{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:26:11Z","timestamp":1766298371324,"version":"3.37.3"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"China NSFC projects","award":["62122050","62071288"],"award-info":[{"award-number":["62122050","62071288"]}]},{"name":"Shanghai Municipal Science and Technology Commission Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2023.3345150","type":"journal-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T19:52:33Z","timestamp":1703274753000},"page":"973-983","source":"Crossref","is-referenced-by-count":2,"title":["Universal Cross-Lingual Data Generation for Low Resource ASR"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9498-1592","authenticated-orcid":false,"given":"Wei","family":"Wang","sequence":"first","affiliation":[{"name":"Auditory Cognition and Computational Acoustics Lab, the Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0314-3790","authenticated-orcid":false,"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Auditory Cognition and Computational Acoustics Lab, the Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref2","article-title":"SpeechStew: Simply mix all available speech recognition data to train one large neural network","volume-title":"Workshop Mach. Learn. Speech Lang. Process.","author":"Chan","year":"2021"},{"key":"ref3","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2620"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461802"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1242"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855086"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3140552"},{"key":"ref12","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747355"},{"article-title":"Applying wav2vec2.0 to speech recognition in various low-resource languages","year":"2020","author":"Yi","key":"ref15"},{"article-title":"Effectiveness of self-supervised pre-training for speech recognition","year":"2019","author":"Baevski","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3184480"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462201"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2955"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053112"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2345"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-448"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref28","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1511"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-117"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"article-title":"Exploring machine speech chain for domain adaptation and few-shot speaker adaptation","year":"2021","author":"Yue","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1555"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746475"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413930"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref46","first-page":"5410","article-title":"Almost unsupervised text to speech and automatic speech recognition","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Ren","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053571"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688101"},{"key":"ref50","first-page":"135","article-title":"A unit selection-based speech synthesis approach for mandarin chinese","volume":"16","author":"Dong","year":"2006","journal-title":"J. Chin. Lang. Comput."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11066"},{"key":"ref53","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. Int. Conf. Lang. Resour. Eval.","author":"Ardila","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref55","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10372076.pdf?arnumber=10372076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T05:53:00Z","timestamp":1709445180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10372076\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3345150","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}