{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T03:45:34Z","timestamp":1772595934416,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447190","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"4840-4844","source":"Crossref","is-referenced-by-count":4,"title":["AdvTTS: Adversarial Text-to-Speech Synthesis Attack on Speaker Identification Systems"],"prefix":"10.1109","author":[{"given":"Chu-Xiao","family":"Zuo","sequence":"first","affiliation":[{"name":"Nanjing University,National Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,China"}]},{"given":"Zhi-Jun","family":"Jia","sequence":"additional","affiliation":[{"name":"Nanjing University,National Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,China"}]},{"given":"Wu-Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University,National Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2015","journal-title":"ICLR"},{"key":"ref2","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2014","journal-title":"ICLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref5","first-page":"2206","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","volume":"119","author":"Croce","year":"2020","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tdsc.2022.3220673"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00004"},{"key":"ref10","article-title":"SMACK: semantically meaningful adversarial audio attack","author":"Yu","year":"2023","journal-title":"USENIX Security"},{"key":"ref11","article-title":"Blacklight: Defending black-box adversarial attacks on deep neural networks","author":"Li","year":"2020","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10139"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495413"},{"key":"ref14","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume":"162","author":"Casanova","year":"2022","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref16","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1275"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447190.pdf?arnumber=10447190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:31:32Z","timestamp":1722576692000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447190","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}