{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:53:35Z","timestamp":1784904815705,"version":"3.55.0"},"reference-count":61,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB3103500"],"award-info":[{"award-number":["2022YFB3103500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071142"],"award-info":[{"award-number":["62071142"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"publisher","award":["2024A1515012299"],"award-info":[{"award-number":["2024A1515012299"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2024.3520001","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:27:50Z","timestamp":1734550070000},"page":"871-885","source":"Crossref","is-referenced-by-count":15,"title":["Robust AI-Synthesized Speech Detection Using Feature Decomposition Learning and Synthesizer Feature Augmentation"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6320-9096","authenticated-orcid":false,"given":"Kuiyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3529-0541","authenticated-orcid":false,"given":"Zhongyun","family":"Hua","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8183-8435","authenticated-orcid":false,"given":"Yushu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics, Nanchang, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifang","family":"Guo","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9439-4623","authenticated-orcid":false,"given":"Tao","family":"Xiang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University, Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW46912.2020.9105991"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCTURKEY56345.2022.9931802"},{"key":"ref3","volume-title":"Listen to This Deepfake Audio Impersonating a CEO in Brazen Fraud Attempt","author":"Franceschi-Bicchierai","year":"2020"},{"key":"ref4","volume-title":"Telegram Still Hasn\u2019t Removed an AI Bot That\u2019s Abusing Women","author":"Burgess","year":"2020"},{"key":"ref5","first-page":"1","article-title":"WaveFake: A data set to facilitate audio DeepFake detection","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Frank"},{"key":"ref6","first-page":"74213","article-title":"P-Flow: A fast and data-efficient zero-shot TTS through speech prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kim"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29411"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/a15050155"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00097"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2694139"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124420"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197531"},{"key":"ref13","first-page":"104","article-title":"Detecting AI-synthesized speech using bispectral analysis","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) Workshops","author":"Al Badawy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747605"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446560"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3089437"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26523"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747434"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref22","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner"},{"key":"ref23","first-page":"11119","article-title":"Guided-TTS: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref24","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov"},{"key":"ref25","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095105"},{"key":"ref27","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":"ref28","first-page":"16624","article-title":"HierSpeech: Bridging the gap between text and speech by hierarchical variational inference using self-supervised representations for speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lee"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26530"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484742"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-360"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3324724"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3552466.3556530"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSP59544.2023.10197715"},{"key":"ref38","first-page":"1","article-title":"Audio spectrogram transformer for synthetic speech detection via speech formant analysis","volume-title":"Proc. IEEE Int. Workshop Inf. Forensics Secur. (WIFS)","author":"Cuccovillo"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00444"},{"key":"ref40","article-title":"CLAD: Robust audio deepfake detection against manipulation attacks with contrastive learning","author":"Wu","year":"2024","journal-title":"arXiv:2404.15854"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-245"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","first-page":"2488","article-title":"How does batch normalization help optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Santurkar"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583222"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref48","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong"},{"key":"ref49","volume-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref50","article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv:1711.00354"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref54","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Baevski"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533654"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_37"},{"issue":"86","key":"ref60","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/10806877.pdf?arnumber=10806877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:38:59Z","timestamp":1736969939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10806877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tifs.2024.3520001","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}