenced-by-count":69,"title":["Improving Automatic Speech Recognition Performance for Low-Resource Languages With Self-Supervised Models"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3172-2837","authenticated-orcid":false,"given":"Jing","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3841-1959","authenticated-orcid":false,"given":"Wei-Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Ethnologue: Languages of the world","author":"Eberhard","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638959"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2015.2422573"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461802"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-481"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707763"},{"key":"ref7","first-page":"1","article-title":"Towards improving low-resource speech recognition using articulatory and language features","volume-title":"Proc. Int. Workshop Spoken Lang. Transl.","volume":"45","author":"Mller","year":"2016"},{"key":"ref8","article-title":"Multilingual speech recognition for low-resource indian languages using multi-task conformer","year":"2021"},{"key":"ref9","article-title":"Multilingual techniques for low resource automatic speech recognition","author":"Chuangsuwanich","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2062"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854673"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053112"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2015-711"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-207"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SSD.2019.8893184"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2226"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1473"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-349"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1873"},{"key":"ref25","first-page":"1","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2019"},{"key":"ref26","first-page":"1","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref32","article-title":"OpenASR21 challenge (open automatic speech recognition 2021 challenge) evaluation plan","year":"2021"},{"key":"ref33","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Kornblith","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.427"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1074"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/app12020903"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1417"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688260"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-303"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref44","first-page":"16","article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED","volume-title":"Proc. Workshop Spoken Lang. Technol. Under-resourced Lang.","author":"Gales","year":"2014"},{"key":"ref45","article-title":"CLSRIL-23: Cross lingual speech representations for indic languages","author":"Gupta","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-787"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref52","first-page":"4218","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proc. Lang. Resour. Eval. Conf.","author":"Ardila","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1163\/2210-7363_ecll_com_00000029"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1017\/S0025100300006423"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1075\/loall.10"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.4324\/9781315722580"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1044\/1058-0360(2002\/031)"},{"key":"ref64","article-title":"A fine-tuned wav2vec 2.0\/HuBERT benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021"},{"key":"ref65","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746852"},{"key":"ref68","article-title":"Speech representation learning through self-supervised pretraining and multi-task finetuning","author":"Chen","year":"2021"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-60"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-556"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3071668"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-807"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3078715"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1843"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053808"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1007"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.96"},{"key":"ref81","first-page":"90","article-title":"Multilingual bottle-neck features and its application for under-resourced languages","volume-title":"Proc. Spoken Lang. Technol. Under-Resourced Lang.","author":"Vu","year":"2012"},{"key":"ref82","first-page":"1","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09801640.pdf?arnumber=9801640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:37:25Z","timestamp":1706758645000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9801640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":82,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3184480","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}