{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T22:28:33Z","timestamp":1783204113389,"version":"3.54.6"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":["61571363"],"award-info":[{"award-number":["61571363"]}],"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":[[2019,11]]},"DOI":"10.1109\/taslp.2019.2933146","type":"journal-article","created":{"date-parts":[[2019,8,5]],"date-time":"2019-08-05T19:43:10Z","timestamp":1565034190000},"page":"1826-1838","source":"Crossref","is-referenced-by-count":22,"title":["Adversarial Regularization for Attention Based End-to-End Robust Speech Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2642-5096","authenticated-orcid":false,"given":"Sining","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei-Yuh","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref32","article-title":"Pattern recognition and machine learning","author":"bishop","year":"0"},{"key":"ref31","article-title":"Did you hear that? adversarial examples against automatic speech recognition","author":"alzantot","year":"2018"},{"key":"ref30","first-page":"6977","article-title":"Houdini: Fooling deep structured visual and speech recognition models with adversarial examples","author":"cisse","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref36","article-title":"Aishell-2: Transforming mandarin ASR research into industrial scale","author":"du","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref34","article-title":"Unsupervised data augmentation","author":"xie","year":"2019","journal-title":"arXiv preprint arXiv 1904 12848"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1247"},{"key":"ref27","article-title":"Explaining and harnessing adversarial examples (2014)","author":"goodfellow","year":"2014","journal-title":"ICLRE"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref22","article-title":"Pattern recognition and machine learning","author":"bishop","year":"2006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1201\/9781351251389-8","article-title":"Adversarial examples in the physical world","author":"kurakin","year":"2018","journal-title":"Artificial Intelligence Safety and Security"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1316"},{"key":"ref25","article-title":"Distributional smoothing with virtual adversarial training","author":"miyato","year":"2016","journal-title":"ICLRE"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461423"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682468"},{"key":"ref59","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2019-2680","article-title":"Specaugment: A simple data augmentation method for automatic speech recognition","author":"park","year":"2019"},{"key":"ref58","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Advances Neural Inf Process Syst"},{"key":"ref57","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-50617-7.50010-0"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683479"},{"key":"ref54","article-title":"Robust audio adversarial example for a physical attack","author":"yakura","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462452"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462663"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1746"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2018.08.006"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref12","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref13","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref14","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1780"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.063"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461932"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461682"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref49","article-title":"Invariant representations for noisy speech recognition","author":"serdyuk","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-879"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510508"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"ref41","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1030"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8784423\/08788563.pdf?arnumber=8788563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:05:11Z","timestamp":1657746311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8788563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":59,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2933146","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11]]}}}