{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:21:38Z","timestamp":1784301698348,"version":"3.55.0"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201524"],"award-info":[{"award-number":["62201524"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271455"],"award-info":[{"award-number":["62271455"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61971383"],"award-info":[{"award-number":["61971383"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["CUC23GZ016"],"award-info":[{"award-number":["CUC23GZ016"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tifs.2023.3324724","type":"journal-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T18:00:31Z","timestamp":1697479231000},"page":"344-358","source":"Crossref","is-referenced-by-count":55,"title":["Domain Generalization via Aggregation and Separation for Audio Deepfake Detection"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8366-9011","authenticated-orcid":false,"given":"Yuankun","family":"Xie","sequence":"first","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication and the School of Information and Communication Engineering, Communication University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3407-4318","authenticated-orcid":false,"given":"Haonan","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8383-8762","authenticated-orcid":false,"given":"Yutian","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3562-5612","authenticated-orcid":false,"given":"Long","family":"Ye","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-011-5730-8","volume-title":"An Introduction to Text-to-Speech Synthesis","volume":"3","author":"Dutoit","year":"1997"},{"key":"ref2","article-title":"Voice conversion challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion","author":"Zhao","year":"2020","journal-title":"arXiv:2008.12527"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS55849.2022.9975433"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2771947"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-438"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref9","article-title":"Raw differentiable architecture search for speech deepfake and spoofing detection","author":"Ge","year":"2021","journal-title":"arXiv:2107.12212"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-12"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1820"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.04.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10078"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00851"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00409"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146781"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3125603"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3055018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3158551"},{"key":"ref21","article-title":"WaveFake: A data set to facilitate audio deepfake detection","author":"Frank","year":"2021","journal-title":"arXiv:2111.02813"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2537844"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref26","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ren"},{"key":"ref27","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv:2006.04558"},{"key":"ref28","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":"ref29","article-title":"NaturalSpeech: End-to-end text to speech synthesis with human-level quality","author":"Tan","year":"2022","journal-title":"arXiv:2205.04421"},{"key":"ref30","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref33","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":"ref34","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref35","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020","journal-title":"arXiv:2009.09761"},{"key":"ref36","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"Chen","year":"2020","journal-title":"arXiv:2009.00713"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1316"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref43","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2016-41"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.007"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2956589"},{"key":"ref49","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2022-14"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747768"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747605"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3076358"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747766"},{"key":"ref57","article-title":"ASVspoof 2021: Automatic speaker verification spoofing and countermeasures challenge evaluation plan","author":"Delgado","year":"2021","journal-title":"arXiv:2109.00535"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023257"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2825949"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01026"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00671"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475279"},{"key":"ref65","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"Huang","year":"2015","journal-title":"arXiv:1508.01991"},{"key":"ref66","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref71","article-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset","author":"Khalid","year":"2021","journal-title":"arXiv:2108.05080"},{"key":"ref72","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","volume-title":"Proc. Univ. Edinburgh. Centre Speech Technol. Res. (CSTR)","author":"Veaux"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref74","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":"ref75","article-title":"CFAD: A Chinese dataset for fake audio detection","author":"Ma","year":"2022","journal-title":"arXiv:2207.12308"},{"key":"ref76","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":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref79","article-title":"THCHS-30: A free Chinese speech corpus","author":"Wang","year":"2015","journal-title":"arXiv:1512.01882"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-729"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041110"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref83","article-title":"A multi-device dataset for urban acoustic scene classification","author":"Mesaros","year":"2018","journal-title":"arXiv:1807.09840"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"issue":"1","key":"ref89","first-page":"11","article-title":"Improved text-independent speaker identification using fused MFCC & IMFCC feature sets based on Gaussian filter","volume":"5","author":"Chakroborty","year":"2009","journal-title":"Int. J. Signal Process."},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref92","article-title":"Voice spoofing countermeasures: Taxonomy, state-of-the-art, experimental analysis of generalizability, open challenges, and the way forward","author":"Khan","year":"2022","journal-title":"arXiv:2210.00417"},{"issue":"11","key":"ref93","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10206\/10319981\/10286049.pdf?arnumber=10286049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T01:43:09Z","timestamp":1710380589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10286049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/tifs.2023.3324724","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}