{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:57:35Z","timestamp":1767988655504,"version":"3.49.0"},"reference-count":33,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2053"],"award-info":[{"award-number":["U23B2053"]}],"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":["WK2100000043"],"award-info":[{"award-number":["WK2100000043"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3563306","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T17:44:55Z","timestamp":1745343895000},"page":"1905-1909","source":"Crossref","is-referenced-by-count":2,"title":["Asynchronous Voice Anonymization by Learning From Speaker-Adversarial Speech"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6174-2641","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9421-1049","authenticated-orcid":false,"given":"Liping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9133-3000","authenticated-orcid":false,"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/app9194050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref5","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Casanova","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref8","article-title":"Clova baseline system for the voxceleb speaker recognition challenge 2020","author":"Heo","year":"2020"},{"key":"ref9","article-title":"BUT system description to VoxCeleb speaker recognition challenge 2019","author":"Zeinali","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1983.tb04378.x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1983.tb04377.x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1333"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1888"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-28"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3519879"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447871"},{"key":"ref18","article-title":"Anonymizing speech: Evaluating and designing speaker anonymization techniques","author":"Champion","year":"2023"},{"key":"ref19","first-page":"5181","article-title":"V-cloak: Intelligibility-, naturalness-& timbre-preserving real-time voice anonymization","volume-title":"Proc. 32nd USENIX Secur. Symp.","author":"Deng","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3596266"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447699"},{"key":"ref22","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Goodfellow","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref24","first-page":"1","article-title":"Nesterov accelerated gradient and scale invariance for adversarial attacks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00437"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref30","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101362"},{"key":"ref33","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10972327.pdf?arnumber=10972327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:46:38Z","timestamp":1747071998000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10972327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3563306","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}