{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:26:32Z","timestamp":1792513592691,"version":"4.5.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890469","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Black-Box Adversarial Defense Against Voice Conversion Using Latent Space Perturbation"],"prefix":"10.1109","author":[{"given":"Jie","family":"Gao","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyun","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhisheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/app13053100"},{"key":"ref3","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096642"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095565"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-319"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383529"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/535"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623209"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3365034"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cec.2008.4631255"},{"key":"ref17","article-title":"Black-box adversarial attack with transferable model-based embedding","author":"Huang","year":"2019"},{"key":"ref18","article-title":"Quickvc: Any-to-many voice conversion using inverse short-time fourier transform for faster conversion","author":"Guo","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref20","article-title":"English multi-speaker corpus for cstr voice cloning toolkit","author":"Yamagishi","year":"2012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref22","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101026"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-15"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389672"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26607"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890469.pdf?arnumber=10890469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:09Z","timestamp":1774416129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890469","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}