{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:52:29Z","timestamp":1778604749729,"version":"3.51.4"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209891","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["Boosting the Transferability of Audio Adversarial Examples with Acoustic Representation Optimization"],"prefix":"10.1109","author":[{"given":"Weifei","family":"Jin","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,National Engineering Research Center of Disaster Backup and Recovery School of Cyberspace Security,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Su","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,National Engineering Research Center of Disaster Backup and Recovery School of Cyberspace Security,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hejia","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,National Engineering Research Center of Disaster Backup and Recovery School of Cyberspace Security,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulin","family":"Ye","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,National Engineering Research Center of Disaster Backup and Recovery School of Cyberspace Security,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Hao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,National Engineering Research Center of Disaster Backup and Recovery School of Cyberspace Security,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2020.3006860"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16438-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3557894"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3283915"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3689217.3690615"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3665451.3665532"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539268"},{"key":"ref9","first-page":"3799","article-title":"{SMACK}: Semantically meaningful adversarial audio attack","volume-title":"Proceedings of the 32nd USENIX Security Symposium","author":"Yu"},{"key":"ref10","article-title":"Intriguing properties of neural networks","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Szegedy"},{"key":"ref11","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Amodei"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/741"},{"key":"ref13","article-title":"Faag: Fast adversarial audio generation through interactive attack optimisation","author":"Miao","year":"2022"},{"key":"ref14","first-page":"2667","article-title":"{Devil\u2019s} whisper: A general approach for physical adversarial attacks against commercial black-box speech recognition devices","volume-title":"Proceedings of the 29th USENIX Security Symposium","author":"Chen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096873"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107184"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500431"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670309"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","volume-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref23","volume-title":"Alibaba asr","year":"2024"},{"key":"ref24","volume-title":"Iflytek speech to text","year":"2024"},{"key":"ref25","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford"},{"key":"ref26","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"33","author":"Baevski"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209891.pdf?arnumber=11209891","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:32:53Z","timestamp":1761888773000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209891\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209891","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}