{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T16:37:03Z","timestamp":1794328623805,"version":"4.9.0"},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"JST, PRESTO","award":["JPMJPR23P9"],"award-info":[{"award-number":["JPMJPR23P9"]}]},{"name":"French Agence Nationale de la Recherche","award":["ANR-22-CE39-0009"],"award-info":[{"award-number":["ANR-22-CE39-0009"]}],"id":[{"id":"https:\/\/ror.org\/00rbzpz17","id-type":"ROR","asserted-by":"crossref"}]},{"name":"French Agence Nationale de la Recherche","award":["ANR22-PECY-0011"],"award-info":[{"award-number":["ANR22-PECY-0011"]}],"id":[{"id":"https:\/\/ror.org\/00rbzpz17","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["MHP\/048\/24"],"award-info":[{"award-number":["MHP\/048\/24"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program of China","award":["2024YFE0217200"],"award-info":[{"award-number":["2024YFE0217200"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Audio, Speech Lang. Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/taslpro.2026.3682962","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T19:58:00Z","timestamp":1775851080000},"page":"2354-2367","source":"Crossref","is-referenced-by-count":3,"title":["ASVspoof 5: Evaluation of Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8246-0606","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"first","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4475-2517","authenticated-orcid":false,"given":"H\u00e9ctor","family":"Delgado","sequence":"additional","affiliation":[{"name":"Microsoft, Pozuelo de Alarcón, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1207-5651","authenticated-orcid":false,"given":"Xuechen","family":"Liu","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hemlata","family":"Tak","sequence":"additional","affiliation":[{"name":"Pindrop, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9133-3000","authenticated-orcid":false,"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Research Centre for Data Science & Artificial Intelligence, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4052-2754","authenticated-orcid":false,"given":"Ivan","family":"Kukanov","sequence":"additional","affiliation":[{"name":"KLASS Engineering and Solutions, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0624-2903","authenticated-orcid":false,"given":"Md","family":"Sahidullah","sequence":"additional","affiliation":[{"name":"Institute for Advancing Intelligence, TCG CREST, Kolkata, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Massimiliano","family":"Todisco","sequence":"additional","affiliation":[{"name":"Digital Security Department, EURECOM (Campus SophiaTech), Biot, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3955","authenticated-orcid":false,"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Information TechnologyBiometric Presentation Attack Detection","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref3","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Casanova","year":"2022"},{"key":"ref4","first-page":"705","article-title":"Neural codec language models are zero-shot text to speech synthesizers","volume-title":"IEEE Trans. Audio, Speech Lang. Process.","volume":"33","author":"Chen","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref6","article-title":"Coqui TTS","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/blizzard.2023-4"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-99-0827-1","volume-title":"Neural Text-to-Speech Synth.","author":"Tan","year":"2023"},{"key":"ref9","article-title":"NeMo: A toolkit for conversational AI and large language models","author":"Harper","year":"2023"},{"key":"ref10","article-title":"ElevenLabs Python library","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref14","article-title":"ADD 2023: The second audio deepfake detection challenge","volume-title":"Proc. IJCAI DADA Workshop","author":"Yi","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3733102.3736707"},{"key":"ref16","article-title":"Using MLAAD for source tracing of audio deepfakes","author":"Mller"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref18","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/vcc_bc.2020-14"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2025.101825"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.08.001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-23"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3009494"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3313648"},{"key":"ref27","article-title":"ASVspoof 5 evaluation plan","author":"Delgado","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-703"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-14"},{"key":"ref31","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov","year":"2021"},{"key":"ref32","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Popov","year":"2022"},{"key":"ref33","first-page":"3171","article-title":"Creating new language and voice components for the updated MaryTTS text-to-speech synthesis platform","volume-title":"Proc. Int. Conf. Lang. Resour. Eval.","author":"Steiner","year":"2018"},{"key":"ref34","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-14"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681345"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref41","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92), [sound]","author":"Yamagishi","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11270"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-422"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-563"},{"key":"ref49","article-title":"NIST 2020 CTS speaker recognition challengeevaluation plan","author":"Seyed","year":"2020"},{"key":"ref50","article-title":"Calibration tutorial","author":"Ferrer","year":"2024"},{"key":"ref51","article-title":"The BOSARIS toolkit: Theory, algorithms and code for surviving the new DCF","author":"Brmmer","year":"2011"},{"key":"ref52","article-title":"An overview of log likelihood ratio cost in forensic scienceWhere is it used and what values can we expect?","volume-title":"Forensic Sci. Int.: Synergy","volume":"8","author":"Lierop","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-2"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-16"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-22"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-11"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-10"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-7"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-21"},{"key":"ref62","article-title":"Speaker recognition in unconstrained environments","author":"Nautsch","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-820"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-661"},{"key":"ref68","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74200-5_19"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-541"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3626963"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU65441.2025.11434670"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC65261.2025.11249190"},{"key":"ref76","first-page":"1","article-title":"MLAAD: The multi-language audio anti-spoofing dataset","volume-title":"Proc. Int. Joint Conf. Neural Netw.","author":"Mller","year":"2024"},{"key":"ref77","first-page":"1","article-title":"Revealing cross-lingual bias in synthetic speech detection under controlled conditions","volume-title":"Proc. 5th Symp. Secur. Privacy Speech Commun.","author":"Moreno","year":"2025"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832142"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-100"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3552466.3556525"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980129"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1283"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2025.101840"},{"key":"ref84","first-page":"1","article-title":"Proactive detection of voice cloning with localized watermarking","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Roman","year":"2024"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1269"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-472"},{"key":"ref87","article-title":"Neural codec source tracing: Toward comprehensive attribution in open-set condition","author":"Xie","year":"2025"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1297"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/asru65441.2025.11434771"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1757"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2079"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2065"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2001"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU65441.2025.11434703"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-172"},{"key":"ref96","first-page":"9241","article-title":"The vicomtech audio deepfake detection system based on Wav2Vec2 for the 2022 ADD challenge","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Martin-Donas","year":"2022"},{"key":"ref97","first-page":"2245","article-title":"Replay attacks against audio deepfake detection","volume-title":"Proc. Interspeech","author":"Mller","year":"2025"}],"container-title":["IEEE Transactions on Audio, Speech and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723155\/11302005\/11478771.pdf?arnumber=11478771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T04:56:23Z","timestamp":1777352183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11478771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":97,"URL":"https:\/\/doi.org\/10.1109\/taslpro.2026.3682962","relation":{"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1109\/taslpro.2026.3682962\/mm1","asserted-by":"subject"}]},"ISSN":["2998-4173"],"issn-type":[{"value":"2998-4173","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}