{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:17:22Z","timestamp":1774419442964,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889022","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["SpecViT: A Custom Vision-Transformer based Approach for Audio Deepfake Detection"],"prefix":"10.1109","author":[{"given":"Sharmistha","family":"Modak","sequence":"first","affiliation":[{"name":"Indian Institute of Engineering Science and Technology,Department of Information Technology,Shibpur,India,711103"}]},{"given":"Arnab Kumar","family":"Das","sequence":"additional","affiliation":[{"name":"Indian Institute of Engineering Science and Technology,Department of Information Technology,Shibpur,India,711103"}]},{"given":"Ruchira","family":"Naskar","sequence":"additional","affiliation":[{"name":"Indian Institute of Engineering Science and Technology,Department of Information Technology,Shibpur,India,711103"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.384165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00444-8"},{"key":"ref3","first-page":"1","article-title":"D-fence layer: an ensemble framework for comprehensive deepfake detection","author":"Amerini","year":"2024","journal-title":"Multimedia Tools and Applications"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-020-09681-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/CCC50068.2020.9189596"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.03.209"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2999185"},{"key":"ref9","article-title":"The deepfake detection challenge (dfdc) preview dataset","author":"Dolhansky","year":"2019"},{"key":"ref10","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00341"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"ref14","first-page":"3","volume-title":"Real-time-voice-cloning","author":"Jemine","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3476099.3484315"},{"key":"ref16","article-title":"Fakeavceleb: A novel audio-video multimodal deepfake dataset","author":"Khalid","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/fi13040093"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3348450"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WINCOM59760.2023.10323004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.397"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462584"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10101163"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747768"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3425780"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103525"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2018.08.003"},{"key":"ref29","article-title":"Deepfacelab: Integrated, flexible and extensible face-swapping framework","author":"Perov","year":"2020"},{"key":"ref30","article-title":"Stand-alone self-attention in vision models","volume":"32","author":"Ramachandran","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00106"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-472"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICIRCA51532.2021.9544522"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3552466.3556530"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2022-14"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1383"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746820"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446560"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3290752"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2019.12.014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref49","article-title":"Slim: Style-linguistics mismatch model for generalized audio deepfake detection","author":"Zhu","year":"2024"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889022.pdf?arnumber=10889022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:54Z","timestamp":1774416174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889022\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889022","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}