{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:36:24Z","timestamp":1740101784409,"version":"3.37.3"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095043","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["ASSD: Synthetic Speech Detection in the AAC Compressed Domain"],"prefix":"10.1109","author":[{"given":"Amit Kumar","family":"Singh Yadav","sequence":"first","affiliation":[{"name":"Purdue University,Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering,West Lafayette,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyue","family":"Xiang","sequence":"additional","affiliation":[{"name":"Purdue University,Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering,West Lafayette,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily R.","family":"Bartusiak","sequence":"additional","affiliation":[{"name":"Purdue University,Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering,West Lafayette,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Bestagini","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milano,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefano","family":"Tubaro","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milano,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward J.","family":"Delp","sequence":"additional","affiliation":[{"name":"Purdue University,Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering,West Lafayette,Indiana,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.395275"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414427"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref7","first-page":"1","article-title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Ren"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462018"},{"key":"ref9","first-page":"10019","article-title":"Neural Voice Cloning with a Few Samples","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","volume":"31","author":"Arik"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2723721"},{"key":"ref11","article-title":"Goldman Sachs, Ozy Media and a $40 Million Conference Call Gone Wrong","volume-title":"The New York Times","author":"Smith","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASYU52992.2021.9598977"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICAI52203.2021.9445238"},{"key":"ref14","article-title":"An Overview of Recent Work in Media Forensics: Methods and Threats","author":"Bhagtani","year":"2022","journal-title":"arXiv preprint arXiv:2204.12067"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF53345.2021.9723142"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3089437"},{"volume-title":"1997 Information technology - Generic Coding of Moving Pictures and Associated Audio Information - Part 7: Advanced Audio Coding (AAC)","year":"1997","key":"ref17"},{"key":"ref18","first-page":"487","article-title":"General Audio Coding","volume-title":"The MPEG-4 Book","author":"Herre","year":"2002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413828"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.11.004"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2647201"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4277-2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-021-06297-w"},{"volume-title":"TheoryandApplicationsofDigitalSpeechProcessing","year":"2010","author":"Rabiner","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-43886-2_19"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747639"},{"volume-title":"1995 Information technology - Generic Coding of Moving Pictures and Associated Audio Information - Part 3: Audio","year":"1995","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/info9070161"},{"article-title":"Attention is All You Need","volume-title":"Proceedings of the Neural Information Processing Systems","author":"Vaswani","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2352\/ei.2023.35.4.mwsf-372"},{"article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Dosovitskiy","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-227"},{"article-title":"MP3 and AAC Explained","volume-title":"Proceedings of the 17th International Conference of Audio Engineering Society: High-Quality Audio Coding","author":"Brandenburg","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.842996"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"volume-title":"ASVspoof 2019: The 3rd Automatic Speaker Verification Spoofing and Countermeasures Challenge database","year":"2019","author":"Yamagishi","key":"ref43"},{"volume-title":"YouTube Recommended Upload Encoding Settings","year":"2022","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.aci.2018.08.003"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.764"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_29"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095043.pdf?arnumber=10095043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:36:08Z","timestamp":1709246168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095043","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}