{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:42:47Z","timestamp":1784738567593,"version":"3.55.0"},"reference-count":53,"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":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["25K21245"],"award-info":[{"award-number":["25K21245"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["23K18491"],"award-info":[{"award-number":["23K18491"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["25H01139"],"award-info":[{"award-number":["25H01139"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001695","name":"Japan Science and Technology Agency (JST) Program for Co-Creating Startup Ecosystem","doi-asserted-by":"publisher","award":["JPMJSF2318"],"award-info":[{"award-number":["JPMJSF2318"]}],"id":[{"id":"10.13039\/501100001695","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3680508","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:54:26Z","timestamp":1775246066000},"page":"57144-57161","source":"Crossref","is-referenced-by-count":1,"title":["Multilingual Deepfake Speech Dataset for Robust and Generalizable Detection"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9853-8893","authenticated-orcid":false,"given":"Candy Olivia","family":"Mawalim","sequence":"first","affiliation":[{"name":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutong","family":"Wang","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aulia","family":"Adila","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9260-0403","authenticated-orcid":false,"given":"Shogo","family":"Okada","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6605-2052","authenticated-orcid":false,"given":"Masashi","family":"Unoki","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Audio deepfake detection: A survey","author":"Yi","year":"2023","journal-title":"arXiv:2308.14970"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref5","first-page":"97:1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583222"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-42"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906599"},{"key":"ref10","article-title":"WaveFake: A data set to facilitate audio DeepFake detection","volume-title":"Proc. NeurIPS Track Datasets Benchmarks","author":"Frank"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2024.103122"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref15","first-page":"125","article-title":"ADD 2023: The second audio deepfake detection challenge","volume-title":"Proc. Workshop Deepfake Audio Detection Anal. Co-located","author":"Yi"},{"key":"ref16","article-title":"Real-time detection of AI-generated speech for DeepFake voice conversion","author":"Bird","year":"2023","journal-title":"arXiv:2308.12734"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650962"},{"key":"ref18","first-page":"4977","article-title":"Cross-domain audio deepfake detection: Dataset and analysis","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Li"},{"key":"ref19","article-title":"ASVspoof 5: Design, collection and validation of resources for spoofing, deepfake, and adversarial attack detection using crowdsourced speech","author":"Wang","year":"2025","journal-title":"arXiv:2502.08857"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832250"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670285"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3733102.3736707"},{"key":"ref23","volume-title":"The Lj Speech Dataset","author":"Ito","year":"2017"},{"key":"ref24","article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv:1711.00354"},{"key":"ref25","volume-title":"The M-AILABS Speech Dataset","author":"Celeste","year":"2020"},{"key":"ref26","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Ardila"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1397"},{"key":"ref33","article-title":"Challenges in speech spoofing countermeasures for Southeast Asian languages","author":"Mawalim","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iSAI-NLP60301.2023.10354956"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICAICTA63815.2024.10763091"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/116.20240080"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1972"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA64382.2024.10800220"},{"key":"ref39","article-title":"MediaSpeech: Multilanguage ASR benchmark and dataset","author":"Kolobov","year":"2021","journal-title":"arXiv:2103.16193"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.639"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-022-09621-4"},{"key":"ref42","article-title":"JVS corpus: Free Japanese multi-speaker voice corpus","author":"Takamichi","year":"2019","journal-title":"arXiv:1908.06248"},{"key":"ref43","volume-title":"Lotus (Thai Speech Recognition Corpus)","year":"2025"},{"key":"ref44","first-page":"51","article-title":"A non-expert kaldi recipe for Vietnamese speech recognition system","volume-title":"Proc. 3rd Int. Workshop Worldwide Lang. Service Infrastruct. 2nd Workshop Open Infrastructures Anal. Frameworks Human Lang. Technol. (WLSI\/OIAF4HLT)","author":"Luong"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC63619.2025.10848707"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3174"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747766"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-126"},{"key":"ref51","volume-title":"ASVspoof 5 Evaluation Plan","author":"Delgado","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3733102.3736706"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11474450.pdf?arnumber=11474450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:06:14Z","timestamp":1776715574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11474450\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3680508","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}