{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:04:01Z","timestamp":1764403441031,"version":"3.33.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848962","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Adversarial Augmentation and Adaptation for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jen-Tzung","family":"Chien","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Yu","family":"Sun","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1652"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10457"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-545"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1212"},{"key":"ref6","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":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2023.101576"},{"key":"ref10","first-page":"8588","article-title":"A closer look at accuracy vs. robustness","volume":"33","author":"Yang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317410"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746696"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3421281"},{"journal-title":"Explaining and harnessing adversarial examples","year":"2014","author":"Goodfellow","key":"ref14"},{"article-title":"Adversarial training methods for semi-supervised text classification","volume-title":"Proc. of International Conference on Learning Representations","author":"Miyato","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447702"},{"key":"ref18","article-title":"Adversarial training for free!","volume":"32","author":"Shafahi","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"FreeLB: Enhanced adversarial training for natural language understanding","volume-title":"Proc. of International Conference on Learning Representations","author":"Zhu","key":"ref19"},{"key":"ref20","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. of International Conference on Machine Learning","author":"Zhang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.197"},{"key":"ref22","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. of Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2024,12,3]]},"location":"Macau, Macao","end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848962.pdf?arnumber=10848962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:23:36Z","timestamp":1738045416000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848962","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}