{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:13:40Z","timestamp":1763190820977,"version":"3.45.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228261","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Wav2DF-TSL: Two-stage Learning with Efficient Pre-training and Hierarchical Experts Fusion for Robust 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"}]},{"given":"Yihao","family":"Chen","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}]},{"given":"Minqiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}]},{"given":"Jianbo","family":"Zhan","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}]},{"given":"Liang","family":"He","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Technology,Urumqi,China"}]},{"given":"Lei","family":"Fang","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}]},{"given":"Sian","family":"Fang","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}]},{"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China"}]}],"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","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-563"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-702"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2125"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746722"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1281"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3089437"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3251895"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095373"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3331949"},{"key":"ref14","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446612"},{"article-title":"Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Jung","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-14"},{"article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Hu","key":"ref20"},{"article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International Conference on Machine Learning (ICML)","author":"Stickland","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681345"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1472"},{"article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"International Conference on Learning Representations (ICLR)","author":"Shazeer","key":"ref24"},{"key":"ref25","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Joint Conference on Artificial Intelligence","author":"Kim"},{"key":"ref26","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/577"},{"key":"ref28","first-page":"1","article-title":"Freevc: Towards high-quality text-free voice conversion","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Huang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-44"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448049"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1820"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447923"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-177"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-659"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446560"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094779"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446331"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446270"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228261.pdf?arnumber=11228261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:11:48Z","timestamp":1763190708000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228261\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228261","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}