{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T22:26:44Z","timestamp":1781216804482,"version":"3.54.1"},"reference-count":98,"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\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["110-2628-E-002-001"],"award-info":[{"award-number":["110-2628-E-002-001"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"name":"HKSAR Government's Research Grants Council General Research Fund","award":["14208718"],"award-info":[{"award-number":["14208718"]}]},{"name":"Centre for Perceptual and Interactive Intelligence, a CUHK InnoCentre"}],"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.2021.3133189","type":"journal-article","created":{"date-parts":[[2021,12,9]],"date-time":"2021-12-09T21:12:34Z","timestamp":1639084354000},"page":"202-217","source":"Crossref","is-referenced-by-count":25,"title":["Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7166-5534","authenticated-orcid":false,"given":"Haibin","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2954-3271","authenticated-orcid":false,"given":"Xu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2502-3992","authenticated-orcid":false,"given":"Andy T.","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8533-0524","authenticated-orcid":false,"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9654-5747","authenticated-orcid":false,"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/9781108552332"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref3","first-page":"1","article-title":"A small footprint i-vector extractor","volume-title":"Proc. Odyssey Speaker Lang. Recognit. Workshop","author":"Kenny","year":"2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref5","first-page":"249","article-title":"Analysis of i-vector length normalization in speaker recognition systems","volume-title":"Proc. Interspeech","author":"Espy-Wilson","year":"2011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853887"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-51"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref14","first-page":"116","article-title":"A comparison between human perception and a speaker verification system score of a voice imitation","volume":"119","author":"Zetterholm","year":"2004","journal-title":"Evaluation"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041636"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-01931-4_18"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11581-8_59"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288895"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1052"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"ref22","article-title":"ASVspoof 2019: The 3rd automatic speaker verification spoofing and countermeasures challenge database","author":"Yamagishi","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2015-462"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3000641"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413828"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2125"},{"key":"ref29","article-title":"Intriguing properties of neural networks","volume-title":"Int. Conf. Learn. Representations","author":"Szegedy","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref31","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014"},{"key":"ref32","first-page":"49","article-title":"Commandersong: A systematic approach for practical adversarial voice recognition","volume-title":"Proc. 27th USENIX Secur. Symp.","author":"Yuan","year":"2018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23288"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/741"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00016"},{"key":"ref36","first-page":"5231","article-title":"Imperceptible, robust, and targeted adversarial examples for automatic speech recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qin","year":"2019"},{"key":"ref37","first-page":"6977","article-title":"Houdini: Fooling deep structured visual and speech recognition models with adversarial examples","volume":"30","author":"Cisse","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref38","article-title":"Generating adversarial examples for speech recognition","author":"Iter","year":"2017"},{"key":"ref39","article-title":"Did you hear that? Adversarial examples against automatic speech recognition","volume-title":"NIPS Mach. Deception workshop","author":"Alzantot","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003763"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2026"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2834"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053643"},{"key":"ref44","article-title":"Practical attacks on voice spoofing countermeasures","author":"Kassis","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2478068"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383529"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.33682\/sp9n-qk06"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414844"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053076"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053747"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2430"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3376897.3377856"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00004"},{"key":"ref54","article-title":"Crafting adversarial examples for speech paralinguistics applications","volume-title":"DYnamic Novel Adv. Mach. Learn. Intell. Cyber Secur. Workshop Conjunction","author":"Gong","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1955"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2458"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-07974-5_2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2983"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2441"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1966"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref64","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow","year":"2015"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413737"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639510"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref68","article-title":"BUT system description to Voxceleb speaker recognition challenge","author":"Zeinali","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1608"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2195"},{"key":"ref72","first-page":"71","article-title":"Cosine similarity scoring without score normalization techniques","volume-title":"Proc. Speaker Odyssey","author":"Dehak","year":"2010"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639151"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref76","article-title":"Representation learning with contrastive predictive coding","volume-title":"CoRR","author":"Oord","year":"2018"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref80","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1473"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref88","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref89","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref90","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Int. Conf. Learn. Representations","author":"Lan","year":"2020"},{"key":"ref91","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00034"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00078"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/FG57933.2023.10042617"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref98","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma","year":"2015"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09645217.pdf?arnumber=9645217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T21:02:44Z","timestamp":1709326964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9645217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3133189","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}