{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T04:08:29Z","timestamp":1741838909003,"version":"3.38.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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"}]},{"DOI":"10.13039\/501100019014","name":"Chengdu Science and Technology Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100019014","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,8]]},"DOI":"10.1109\/globecom52923.2024.10901725","type":"proceedings-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T17:30:35Z","timestamp":1741714235000},"page":"3146-3151","source":"Crossref","is-referenced-by-count":0,"title":["BadTTS: Identifying Vulnerabilities in Neural Text-to-Speech Models"],"prefix":"10.1109","author":[{"given":"Rui","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Li","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China,School of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaming","family":"He","sequence":"additional","affiliation":[{"name":"Chengdu University of Technology,College of Computer Science and Cyber Security (Oxford Brookes College),China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300376"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30817-9_6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-08841-6"},{"key":"ref4","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"Badnets: Identifying vulnerabilities in the machine learning model supply chain","year":"2017","author":"Gu","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00786"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3402179"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612108"},{"article-title":"The lj speech dataset","year":"2017","author":"Ito","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0169"},{"key":"ref13","first-page":"61","article-title":"Locating boundaries for prosodic constituents in unrestricted mandarin texts","author":"Chu","year":"2001","journal-title":"International Journal of Computational Linguistics & Chinese Language Processing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.01.002"},{"article-title":"Wavenet: A generative model for raw audio","year":"2016","author":"Van Den Oord","key":"ref15"},{"article-title":"Adversarial audio synthesis","year":"2018","author":"Donahue","key":"ref16"},{"key":"ref17","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of ICML","author":"Radford"},{"key":"ref18","first-page":"2370","article-title":"Beyond exploding and vanishing gradients: analysing rnn training using attractors and smoothness","volume-title":"Proceedings of AISTATS","author":"Ribeiro"}],"event":{"name":"GLOBECOM 2024 - 2024 IEEE Global Communications Conference","start":{"date-parts":[[2024,12,8]]},"location":"Cape Town, South Africa","end":{"date-parts":[[2024,12,12]]}},"container-title":["GLOBECOM 2024 - 2024 IEEE Global Communications Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10900933\/10900934\/10901725.pdf?arnumber=10901725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T05:51:03Z","timestamp":1741758663000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10901725\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/globecom52923.2024.10901725","relation":{},"subject":[],"published":{"date-parts":[[2024,12,8]]}}}