{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:54:02Z","timestamp":1762325642648,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"AFRL and DARPA","award":["FA8750-20-2-1004"],"award-info":[{"award-number":["FA8750-20-2-1004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,28]]},"DOI":"10.1145\/3577163.3595112","type":"proceedings-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T22:10:56Z","timestamp":1687212656000},"page":"157-162","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Synthesized Speech Attribution Using The Patchout Spectrogram Attribution Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7399-4876","authenticated-orcid":false,"given":"Kratika","family":"Bhagtani","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8202-8853","authenticated-orcid":false,"given":"Emily R.","family":"Bartusiak","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6464-7688","authenticated-orcid":false,"given":"Amit Kumar Singh","family":"Yadav","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0406-0222","authenticated-orcid":false,"given":"Paolo","family":"Bestagini","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Milan, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2909-7323","authenticated-orcid":false,"given":"Edward J.","family":"Delp","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2017. Deep Learning for Siri's Voice: On-device Deep Mixture Density Net- works for Hybrid Unit Selection Synthesis. https:\/\/machinelearning.apple.com\/research\/siri-voices"},{"key":"e_1_3_2_1_2_1","unstructured":"2020. Semantic Forensics (SemaFor). https:\/\/www.darpa.mil\/program\/semantic- forensics"},{"key":"e_1_3_2_1_3_1","unstructured":"2022. AI enabled real people's voices. https:\/\/murf.ai\/"},{"key":"e_1_3_2_1_4_1","unstructured":"2022. Deepfake Zelenskyy surrender video is the ?first intentionally used' in Ukraine war. https:\/\/www.euronews.com\/my-europe\/2022\/03\/16\/deepfake-zelenskyy-surrender-video-is-the-first-intentionally-used-in-ukraine-war"},{"key":"e_1_3_2_1_5_1","unstructured":"2022. Standard WaveNet and Neural2 voices. https:\/\/cloud.google.com\/text-to- speech\/docs\/wavenet"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF53345.2021.9723142"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.07546"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2204.12067"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR54900.2022.00064"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"e_1_3_2_1_11_1","unstructured":"Thomas Brewster. 2021. Fraudsters Cloned Company Director's Voice In $35 Million Bank Heist Police Find. https:\/\/www.forbes.com\/sites\/thomasbrewster\/2021\/10\/14\/huge-bank-fraud-uses-deep-fake-voice-tech-to-steal-millions\/'sh=6944ebd37559"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-19"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2999185"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2012.19"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021--698"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAI52203.2021.9445238"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the International Conference on Learning Representations (April","author":"Hendrycks Dan","year":"2017","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. Proceedings of the International Conference on Learning Representations (April 2017). https:\/\/openreview.net\/forum?id=Hkg4TI9xl Toulon, France."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.395275"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022--227"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413828"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2812185"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2019.00103"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660175"},{"key":"e_1_3_2_1_24_1","volume-title":"Schafer","author":"Rabiner Lawrence R.","year":"2010","unstructured":"Lawrence R. Rabiner and Ronald W. Schafer. 2010. Theory and Applications of Digital Speech Processing 1st ed.). Prentice Hall Press, USA."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011--820"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.15561"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aci.2018.08.003"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639067"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.2352\/EI.2023.35.4.MWSF-372"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.03323"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.7488\/ds"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3076358"}],"event":{"name":"IH&MMSec '23: ACM Workshop on Information Hiding and Multimedia Security","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"IH&MMSec '23"},"container-title":["Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577163.3595112","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577163.3595112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:10Z","timestamp":1750182670000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577163.3595112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,28]]},"references-count":36,"alternative-id":["10.1145\/3577163.3595112","10.1145\/3577163"],"URL":"https:\/\/doi.org\/10.1145\/3577163.3595112","relation":{},"subject":[],"published":{"date-parts":[[2023,6,28]]},"assertion":[{"value":"2023-06-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}