{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:26:31Z","timestamp":1792513591022,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,4]]},"DOI":"10.1145\/3627106.3627183","type":"proceedings-article","created":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T18:13:22Z","timestamp":1701540802000},"page":"394-408","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Protecting Your Voice from Speech Synthesis Attacks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6956-8126","authenticated-orcid":false,"given":"Zihao","family":"Liu","sequence":"first","affiliation":[{"name":"Iowa State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5562-8001","authenticated-orcid":false,"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Iowa State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9646-7099","authenticated-orcid":false,"given":"Chenglin","family":"Miao","sequence":"additional","affiliation":[{"name":"Iowa State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,12,4]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2019. Resemblyzer. https:\/\/github.com\/resemble-ai\/Resemblyzer."},{"key":"e_1_3_2_1_2_1","unstructured":"2019. The Wall Street Journal. https:\/\/www.wsj.com\/articles\/fraudsters-use-ai-to-mimic-ceos-voice-in-unusual-cybercrime-case-11567157402."},{"key":"e_1_3_2_1_3_1","unstructured":"2021. Forbes. https:\/\/www.forbes.com\/sites\/thomasbrewster\/2021\/10\/14\/huge-bank-fraud-uses-deep-fake-voice-tech-to-steal-millions\/?sh=2fdf0c417559."},{"key":"e_1_3_2_1_4_1","unstructured":"2021. vc-github. https:\/\/github.com\/cyhuang-tw\/attack-vc."},{"key":"e_1_3_2_1_5_1","unstructured":"2023. Alexa. https:\/\/www.amazon.com\/gp\/help\/customer\/display.html?nodeId=GYCXKY2AB2QWZT2X."},{"key":"e_1_3_2_1_6_1","unstructured":"2023. audible. https:\/\/www.audible.com\/."},{"key":"e_1_3_2_1_7_1","unstructured":"2023. Azure. https:\/\/azure.microsoft.com\/en-us\/services\/cognitive-services\/speaker-recognition\/."},{"key":"e_1_3_2_1_8_1","unstructured":"2023. Mturk. https:\/\/www.mturk.com\/."},{"key":"e_1_3_2_1_9_1","unstructured":"2023. soundcloud. https:\/\/soundcloud.com."},{"key":"e_1_3_2_1_10_1","unstructured":"2023. speechify. https:\/\/www.speechify.com\/."},{"key":"e_1_3_2_1_11_1","unstructured":"2023. WeChat. https:\/\/help.wechat.com\/cgi-bin\/micromsg-bin\/oshelpcenter?opcode=2&plat=ios&lang=en&id=150819uqYnUR150819YzINVb."},{"key":"e_1_3_2_1_12_1","volume-title":"29th USENIX Security Symposium (USENIX Security 20)","author":"Ahmed Muhammad\u00a0Ejaz","year":"2020","unstructured":"Muhammad\u00a0Ejaz Ahmed, Il-Youp Kwak, Jun\u00a0Ho Huh, Iljoo Kim, Taekkyung Oh, and Hyoungshick Kim. 2020. Void: A fast and light voice liveness detection system. In 29th USENIX Security Symposium (USENIX Security 20). 2685\u20132702."},{"key":"e_1_3_2_1_13_1","volume-title":"CVPR Workshops. 104\u2013109","author":"AlBadawy A","year":"2019","unstructured":"Ehab\u00a0A AlBadawy, Siwei Lyu, and Hany Farid. 2019. Detecting AI-Synthesized Speech Using Bispectral Analysis.. In CVPR Workshops. 104\u2013109."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3433210.3437518"},{"key":"e_1_3_2_1_15_1","volume-title":"Workshop on Very Large Scale Phonetics Research, UPenn","author":"Anumanchipalli Gopala\u00a0Krishna","year":"2011","unstructured":"Gopala\u00a0Krishna Anumanchipalli, Kishore Prahallad, and Alan\u00a0W Black. 2011. Festvox: Tools for creation and analyses of large speech corpora. In Workshop on Very Large Scale Phonetics Research, UPenn, Philadelphia, Vol.\u00a070."},{"key":"e_1_3_2_1_16_1","volume-title":"Neural voice cloning with a few samples. Advances in Neural Information Processing Systems 31","author":"Arik Sercan","year":"2018","unstructured":"Sercan Arik, Jitong Chen, Kainan Peng, Wei Ping, and Yanqi Zhou. 2018. Neural voice cloning with a few samples. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_1_17_1","volume-title":"Algorithms for hyper-parameter optimization. Advances in neural information processing systems 24","author":"Bergstra James","year":"2011","unstructured":"James Bergstra, R\u00e9mi Bardenet, Yoshua Bengio, and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. Advances in neural information processing systems 24 (2011)."},{"key":"e_1_3_2_1_18_1","volume-title":"31st USENIX Security Symposium (USENIX Security 22)","author":"Blue Logan","year":"2022","unstructured":"Logan Blue, Kevin Warren, Hadi Abdullah, Cassidy Gibson, Luis Vargas, Jessica O\u2019Dell, Kevin Butler, and Patrick Traynor. 2022. Who Are You (I Really Wanna Know)? Detecting Audio { DeepFakes} Through Vocal Tract Reconstruction. In 31st USENIX Security Symposium (USENIX Security 22). 2691\u20132708."},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Machine Learning. PMLR, 2709\u20132720","author":"Casanova Edresson","year":"2022","unstructured":"Edresson Casanova, Julian Weber, Christopher\u00a0D Shulby, Arnaldo\u00a0Candido Junior, Eren G\u00f6lge, and Moacir\u00a0A Ponti. 2022. Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone. In International Conference on Machine Learning. PMLR, 2709\u20132720."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.133"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10869-016-9458-5"},{"key":"e_1_3_2_1_22_1","volume-title":"One-shot voice conversion by separating speaker and content representations with instance normalization. arXiv preprint arXiv:1904.05742","year":"2019","unstructured":"Ju-chieh Chou, Cheng-chieh Yeh, and Hung-yi Lee. 2019. One-shot voice conversion by separating speaker and content representations with instance normalization. arXiv preprint arXiv:1904.05742 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Catch You and I Can: Revealing Source Voiceprint Against Voice Conversion. arXiv preprint arXiv:2302.12434","author":"Deng Jiangyi","year":"2023","unstructured":"Jiangyi Deng, Yanjiao Chen, Yinan Zhong, Qianhao Miao, Xueluan Gong, and Wenyuan Xu. 2023. Catch You and I Can: Revealing Source Voiceprint Against Voice Conversion. arXiv preprint arXiv:2302.12434 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"An introduction to text-to-speech synthesis. Vol.\u00a03","author":"Dutoit Thierry","unstructured":"Thierry Dutoit. 1997. An introduction to text-to-speech synthesis. Vol.\u00a03. Springer Science & Business Media."},{"key":"e_1_3_2_1_25_1","volume-title":"The rainbow passage. Voice and articulation drillbook 2","author":"Fairbanks Grant","year":"1960","unstructured":"Grant Fairbanks. 1960. The rainbow passage. Voice and articulation drillbook 2 (1960), 127\u2013127."},{"key":"e_1_3_2_1_26_1","volume-title":"Wavefake: A data set to facilitate audio deepfake detection. arXiv preprint arXiv:2111.02813","author":"Frank Joel","year":"2021","unstructured":"Joel Frank and Lea Sch\u00f6nherr. 2021. Wavefake: A data set to facilitate audio deepfake detection. arXiv preprint arXiv:2111.02813 (2021)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISECS.2010.65"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"e_1_3_2_1_29_1","volume-title":"Hierarchical generative modeling for controllable speech synthesis. arXiv preprint arXiv:1810.07217","author":"Hsu Wei-Ning","year":"2018","unstructured":"Wei-Ning Hsu, Yu Zhang, Ron\u00a0J Weiss, Heiga Zen, Yonghui Wu, Yuxuan Wang, Yuan Cao, Ye Jia, Zhifeng Chen, Jonathan Shen, 2018. Hierarchical generative modeling for controllable speech synthesis. arXiv preprint arXiv:1810.07217 (2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-5"},{"key":"e_1_3_2_1_31_1","volume-title":"2021 IEEE Spoken Language Technology Workshop (SLT). IEEE, 552\u2013559","author":"Lin Y","year":"2021","unstructured":"Chien-yu Huang, Yist\u00a0Y Lin, Hung-yi Lee, and Lin-shan Lee. 2021. Defending your voice: Adversarial attack on voice conversion. In 2021 IEEE Spoken Language Technology Workshop (SLT). IEEE, 552\u2013559."},{"key":"e_1_3_2_1_32_1","volume-title":"2021 IEEE Spoken Language Technology Workshop (SLT). IEEE, 514\u2013521","year":"2021","unstructured":"Tzu-hsien Huang, Jheng-hao Lin, and Hung-yi Lee. 2021. How far are we from robust voice conversion: A survey. In 2021 IEEE Spoken Language Technology Workshop (SLT). IEEE, 514\u2013521."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-020-00691-4"},{"key":"e_1_3_2_1_34_1","unstructured":"Corentin Jemine 2019. Master thesis: Real-time voice cloning. (2019)."},{"key":"e_1_3_2_1_35_1","volume-title":"Direct speech-to-speech translation with a sequence-to-sequence model. arXiv preprint arXiv:1904.06037","author":"Jia Ye","year":"2019","unstructured":"Ye Jia, Ron\u00a0J Weiss, Fadi Biadsy, Wolfgang Macherey, Melvin Johnson, Zhifeng Chen, and Yonghui Wu. 2019. Direct speech-to-speech translation with a sequence-to-sequence model. arXiv preprint arXiv:1904.06037 (2019)."},{"key":"e_1_3_2_1_36_1","volume-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis. Advances in neural information processing systems 31","author":"Jia Ye","year":"2018","unstructured":"Ye Jia, Yu Zhang, Ron Weiss, Quan Wang, Jonathan Shen, Fei Ren, Patrick Nguyen, Ruoming Pang, Ignacio Lopez\u00a0Moreno, Yonghui Wu, 2018. Transfer learning from speaker verification to multispeaker text-to-speech synthesis. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495550"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682743"},{"key":"e_1_3_2_1_40_1","volume-title":"S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations. arXiv preprint arXiv:2104.02901","author":"Lin Y","year":"2021","unstructured":"Jheng-hao Lin, Yist\u00a0Y Lin, Chung-Ming Chien, and Hung-yi Lee. 2021. S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations. arXiv preprint arXiv:2104.02901 (2021)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1999-313"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1080\/17483107.2017.1319428"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24177-7_30"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"John Mullennix and Steven Stern. 2010. Computer Synthesized Speech Technologies: Tools for Aiding Impairment: Tools for Aiding Impairment. IGI Global.","DOI":"10.4018\/978-1-61520-725-1"},{"key":"e_1_3_2_1_46_1","volume-title":"Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612","author":"Nagrani Arsha","year":"2017","unstructured":"Arsha Nagrani, Joon\u00a0Son Chung, and Andrew Zisserman. 2017. Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)."},{"key":"e_1_3_2_1_47_1","unstructured":"Satoshi Nakamura. 2009. Overcoming the language barrier with speech translation technology. Technical Report. Citeseer."},{"key":"e_1_3_2_1_48_1","volume-title":"Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499","author":"van\u00a0den Oord Aaron","year":"2016","unstructured":"Aaron van\u00a0den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu. 2016. Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_50_1","volume-title":"Fighting Voice Spam with a Virtual Assistant Prototype. arXiv preprint arXiv:2008.03554","author":"Pandit Sharbani","year":"2020","unstructured":"Sharbani Pandit, Jienan Liu, Roberto Perdisci, and Mustaque Ahamad. 2020. Fighting Voice Spam with a Virtual Assistant Prototype. arXiv preprint arXiv:2008.03554 (2020)."},{"key":"e_1_3_2_1_51_1","unstructured":"Wei Ping Kainan Peng Andrew Gibiansky Sercan\u00a0\u00d6mer Arik Ajay Kannan Sharan Narang Jonathan Raiman and John Miller. 2017. Deep Voice 3: 2000-Speaker Neural Text-to-Speech. (2017)."},{"key":"e_1_3_2_1_52_1","volume-title":"International Conference on Machine Learning. PMLR, 5210\u20135219","author":"Qian Kaizhi","year":"2019","unstructured":"Kaizhi Qian, Yang Zhang, Shiyu Chang, Xuesong Yang, and Mark Hasegawa-Johnson. 2019. Autovc: Zero-shot voice style transfer with only autoencoder loss. In International Conference on Machine Learning. PMLR, 5210\u20135219."},{"key":"e_1_3_2_1_53_1","volume-title":"Fastspeech: Fast, robust and controllable text to speech. Advances in Neural Information Processing Systems 32","author":"Ren Yi","year":"2019","unstructured":"Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2019. Fastspeech: Fast, robust and controllable text to speech. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380179"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3483272"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427228.3427289"},{"key":"e_1_3_2_1_57_1","volume-title":"Naturalspeech: End-to-end text to speech synthesis with human-level quality. arXiv preprint arXiv:2205.04421","author":"Tan Xu","year":"2022","unstructured":"Xu Tan, Jiawei Chen, Haohe Liu, Jian Cong, Chen Zhang, Yanqing Liu, Xi Wang, Yichong Leng, Yuanhao Yi, Lei He, 2022. Naturalspeech: End-to-end text to speech synthesis with human-level quality. arXiv preprint arXiv:2205.04421 (2022)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"e_1_3_2_1_59_1","volume-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux Christophe","unstructured":"Christophe Veaux, Junichi Yamagishi, Kirsten MacDonald, 2017. CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit. University of Edinburgh. The Centre for Speech Technology Research (CSTR) (2017)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448300.3467825"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"e_1_3_2_1_62_1","unstructured":"Chen Wang Cong Shi Yingying Chen Yan Wang and Nitesh Saxena. 2020. WearID: Wearable-assisted low-effort authentication to voice assistants using cross-domain speech similarity. arXiv preprint arXiv:2003.09083 (2020)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737422"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413716"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417254"},{"key":"e_1_3_2_1_66_1","volume-title":"Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135","author":"Wang Yuxuan","year":"2017","unstructured":"Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron\u00a0J Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, 2017. Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3484742"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3354248"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133962"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978296"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23525"}],"event":{"name":"ACSAC '23: Annual Computer Security Applications Conference","location":"Austin TX USA","acronym":"ACSAC '23"},"container-title":["Annual Computer Security Applications Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627106.3627183","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627106.3627183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:40:59Z","timestamp":1755884459000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627106.3627183"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":71,"alternative-id":["10.1145\/3627106.3627183","10.1145\/3627106"],"URL":"https:\/\/doi.org\/10.1145\/3627106.3627183","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]},"assertion":[{"value":"2023-12-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}