{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:57:53Z","timestamp":1774558673534,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100019413","name":"Gansu Provincial Department of Education Young Doctoral Fund","doi-asserted-by":"publisher","award":["2025CXZX049"],"award-info":[{"award-number":["2025CXZX049"]}],"id":[{"id":"10.13039\/501100019413","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Lanzhou University Fundamental Research Funds for Central Universities","award":["lzujbky-2025-it02"],"award-info":[{"award-number":["lzujbky-2025-it02"]}]},{"name":"Lanzhou University Fundamental Research Funds for Central Universities","award":["lzujbky-2025-jdzx10"],"award-info":[{"award-number":["lzujbky-2025-jdzx10"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62302438"],"award-info":[{"award-number":["62302438"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Supercomputing Center of Lanzhou University; and in part by the Open Research Fund of The State Key Laboratory of Blockchain and Data Security, Zhejiang University."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,4,1]]},"DOI":"10.1109\/jiot.2025.3648834","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:39:39Z","timestamp":1767033579000},"page":"14084-14095","source":"Crossref","is-referenced-by-count":0,"title":["MultiSiFer: Detecting Multiple-Speaker Fake Voice Without Speaker-Irrelative Features"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3685-4852","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0695-2187","authenticated-orcid":false,"given":"Xuan","family":"Hai","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8312-1881","authenticated-orcid":false,"given":"Ziyao","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"}]},{"given":"Zihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1133-5476","authenticated-orcid":false,"given":"Qingyuan","family":"Fei","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8054-5446","authenticated-orcid":false,"given":"Qingguo","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref3","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv:2301.02111"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref5","article-title":"NaturalSpeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","author":"Shen","year":"2023","journal-title":"arXiv:2304.09116"},{"issue":"8","key":"ref6","first-page":"A1","article-title":"Fraudsters used ai to mimic CEO\u2019s voice in unusual cybercrime case","volume":"30","author":"Stupp","year":"2019","journal-title":"Wall Street J."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1281"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3306711"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036777"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-42"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00029"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688273"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613841"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref18","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref19","article-title":"VALL-E 2: Neural codec language models are human parity zero-shot text to speech synthesizers","author":"Chen","year":"2024","journal-title":"arXiv:2406.05370"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref21","article-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks","author":"Kaneko","year":"2017","journal-title":"arXiv:1711.11293"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445804"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472051"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2289"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3174"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-563"},{"key":"ref28","first-page":"104","article-title":"Detecting AI-synthesized speech using bispectral analysis","volume-title":"Proc. CVPR workshops","author":"AlBadawy"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115465"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094704"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446270"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2024.24200"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413716"},{"key":"ref35","first-page":"2691","article-title":"Who are you (I really wanna know)? Detecting audio DeepFakes through vocal tract reconstruction","volume-title":"Proc. 31st USENIX Secur. Symp.","author":"Blue"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref38","article-title":"ASVspoof 2021: Automatic speaker verification spoofing and countermeasures challenge evaluation plan","author":"Delgado","year":"2021","journal-title":"arXiv:2109.00535"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref42","first-page":"6765","article-title":"Audio deepfake detection with self-supervised XLS-R and SLS classifier","volume-title":"Proc. 32nd ACM Int. Conf. Multimedia","author":"Qishan"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11456203\/11316509.pdf?arnumber=11316509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:52:31Z","timestamp":1774554751000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11316509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,1]]},"references-count":42,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3648834","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,1]]}}}