{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T00:06:16Z","timestamp":1772150776081,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T00:00:00Z","timestamp":1717977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"HORIZON EUROPE Framework Programme","doi-asserted-by":"publisher","award":["101070093"],"award-info":[{"award-number":["101070093"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Bundesministerium f\u00fcr Bildung und Forschung","award":["03RU2U151D"],"award-info":[{"award-number":["03RU2U151D"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,10]]},"DOI":"10.1145\/3643491.3660288","type":"proceedings-article","created":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T06:19:37Z","timestamp":1717222777000},"page":"23-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Audio Transformer for Synthetic Speech Detection via Benford's Law Distribution Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7717-6943","authenticated-orcid":false,"given":"Anitha Bhat","family":"Talagini Ashoka","sequence":"first","affiliation":[{"name":"Fraunhofer Institute for Digital Media Technology IDMT, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5559-6508","authenticated-orcid":false,"given":"Luca","family":"Cuccovillo","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Digital Media Technology IDMT\\t, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4777-6335","authenticated-orcid":false,"given":"Patrick","family":"Aichroth","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Digital Media Technology IDMT\\t, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,10]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"551","article-title":"The Law of Anomalous Numbers","volume":"78","author":"Benford Frank","year":"1938","unstructured":"Frank Benford. 1938. The Law of Anomalous Numbers. Proceedings of the American Philosophical Society 78, 4 (1938), 551\u2013572.","journal-title":"Proceedings of the American Philosophical Society"},{"key":"e_1_3_2_1_2_1","volume-title":"2020 25th international conference on pattern recognition (ICPR). IEEE, 5495\u20135502","author":"Bonettini Nicolo","year":"2021","unstructured":"Nicolo Bonettini, Paolo Bestagini, Simone Milani, and Stefano Tubaro. 2021. On the use of Benford\u2019s law to detect GAN-generated images. In 2020 25th international conference on pattern recognition (ICPR). IEEE, 5495\u20135502."},{"key":"e_1_3_2_1_3_1","volume-title":"Workshop on Multi-view Lip-reading, ACCV.","author":"Chung S.","unstructured":"J.\u00a0S. Chung and A. Zisserman. 2016. Out of time: automated lip sync in the wild. In Workshop on Multi-view Lip-reading, ACCV."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445932"},{"key":"e_1_3_2_1_5_1","volume-title":"Open Challenges in Synthetic Speech Detection. In IEEE International Workshop on Information Forensics and Security (WIFS)","author":"Cuccovillo Luca","year":"2022","unstructured":"Luca Cuccovillo, Christoforos Papastergiopoulos, Anastasios Vafeiadis, Artem Yaroshchuk, Patrick Aichroth, Konstantinos Votis, and Dimitrios Tzovaras. 2022. Open Challenges in Synthetic Speech Detection. In IEEE International Workshop on Information Forensics and Security (WIFS). Shanghai, China, 1\u20136."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1080\/02664760601004940"},{"key":"e_1_3_2_1_7_1","unstructured":"EBU. 2020. R128-2020: Loudness Normalization and Permitted Maximum Level of Audio Signals."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","volume-title":"Gaussian Error Linear Units (GELUs). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian Error Linear Units (GELUs). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414470"},{"key":"e_1_3_2_1_11_1","volume-title":"AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks. In arXiv preprint arXiv:2110.01200.","author":"Heo Hee-Soo","year":"2021","unstructured":"Jee-weon Jung, Hee-Soo Heo, Hemlata Tak, Hye-jin Shim, Joon\u00a0Son Chung, Bong-Jin Lee, Ha-Jin Yu, and Nicholas Evans. 2021. AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks. In arXiv preprint arXiv:2110.01200."},{"key":"e_1_3_2_1_12_1","volume-title":"On information and sufficiency. The annals of mathematical statistics 22, 1","author":"Kullback Solomon","year":"1951","unstructured":"Solomon Kullback and Richard\u00a0A Leibler. 1951. On information and sufficiency. The annals of mathematical statistics 22, 1 (1951), 79\u201386."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Daniele Mari Federica Latora and Simone Milani. 2022. The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection. arxiv:2210.02746\u00a0[cs.SD]","DOI":"10.1109\/WIFS55849.2022.9975404"},{"key":"e_1_3_2_1_14_1","unstructured":"Daniele Mari Davide Salvi Paolo Bestagini and Simone Milani. 2023. All-for-One and One-For-All: Deep learning-based feature fusion for Synthetic Speech Detection. arxiv:2307.15555\u00a0[cs.SD]"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0016-0032(96)00063-4"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-9"},{"key":"e_1_3_2_1_17_1","volume-title":"Human Perception of Audio Deepfakes. In ACM International Workshop on Deepfake Detection for Audio Multimedia (DDAM)","author":"M\u00fcller M.","year":"2022","unstructured":"Nicolas\u00a0M. M\u00fcller, Karla Pizzi, and Jennifer Williams. 2022. Human Perception of Audio Deepfakes. In ACM International Workshop on Deepfake Detection for Audio Multimedia (DDAM). Lisboa, Portugal, 85\u201391."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1080\/00029890.1976.11994162"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3137597.3137600"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCom.2015.7150688"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-0475.2009.00475.x"},{"key":"e_1_3_2_1_27_1","volume-title":"ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech. Computer Speech & Language 64","author":"Wang Xin","year":"2020","unstructured":"Xin Wang, Junichi Yamagishi, Massimiliano Todisco, H\u00e9ctor Delgado, Andreas Nautsch, Nicholas Evans, Md Sahidullah, Ville Vestman, Tomi Kinnunen, Kong\u00a0Aik Lee, 2020. ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech. Computer Speech & Language 64 (2020)."}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["3rd ACM International Workshop on Multimedia AI against Disinformation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643491.3660288","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3643491.3660288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:35:32Z","timestamp":1756236932000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3643491.3660288"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,10]]},"references-count":27,"alternative-id":["10.1145\/3643491.3660288","10.1145\/3643491"],"URL":"https:\/\/doi.org\/10.1145\/3643491.3660288","relation":{},"subject":[],"published":{"date-parts":[[2024,6,10]]},"assertion":[{"value":"2024-06-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}