{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:57:37Z","timestamp":1776880657714,"version":"3.51.2"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency (DARPA)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory (AFRL)","doi-asserted-by":"publisher","award":["FA8750-20-2-1004"],"award-info":[{"award-number":["FA8750-20-2-1004"]}],"id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,29]]},"DOI":"10.1109\/ieeeconf59524.2023.10477041","type":"proceedings-article","created":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T19:28:52Z","timestamp":1711999732000},"page":"1100-1105","source":"Crossref","is-referenced-by-count":7,"title":["Transformer Ensemble for Synthesized Speech Detection"],"prefix":"10.1109","author":[{"given":"Emily R.","family":"Bartusiak","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab,West Lafayette,IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kratika","family":"Bhagtani","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab,West Lafayette,IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amit Kumar","family":"Singh Yadav","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab,West Lafayette,IN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward J.","family":"Delp","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab,West Lafayette,IN"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TEM.2021.3117884"},{"key":"ref2","volume-title":"Siri Does More than Ever. Even Before You Ask","year":"2021"},{"key":"ref3","volume-title":"Google Assistant in Your Car","year":"2021"},{"key":"ref4","volume-title":"What Is Alexa?","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CONIT51480.2021.9498529"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICACTE.2010.5579806"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1643823.1643908"},{"key":"ref8","volume-title":"Instagram Adds New Text-to-Speech and Voice Effect Options in Reels","author":"Hutchinson","year":"2021"},{"key":"ref9","volume-title":"How to Use TikToks Text-to-Speech feature","author":"Hatton","year":"2021"},{"key":"ref10","first-page":"5530","article-title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","volume-title":"Proceedings of the International Conference on Machine Learning","volume":"139","author":"Kim"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414427"},{"key":"ref12","first-page":"8599","article-title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","volume-title":"Proceedings of the International Conference on Machine Learning","volume":"139","author":"Popov"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR54900.2022.00064"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref15","first-page":"1","article-title":"An Overview of Recent Work in Media Forensics: Methods and Threats","author":"Bhagtani","year":"2022","journal-title":"arXiv"},{"key":"ref16","article-title":"The State of Deepfakes: Landscape, Threats, and Impact","volume-title":"Deeptrace Lab","author":"Ajder","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref18","article-title":"Deepfakes are Going to Wreck Havoc on Society. We are Not Prepared","volume-title":"Forbes","author":"Toews","year":"2020"},{"key":"ref19","volume-title":"Deepfake Video of Zelenskyy Could be \u2018Tip of the Iceberg\u2019 in Info War, Experts Warn","author":"Allyn","year":"2022"},{"key":"ref20","volume-title":"Deepfake Video of Volodymyr Zelensky Surrendering Surfaces on Social Media","author":"Telegraph","year":"2022"},{"key":"ref21","volume-title":"Goldman Sachs, Ozy Media and a $40 Million Conference Call Gone Wrong","author":"Smith","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-021-01196-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1111\/apps.12290"},{"key":"ref24","article-title":"Whats Next for Remote Work: An Analysis of 2,000 Tasks, 800 Jobs, and Nine Countries","volume-title":"McKinsey Global Institute","author":"Lund","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","first-page":"1","article-title":"Escaping the Big Data Paradigm with Compact Transformers","author":"Hassani","year":"2021","journal-title":"arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref30","article-title":"ASVspoof 2019: The 3rd Automatic Speaker Verification Spoofing and Countermeasures Challenge Database","author":"Yamagishi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research"},{"key":"ref31","first-page":"209","article-title":"The Quefrency Alanysis of Time Series for Echoes: Cepstrum, Pseudo Autocovariance, Cross-Cepstrum and Saphe Cracking","volume-title":"Proceedings of the Symposium on Time Series Analysis","volume":"15","author":"Bogert"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2999185"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3089437"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1085"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462644"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2352\/issn.2470-1173.2021.4.mwsf-273"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87664-7_11"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF53345.2021.9723142"},{"key":"ref39","article-title":"Machine Learning for Speech Forensics and Hypersonic Vehicle Applications","volume-title":"Purdue University","author":"Bartusiak","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA55696.2022.00054"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747186"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref43","first-page":"1","article-title":"Decoupled Weight Decay Regularization","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref45","first-page":"1","article-title":"An Image is Worth 16\n16 Words: Transformers for Image Recognition at Scale","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref46","first-page":"1","article-title":"Adam: A Method for Stochastic Optimization","volume-title":"Proceedings of the International Conference for Learning Representations","author":"Kingma"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref48","first-page":"1","article-title":"Generative Adversarial Nets","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","volume":"27","author":"Goodfellow"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.aci.2018.08.003"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"}],"event":{"name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2023,10,29]]},"end":{"date-parts":[[2023,11,1]]}},"container-title":["2023 57th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10476702\/10476779\/10477041.pdf?arnumber=10477041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T04:43:26Z","timestamp":1712033006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10477041\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,29]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf59524.2023.10477041","relation":{},"subject":[],"published":{"date-parts":[[2023,10,29]]}}}