{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:44:09Z","timestamp":1778053449463,"version":"3.51.4"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100011829","name":"Ministry of Science and Information and Communications Technology (MSIT), South Korea, under the Information Technology Research Center (ITRC) Support Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011829","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute for Information and Communications Technology Planning and Evaluation","award":["IITP-2024-2020-0-01602"],"award-info":[{"award-number":["IITP-2024-2020-0-01602"]}]},{"name":"IITP grant funded by Korean Government (MSIT), Robust Deepfake Audio Detection Development Against Adversarial Attacks","award":["RS-2023-00263037"],"award-info":[{"award-number":["RS-2023-00263037"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3532775","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T18:57:45Z","timestamp":1737572265000},"page":"18040-18052","source":"Crossref","is-referenced-by-count":8,"title":["Dual-Channel Deepfake Audio Detection: Leveraging Direct and Reverberant Waveforms"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4185-5626","authenticated-orcid":false,"given":"Gunwoo","family":"Lee","sequence":"first","affiliation":[{"name":"School of Electronic Engineering, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungmin","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minkyo","family":"Jung","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3817-0514","authenticated-orcid":false,"given":"Joseph","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Statistics and Actuarial Science, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5538-3630","authenticated-orcid":false,"given":"Kihun","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2676-3412","authenticated-orcid":false,"given":"Souhwan","family":"Jung","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0382-7826","authenticated-orcid":false,"given":"Yoseob","family":"Han","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Soongsil University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.397"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref4","article-title":"DeepFaceLab: Integrated, flexible and extensible face-swapping framework","volume-title":"arXiv:2005.05535","author":"Perov","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682863"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3231480"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICICCSP53532.2022.9862519"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746162"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3174"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT58056.2023.10226172"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639163"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc5040049"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-023-01248-x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667026"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/app14188505"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref22","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"arXiv:2006.04558","author":"Ren","year":"2020"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2505"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSE47409.2019.8971793"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3133134"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref34","article-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset","volume-title":"arXiv:2108.05080","author":"Khalid","year":"2021"},{"key":"ref35","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3089437"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682743"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00728"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref41","first-page":"1","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Jia"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096642"},{"key":"ref43","volume-title":"Dual-Channel Deepfake Audio Detection: Leveraging Direct and Reverberant Waveforms","author":"Lee","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980296"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref47","article-title":"AudioGen: Textually guided audio generation","volume-title":"arXiv:2209.15352","author":"Kreuk","year":"2022"},{"key":"ref48","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"arXiv:2301.12503","author":"Liu","year":"2023"},{"key":"ref49","volume-title":"Ai Realistic Voice Rendering (AIR)","year":"2024"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10849546.pdf?arnumber=10849546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T19:21:21Z","timestamp":1738264881000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849546\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3532775","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}