{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T02:28:50Z","timestamp":1782268130066,"version":"3.54.5"},"reference-count":25,"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\/icassp49660.2025.10889337","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Integrating Spectro-Temporal Cross Aggregation and Multi-Scale Dynamic Learning for Audio Deepfake Detection"],"prefix":"10.1109","author":[{"given":"Yunqi","family":"Hao","sequence":"first","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minqiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihao","family":"Chen","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Fang","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref3","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","author":"Baevski"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-14"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3169954"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096278"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref11","article-title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation","volume-title":"Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Jung"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448049"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747421"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"key":"ref16","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-44"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-563"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447923"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-177"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1820"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446612"}],"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\/10889337.pdf?arnumber=10889337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:40Z","timestamp":1774416220000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889337","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}