{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:23:09Z","timestamp":1761582189003,"version":"3.28.0"},"reference-count":30,"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\/icassp43922.2022.9747543","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"8192-8196","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Effective Data Utilization for Low-Resource Speech Recognition"],"prefix":"10.1109","author":[{"given":"Zhikai","family":"Zhou","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangyou","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/Interspeech.2020-1800"},{"year":"2020","author":"liu","article-title":"Tera: Self-supervised learning of transformer encoder representation for speech","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.21437\/Interspeech.2020-1511"},{"key":"ref13","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref16","article-title":"Transfer learning from adult to children for speech recognition: Evaluation, analysis and recommendations","volume":"63","author":"shivakumar","year":"2020","journal-title":"Computer Speech & Language"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Interspeech.2019-2858"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.21437\/Interspeech.2016-598"},{"key":"ref19","article-title":"Language id-based training of multilingual stacked bottleneck features","author":"cutler","year":"2014","journal-title":"InterSpeech"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.21437\/Interspeech.2018-1456"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1016\/j.specom.2018.09.001"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.21437\/Interspeech.2019-2680"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ASRU.2011.6163957"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2019-2092"},{"key":"ref29","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc ICML"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.21437\/Interspeech.2012-16"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/3394486.3403331"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.21437\/Interspeech.2021-2062"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ASRU.2013.6707764"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.21437\/Interspeech.2020-1470"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICASSP.2012.6288862"},{"key":"ref20","article-title":"Identification of mono-and poly-phonemes using acoustic-phonetic features derived by a self-organising neural network","author":"dalsgaard","year":"1992","journal-title":"ICSLP"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1145\/1553374.1553380"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref24","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Sixteenth Interspeech"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.18653\/v1\/2020.coling-main.352"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref25","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"Proceedings of the 12th Language Resources and Evaluation Conference"}],"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\/09747543.pdf?arnumber=9747543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:11:24Z","timestamp":1660579884000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747543\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747543","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}