{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T05:06:14Z","timestamp":1779771974047,"version":"3.53.1"},"reference-count":29,"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\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3694045","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:47:23Z","timestamp":1779133643000},"page":"76700-76721","source":"Crossref","is-referenced-by-count":0,"title":["MIST: A Multilingual Dataset and Benchmark for Fine-Grained Audio Inpainting Tampering Localization"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7188-5972","authenticated-orcid":false,"given":"Tung","family":"Vu","sequence":"first","affiliation":[{"name":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9026-4692","authenticated-orcid":false,"given":"Yen","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4445-2811","authenticated-orcid":false,"given":"Hai","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0973-0889","authenticated-orcid":false,"given":"Cuong","family":"Pham","sequence":"additional","affiliation":[{"name":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9467-4978","authenticated-orcid":false,"given":"Cong","family":"Tran","sequence":"additional","affiliation":[{"name":"Posts and Telecommunications Institute of Technology, Hanoi, Vietnam"}],"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":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref4","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","author":"Baevski"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3059479"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233236"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-930"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888070"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-738"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680795"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref22","article-title":"LEMAS: A 150k-hour large-scale extensible multilingual audio suite with generative speech models","author":"Zhao","year":"2026","journal-title":"arXiv:2601.04233"},{"key":"ref23","article-title":"Gemini: A family of highly capable multimodal models","author":"Anil","year":"2024","journal-title":"arXiv:2312.11805"},{"key":"ref24","article-title":"CosyVoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv:2407.05407"},{"key":"ref25","article-title":"CosyVoice 3: Towards in-the-wild speech generation via scaling-up and post-training","author":"Du","year":"2025","journal-title":"arXiv:2505.17589"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11522802.pdf?arnumber=11522802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T04:51:09Z","timestamp":1779771069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11522802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3694045","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}