{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:39:06Z","timestamp":1777574346886,"version":"3.51.4"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-18-JSTS-0001"],"award-info":[{"award-number":["ANR-18-JSTS-0001"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Japan Science and Technology Agency through Project VoicePersonae","award":["JPMJCR18A6"],"award-info":[{"award-number":["JPMJCR18A6"]}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","award":["349605"],"award-info":[{"award-number":["349605"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SPEECHFAKES"},{"name":"MEXT KAKENHI","award":["21K17775"],"award-info":[{"award-number":["21K17775"]}]},{"name":"MEXT KAKENHI","award":["21H04906"],"award-info":[{"award-number":["21H04906"]}]},{"name":"Region Grand Est, France, joint doctoral funding from Inria and UEF"},{"name":"Science and Engineering Research Council, Agency for Science, Technology and Research (A*STAR), Singapore"},{"name":"Council Research Fund","award":["CR-2021-005"],"award-info":[{"award-number":["CR-2021-005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3285283","type":"journal-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:18:04Z","timestamp":1687198684000},"page":"2507-2522","source":"Crossref","is-referenced-by-count":246,"title":["ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1207-5651","authenticated-orcid":false,"given":"Xuechen","family":"Liu","sequence":"first","affiliation":[{"name":"CNRS, Inria, LORIA, Université de Lorraine, Nancy, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8246-0606","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Digital Content and Media Sciences Research Division, National Institute of Informatics, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0624-2903","authenticated-orcid":false,"given":"Md","family":"Sahidullah","sequence":"additional","affiliation":[{"name":"CNRS, Inria, LORIA, Université de Lorraine, Nancy, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7193-0721","authenticated-orcid":false,"given":"Jose","family":"Patino","sequence":"additional","affiliation":[{"name":"Digital Security Department, EURECOM (Campus SophiaTech), Biot, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4475-2517","authenticated-orcid":false,"given":"H\u00e9ctor","family":"Delgado","sequence":"additional","affiliation":[{"name":"Nuance Communications, Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4371-7322","authenticated-orcid":false,"given":"Tomi","family":"Kinnunen","sequence":"additional","affiliation":[{"name":"School of Computing, University of Eastern Finland, Joensuu, Finland"}]},{"given":"Massimiliano","family":"Todisco","sequence":"additional","affiliation":[{"name":"Digital Security Department, EURECOM (Campus SophiaTech), Biot, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3955","authenticated-orcid":false,"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[{"name":"Digital Content and Media Sciences Research Division, National Institute of Informatics, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8459-1041","authenticated-orcid":false,"given":"Nicholas","family":"Evans","sequence":"additional","affiliation":[{"name":"Digital Security Department, EURECOM (Campus SophiaTech), Biot, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3405-4416","authenticated-orcid":false,"given":"Andreas","family":"Nautsch","sequence":"additional","affiliation":[{"name":"Digital Security Department, EURECOM (Campus SophiaTech), Biot, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9133-3000","authenticated-orcid":false,"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Fact check: The deepfakes in the disinformation war between Russia and Ukraine","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3116438"},{"key":"ref12","article-title":"Deepfakes–The Good, The Bad, And The Ugly","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2458"},{"key":"ref15","article-title":"ASVspoof 2021: Automatic speaker verification spoofing and countermeasures challenge evaluation plan","author":"delgado","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11270"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-95"},{"key":"ref55","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","author":"casanova","year":"0","journal-title":"Proc 39th Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/1994\">"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3167258"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682942"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/BIOSIG.2017.8053510"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3059479"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233236"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.04.005"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859621"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref44","first-page":"9241","article-title":"The vicomtech audio deepfake detection system based on Wav2vec2 for the 2022 ADD challenge","author":"mart\u00edn-do\u00f1as","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-14"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-1524-6_8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref7","article-title":"Microsoft back contest to better detect deepfakes","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3009494"},{"key":"ref4","article-title":"Use real-time caller authentication with voice ID","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref6","article-title":"Deepfake audio detection in the call center","year":"2022"},{"key":"ref5","article-title":"What is a deepfake? Everything you need to know about the AI-powered fake media","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036777"},{"key":"ref34","article-title":"The emime bilingual database","author":"wester","year":"2010"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1281"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00357"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2379648"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-14"},{"key":"ref2","year":"2016","journal-title":"Information Technology—Biometric Presentation Attack Detection"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-12"},{"key":"ref23","first-page":"68","article-title":"The biometric vox system for the ASVspoof 2021 challenge","author":"c\u00e1ceres","year":"0","journal-title":"Proc Ed Autom Speaker Verification Spoofing Countermeasures Challenge"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-3"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-14"},{"key":"ref20","article-title":"Sceptre S8 studio monitor tech sheet","year":"0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-10"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103256"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163888"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10155166.pdf?arnumber=10155166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,31]],"date-time":"2023-07-31T17:40:51Z","timestamp":1690825251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10155166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3285283","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}