{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T13:20:44Z","timestamp":1772371244924,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["62122050"],"award-info":[{"award-number":["62122050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071288"],"award-info":[{"award-number":["62071288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3140552","type":"journal-article","created":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T20:38:29Z","timestamp":1641415109000},"page":"394-403","source":"Crossref","is-referenced-by-count":17,"title":["Optimizing Data Usage for Low-Resource Speech Recognition"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"first","affiliation":[{"name":"X-LANCE, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4626-2677","authenticated-orcid":false,"given":"Zhikai","family":"Zhou","sequence":"additional","affiliation":[{"name":"X-LANCE, Department of Computer Science and Engineering and MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"IARPA babel program","author":"Harper","year":"2012"},{"key":"ref2","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ardila","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288862"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-11"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707764"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163957"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053112"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-16"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2092"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2593"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-448"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1511"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref24","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414641"},{"key":"ref26","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"Zhang","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-022-02075-7"},{"key":"ref30","first-page":"1","article-title":"Language id-based training of multilingual stacked bottleneck features","volume-title":"Proc. 15th Annu. Conf. Int. Speech Commun. Assoc.","author":"Cutler","year":"2014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-598"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref33","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref36","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref41","article-title":"Multilingual training and cross-lingual adaptation on CTC-based acoustic model","author":"Tong","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101077"},{"key":"ref43","article-title":"Multilingual end-to-end speech recognition with a single transformer on low-resource languages","author":"Zhou","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref45","first-page":"7059","article-title":"Cross-lingual language model pretraining","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lample","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.352"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054130"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1679"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref51","article-title":"The kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref52","article-title":"Audio manipulation tool","author":"SoX","year":"2015"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09670678.pdf?arnumber=9670678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:09:44Z","timestamp":1705183784000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9670678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3140552","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}