{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T18:14:42Z","timestamp":1783361682327,"version":"3.54.6"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747639","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"2929-2933","source":"Crossref","is-referenced-by-count":10,"title":["Forensic Analysis and Localization of Multiply Compressed MP3 Audio Using Transformers"],"prefix":"10.1109","author":[{"given":"Ziyue","family":"Xiang","sequence":"first","affiliation":[{"name":"Purdue University,Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering,West Lafayette,Indiana,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Bestagini","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milano,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Tubaro","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milano,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref32","year":"0","journal-title":"FFmpeg MP3 encoding guide"},{"key":"ref31","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","author":"hawthorne","year":"2019","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.764"},{"key":"ref35","article-title":"Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation","author":"powers","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/234034a0"},{"key":"ref10","article-title":"MP3 and AAC explained","author":"brandenburg","year":"1999","journal-title":"Proceedings of the AES 17th International Conference on High-Quality Audio Coding"},{"key":"ref11","first-page":"200","article-title":"Detecting double compression of audio signal","volume":"7541","author":"yang","year":"2010","journal-title":"Media Forensics and Security II"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCC.2013.6664121"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.4304\/jsw.9.10.2522-2527"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-43886-2_19"},{"key":"ref15","first-page":"662","article-title":"Compression history detection for MP3 audio","volume":"12","author":"yan","year":"2018","journal-title":"KSII Transactions on Internet and Information Systems (TIIS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/1687-417X-2014-10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57881-7_35"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/5.241504"},{"key":"ref28","article-title":"Gaussian error linear units (gelus)","author":"hendrycks","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"ref27","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016"},{"key":"ref3","article-title":"Jukebox: A generative model for music","author":"dhariwal","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-010-9045-4"},{"key":"ref29","author":"ito","year":"2017","journal-title":"The LJ speech dataset"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1597817.1597838"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2006.1706505"},{"key":"ref7","year":"0","journal-title":"ISO\/IEC 13818-3 1995 - Information technology–Generic coding of moving pictures and associated audio information–Part 3 Audio"},{"key":"ref2","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020"},{"key":"ref9","year":"0","journal-title":"ISO\/IEC 13818-7 1997 - Information technology–Generic coding of moving pictures and associated audio information–Part 7 Advanced Audio Coding (AAC)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref20","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proceedings of 2020 European Conference on Computer Vision"},{"key":"ref21","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486599"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref26","article-title":"MP3 decoder in theory and practice","author":"sripada","year":"2006","journal-title":"M S thesis"},{"key":"ref25","author":"raissi","year":"2002","journal-title":"The theory behind MP3"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747639.pdf?arnumber=9747639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:12:41Z","timestamp":1661199161000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747639","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}