{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:13:24Z","timestamp":1774419204947,"version":"3.50.1"},"reference-count":39,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889621","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["DiffAttack: Diffusion-based Timbre-reserved Adversarial Attack in Speaker Identification"],"prefix":"10.1109","author":[{"given":"Qing","family":"Wang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jixun","family":"Yao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaokai","family":"Sun","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John H.L.","family":"Hansen","sequence":"additional","affiliation":[{"name":"The University of Texas,Center for Robust Speech Systems (CRSS),Dallas,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/89.365379"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-465"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2671435"},{"key":"ref6","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref8","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1052"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2983"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23362"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1955"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102886"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053747"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3376897.3377856"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053076"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00004"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101199"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1352"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3306714"},{"key":"ref26","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2023-16"},{"key":"ref28","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","author":"Popov","year":"2021"},{"key":"ref29","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref31","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref32","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-12616-5_4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096790"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"}],"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\/10889621.pdf?arnumber=10889621","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:31Z","timestamp":1774416091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889621\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889621","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}