{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:35:47Z","timestamp":1775838947096,"version":"3.50.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science and Technology Council","award":["NSTC 111-2221-E-001-002"],"award-info":[{"award-number":["NSTC 111-2221-E-001-002"]}]},{"name":"National Science and Technology Council","award":["NSTC 113-2221-E-004-001-MY3"],"award-info":[{"award-number":["NSTC 113-2221-E-004-001-MY3"]}]},{"name":"National Science and Technology Council","award":["NSTC 113-2221-E-004-006-MY2"],"award-info":[{"award-number":["NSTC 113-2221-E-004-006-MY2"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Human-Mach. Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/thms.2025.3618409","type":"journal-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:28Z","timestamp":1761153928000},"page":"973-982","source":"Crossref","is-referenced-by-count":3,"title":["AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Deepfake Detection of Frontal Face Videos"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5591-8423","authenticated-orcid":false,"given":"Sahibzada Adil","family":"Shahzad","sequence":"first","affiliation":[{"name":"Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1973-6902","authenticated-orcid":false,"given":"Ammarah","family":"Hashmi","sequence":"additional","affiliation":[{"name":"Social Networks and Human-Centered Computing Program, Taiwan International Graduate Program, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-1670","authenticated-orcid":false,"given":"Yan-Tsung","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Chengchi University, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-0418","authenticated-orcid":false,"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5071","authenticated-orcid":false,"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/2056305120903408"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.107050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.53637\/DELS2700"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.11.106"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00323"},{"key":"ref6","first-page":"9054","article-title":"Defending against neural fake news","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Zellers","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133990"},{"key":"ref8","article-title":"The radicalization risks of GPT-3 and advanced neural language models","author":"McGuffie","year":"2020"},{"key":"ref9","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Workshop Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref11","article-title":"MelNet: A generative model for audio in the frequency domain","author":"Vasquez","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref13","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jia","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.397"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00728"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2021.103364"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.chbr.2024.100538"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00436"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"ref21","article-title":"Deepfake detection with inconsistent head poses: Reproducibility and analysis","author":"Lutz","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-473"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-467"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1515\/revneuro-2022-0065"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC48188.2019.8949228"},{"key":"ref29","first-page":"1","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193049"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref33","first-page":"1","article-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset","volume-title":"Proc. NeurIPS Track Datasets Benchmarks","author":"Khalid","year":"2021"},{"key":"ref34","article-title":"DeepFakes: A new threat to face recognition? assessment and detection","author":"Korshunov","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413630"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00341"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref38","first-page":"5074","article-title":"FaceShifter: Towards high fidelity and occlusion aware face swapping","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Li","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW46912.2020.9105991"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19978"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3501814"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3402446"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"ref49","article-title":"The deepfake detection challenge (DFDC) dataset","author":"Dolhansky","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"ref51","article-title":"Voice spoofing countermeasures: Taxonomy, state-of-the-art, experimental analysis of generalizability, open challenges, and the way forward","author":"Khan","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3616540"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980296"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00197"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980255"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2025.3554477"},{"key":"ref61","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01793-3_21"},{"key":"ref65","first-page":"1755","article-title":"DLIB-ML: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3476099.3484315"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00106"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/icmla58977.2023.00207"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00101"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312738"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309899"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01011"},{"key":"ref75","article-title":"Unsupervised multimodal deepfake detection using intra-and cross-modal inconsistencies","author":"Tian","year":"2023"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2497"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB62174.2024.10744480"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681672"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS46853.2019.9185974"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.229"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00020"},{"key":"ref83","first-page":"46","article-title":"Exposing deepfake videos by detecting face warping artifacts","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Li","year":"2019"}],"container-title":["IEEE Transactions on Human-Machine Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221037\/11272139\/11214430.pdf?arnumber=11214430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:24Z","timestamp":1764787404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11214430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":83,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/thms.2025.3618409","relation":{},"ISSN":["2168-2291","2168-2305"],"issn-type":[{"value":"2168-2291","type":"print"},{"value":"2168-2305","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}