{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T08:32:01Z","timestamp":1769675521401,"version":"3.49.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2023ZD0121101"],"award-info":[{"award-number":["2023ZD0121101"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007085","name":"National University of Defense Technology","doi-asserted-by":"publisher","award":["ZZCX-ZZGC-01-04"],"award-info":[{"award-number":["ZZCX-ZZGC-01-04"]}],"id":[{"id":"10.13039\/501100007085","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biom. Behav. Identity Sci."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tbiom.2025.3615961","type":"journal-article","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T17:40:32Z","timestamp":1759254032000},"page":"111-121","source":"Crossref","is-referenced-by-count":0,"title":["Voice2Visage: Deciphering Faces From Voices"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4022-4301","authenticated-orcid":false,"given":"Wuyang","family":"Chen","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology and the National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5997-5169","authenticated-orcid":false,"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology and the National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2491-2835","authenticated-orcid":false,"given":"Yanjie","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology and the National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1256-8934","authenticated-orcid":false,"given":"Yong","family":"Dou","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology and the National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3245-1901","authenticated-orcid":false,"given":"Huaimin","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology and the National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2003.09.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/a0030945"},{"key":"ref3","first-page":"29181","article-title":"IIANet: An intra- and inter-modality attention network for audio-visual speech separation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8295.2011.02041.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.01.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/0735-7044.120.4.880"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fncir.2015.00022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2006.04.008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nrn2331"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600-0536.2007.01138.x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0194599812438846"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/S0006323197005082"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2007.12.003"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1044\/leader.FTR1.24022019.44"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuropsychologia.2018.03.039"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2023.3263186"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472707"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1118"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2112"},{"key":"ref20","first-page":"1","article-title":"Face reconstruction from voice using generative adversarial networks","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01020"},{"key":"ref23","article-title":"Sound2Vision: Generating diverse visuals from audio through cross-modal latent alignment","author":"Sung-Bin","year":"2024","journal-title":"arXiv:2412.06209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/adma.202417478"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446625"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00607"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-885"},{"key":"ref28","first-page":"1","article-title":"From inference to generation: End-to-end fully self-supervised generation of human face from speech","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Choi"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240601"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"ref33","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2019.00-42"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5121\/csit.2022.120805"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref38","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. 34th Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8537-1_35"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02161"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413624"},{"key":"ref44","article-title":"Tr\u00e4umerAI: Dreaming music with StyleGAN","author":"Jeong","year":"2021","journal-title":"arXiv:2102.04680"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn55064.2022.9892863"},{"key":"ref46","article-title":"From inference to generation: End-to-end fully self-supervised generation of human face from speech","author":"Choi","year":"2020","journal-title":"arXiv:2004.05830"},{"key":"ref47","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref48","first-page":"1416","article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3631593"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref52","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref53","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3622313"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref57","first-page":"1","article-title":"Improved techniques for training GANs","volume-title":"Proc. 30th Adv. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref59","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. 31st Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref60","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"}],"container-title":["IEEE Transactions on Biometrics, Behavior, and Identity Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8423754\/11364034\/11184855.pdf?arnumber=11184855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:29Z","timestamp":1769634089000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11184855\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":62,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tbiom.2025.3615961","relation":{},"ISSN":["2637-6407"],"issn-type":[{"value":"2637-6407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}