{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T07:04:40Z","timestamp":1776841480965,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1815724"],"award-info":[{"award-number":["1815724"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Michigan Translational Research and Commercialization, Advanced Computing Technologies","award":["292883"],"award-info":[{"award-number":["292883"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,12]]},"DOI":"10.1145\/3592572.3592841","type":"proceedings-article","created":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T22:05:45Z","timestamp":1685657145000},"page":"10-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["SpoTNet: A spoofing-aware Transformer Network for Effective Synthetic Speech Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7687","authenticated-orcid":false,"given":"Awais","family":"Khan","sequence":"first","affiliation":[{"name":"Department of Computer Science & Engineering, Oakland University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7927-3436","authenticated-orcid":false,"given":"Khalid Mahmood","family":"Malik","sequence":"additional","affiliation":[{"name":"Department of Computer Science & Engineering, Oakland University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Deep residual neural networks for audio spoofing detection. arXiv preprint arXiv:1907.00501","author":"Alzantot Moustafa","year":"2019","unstructured":"Moustafa Alzantot, Ziqi Wang, and Mani\u00a0B Srivastava. 2019. Deep residual neural networks for audio spoofing detection. arXiv preprint arXiv:1907.00501 (2019)."},{"key":"e_1_3_2_1_2_1","first-page":"55","article-title":"Synthetic speech spoofing detection using MFCC and radial basis function SVM","volume":"8","author":"Bhangale B","year":"2018","unstructured":"Kishor\u00a0B Bhangale, Prashant Titare, Raosaheb Pawar, and Sagar Bhavsar. 2018. Synthetic speech spoofing detection using MFCC and radial basis function SVM. IOSR J. Eng.(IOSRJEN) 8, 6 (2018), 55\u201362.","journal-title":"IOSR J. Eng.(IOSRJEN)"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Zhuxin Chen Zhifeng Xie Weibin Zhang and Xiangmin Xu. 2017. ResNet and Model Fusion for Automatic Spoofing Detection.. In Interspeech. 102\u2013106.","DOI":"10.21437\/Interspeech.2017-1085"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3183951"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10212-0"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3251895"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108283"},{"key":"e_1_3_2_1_9_1","volume-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 6367\u20136371","author":"Heo Hee-Soo","year":"2022","unstructured":"Jee-weon Jung, Hee-Soo Heo, Hemlata Tak, Hye-jin Shim, Joon\u00a0Son Chung, Bong-Jin Lee, Ha-Jin Yu, and Nicholas Evans. 2022. Aasist: Audio anti-spoofing using integrated spectro-temporal graph attention networks. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 6367\u20136371."},{"key":"e_1_3_2_1_10_1","volume-title":"Transformer engineering: design, technology, and diagnostics","author":"Kulkarni V","unstructured":"Shrikrishna\u00a0V Kulkarni and Shrikrishna\u00a0A Khaparde. 2017. Transformer engineering: design, technology, and diagnostics. CRC press."},{"key":"e_1_3_2_1_11_1","volume-title":"ASSERT: Anti-spoofing with squeeze-excitation and residual networks. arXiv preprint arXiv:1904.01120","author":"Lai I","year":"2019","unstructured":"Cheng-I Lai, Nanxin Chen, Jes\u00fas Villalba, and Najim Dehak. 2019. ASSERT: Anti-spoofing with squeeze-excitation and residual networks. arXiv preprint arXiv:1904.01120 (2019)."},{"key":"e_1_3_2_1_12_1","volume-title":"STC antispoofing systems for the ASVspoof2019 challenge. arXiv preprint arXiv:1904.05576","author":"Lavrentyeva Galina","year":"2019","unstructured":"Galina Lavrentyeva, Sergey Novoselov, Andzhukaev Tseren, Marina Volkova, Artem Gorlanov, and Alexandr Kozlov. 2019. STC antispoofing systems for the ASVspoof2019 challenge. arXiv preprint arXiv:1904.05576 (2019)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413828"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414670"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Prasanth Parasu Julien Epps Kaavya Sriskandaraja and Gajan Suthokumar. 2020. Investigating Light-ResNet Architecture for Spoofing Detection Under Mismatched Conditions.. In INTERSPEECH. 1111\u20131115.","DOI":"10.21437\/Interspeech.2020-2039"},{"key":"e_1_3_2_1_17_1","volume-title":"International conference on machine learning. PMLR, 4055\u20134064","author":"Parmar Niki","year":"2018","unstructured":"Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Noam Shazeer, Alexander Ku, and Dustin Tran. 2018. Image transformer. In International conference on machine learning. PMLR, 4055\u20134064."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960369"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.09.103"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12606-8"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5815\/ijigsp.2014.06.04"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"e_1_3_2_1_23_1","volume-title":"ARawNet: A Lightweight Solution for Leveraging Raw Waveforms in Spoof Speech Detection. In 2022 26th International Conference on Pattern Recognition (ICPR). IEEE, 692\u2013698","author":"Teng Zhongwei","year":"2022","unstructured":"Zhongwei Teng, Quchen Fu, Jules White, Maria\u00a0E Powell, and Douglas\u00a0C Schmidt. 2022. ARawNet: A Lightweight Solution for Leveraging Raw Waveforms in Spoof Speech Detection. In 2022 26th International Conference on Pattern Recognition (ICPR). IEEE, 692\u2013698."},{"key":"e_1_3_2_1_24_1","volume-title":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 1352\u20131360","author":"Wang Zheng","year":"2020","unstructured":"Zheng Wang, Sanshuai Cui, Xiangui Kang, Wei Sun, and Zhonghua Li. 2020. Densely connected convolutional network for audio spoofing detection. In 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 1352\u20131360."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/sym14020274"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Xiong Xiao Xiaohai Tian Steven Du Haihua Xu Engsiong Chng and Haizhou Li. 2015. Spoofing speech detection using high dimensional magnitude and phase features: the NTU approach for ASVspoof 2015 challenge.. In Interspeech. 2052\u20132056.","DOI":"10.21437\/Interspeech.2015-465"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3076358"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Yuxiang Zhang12 Wenchao Wang12 and Pengyuan Zhang12. 2021. The effect of silence and dual-band fusion in anti-spoofing system. (2021).","DOI":"10.21437\/Interspeech.2021-1281"}],"event":{"name":"ICMR '23: International Conference on Multimedia Retrieval","location":"Thessaloniki Greece","acronym":"ICMR '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3592572.3592841","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3592572.3592841","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3592572.3592841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:55Z","timestamp":1750183735000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3592572.3592841"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":29,"alternative-id":["10.1145\/3592572.3592841","10.1145\/3592572"],"URL":"https:\/\/doi.org\/10.1145\/3592572.3592841","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}