{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:31:37Z","timestamp":1783225897473,"version":"3.54.6"},"reference-count":55,"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\/100004318","name":"Microsoft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004520","name":"Tokyo Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004520","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016909","name":"Microsoft Research Asia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016909","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.2021.3138674","type":"journal-article","created":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T21:22:55Z","timestamp":1640726575000},"page":"317-329","source":"Crossref","is-referenced-by-count":49,"title":["Exploiting Adapters for Cross-Lingual Low-Resource Speech Recognition"],"prefix":"10.1109","volume":"30","author":[{"given":"Wenxin","family":"Hou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yidong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4833-0880","authenticated-orcid":false,"given":"Jindong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7566-7948","authenticated-orcid":false,"given":"Renjun","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8114-8450","authenticated-orcid":false,"given":"Takahiro","family":"Shinozaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/sym11081018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-57"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref7","article-title":"Multilingual techniques for low resource automatic speech recognition","author":"Chuangsuwanich","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref9","article-title":"Multilingual end-to-end speech recognition with a single transformer on low-resource languages","author":"Zhou","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053112"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414959"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1390"},{"key":"ref14","first-page":"487","article-title":"AdapterFusion: Non-destructive task composition for transfer learning","volume-title":"Proc. 16th Conf. Eur. Chapter Assoc. Comput. Linguistics, Main Volume","author":"Pfeiffer","year":"2021"},{"key":"ref15","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/applin\/aml033"},{"issue":"10","key":"ref17","volume-title":"The Origin of Speech","author":"MacNeilage","year":"2010"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/5190.003.0019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268945"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053443"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461771"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref28","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17661"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref31","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":"ref32","first-page":"1","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":"ref33","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1165"},{"key":"ref35","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.ngt-1.5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.421"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/508"},{"key":"ref40","first-page":"7059","article-title":"Cross-lingual language model pretraining","volume-title":"Advances Neural Inf. Process. Syst.","volume":"32","author":"Lample","year":"2019"},{"key":"ref41","first-page":"646","article-title":"Learning to generate task-specific adapters from task description","volume-title":"Proc. 59th Annu. Meeting Assoc. Comput. Linguistics 11th Int. Joint Conf. Natural Lang. Process.","volume":"2","author":"Ye","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.105"},{"key":"ref43","article-title":"Scalable and efficient MoE training for multitask multilingual models","author":"Kim","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref46","article-title":"Meta-learning: A survey","author":"Vanschoren","year":"2018"},{"key":"ref47","first-page":"2","volume-title":"Statistical Learn. Theory","volume":"1","author":"Vapnik","year":"1998"},{"key":"ref48","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":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref50","first-page":"1","article-title":"The kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Automat. Speech Recognit. Understanding Signal Process. Soc.","author":"Povey","year":"2011"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09664307.pdf?arnumber=9664307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T21:59:34Z","timestamp":1705183174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9664307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3138674","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}