{"id":"https://openalex.org/W4221149301","doi":"https://doi.org/10.1109/icassp43922.2022.9747639","title":"Forensic Analysis and Localization of Multiply Compressed MP3 Audio Using Transformers","display_name":"Forensic Analysis and Localization of Multiply Compressed MP3 Audio Using Transformers","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221149301","doi":"https://doi.org/10.1109/icassp43922.2022.9747639"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747639","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.16499","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057999558","display_name":"Ziyue Xiang","orcid":"https://orcid.org/0000-0001-6054-5801"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyue Xiang","raw_affiliation_strings":["Purdue University,Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering,West Lafayette,Indiana,USA","Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering,West Lafayette,Indiana,USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051370303","display_name":"Paolo Bestagini","orcid":"https://orcid.org/0000-0003-0406-0222"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Bestagini","raw_affiliation_strings":["Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milano,Italy","Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milano,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005378965","display_name":"Stefano Tubaro","orcid":"https://orcid.org/0000-0002-1990-9869"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Tubaro","raw_affiliation_strings":["Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milano,Italy","Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Informazione e Bioingegneria,Dipartimento di Elettronica,Milano,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089688702","display_name":"Edward J. Delp","orcid":"https://orcid.org/0000-0002-2909-7323"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward J. Delp","raw_affiliation_strings":["Purdue University,Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering,West Lafayette,Indiana,USA","Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering,West Lafayette,Indiana,USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Video and Image Processing Lab (VIPER), School of Electrical and Computer Engineering, Purdue University, West Lafayette, Indiana, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0171,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84496539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2929","last_page":"2933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.816216230392456},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.7774089574813843},{"id":"https://openalex.org/keywords/uncompressed-video","display_name":"Uncompressed video","score":0.7355010509490967},{"id":"https://openalex.org/keywords/dynamic-range-compression","display_name":"Dynamic range compression","score":0.6673553586006165},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.637740969657898},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6053006052970886},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5683313608169556},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5484089851379395},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.5462495684623718},{"id":"https://openalex.org/keywords/audio-signal-flow","display_name":"Audio signal flow","score":0.48318734765052795},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4468940198421478},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4313097894191742},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42590928077697754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24046096205711365},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.23411977291107178},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11075690388679504},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08230572938919067},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.06694081425666809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816216230392456},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.7774089574813843},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.7355010509490967},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.6673553586006165},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.637740969657898},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6053006052970886},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5683313608169556},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5484089851379395},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.5462495684623718},{"id":"https://openalex.org/C167940747","wikidata":"https://www.wikidata.org/wiki/Q63727227","display_name":"Audio signal flow","level":5,"score":0.48318734765052795},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4468940198421478},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4313097894191742},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42590928077697754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24046096205711365},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.23411977291107178},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11075690388679504},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08230572938919067},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.06694081425666809},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747639","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.16499","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.16499","pdf_url":"https://arxiv.org/pdf/2203.16499","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:re.public.polimi.it:11311/1233407","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1233407","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.16499","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.16499","pdf_url":"https://arxiv.org/pdf/2203.16499","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1151924489","https://openalex.org/W1474022922","https://openalex.org/W1522301498","https://openalex.org/W1996355929","https://openalex.org/W2004478479","https://openalex.org/W2036326986","https://openalex.org/W2040759991","https://openalex.org/W2056177844","https://openalex.org/W2086320398","https://openalex.org/W2101807845","https://openalex.org/W2117497587","https://openalex.org/W2133824856","https://openalex.org/W2144520790","https://openalex.org/W2151167680","https://openalex.org/W2417429787","https://openalex.org/W2523246573","https://openalex.org/W2793428453","https://openalex.org/W2899663614","https://openalex.org/W2950547518","https://openalex.org/W2963300588","https://openalex.org/W3033411150","https://openalex.org/W3081746081","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3157576687","https://openalex.org/W3177828909","https://openalex.org/W4287643567","https://openalex.org/W4287802874","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6602002561","https://openalex.org/W6627467931","https://openalex.org/W6630236247","https://openalex.org/W6631190155","https://openalex.org/W6649599172","https://openalex.org/W6727249380","https://openalex.org/W6739901393","https://openalex.org/W6749522612","https://openalex.org/W6755182157","https://openalex.org/W6755977528","https://openalex.org/W6776218486","https://openalex.org/W6778485988","https://openalex.org/W6778823374","https://openalex.org/W6778883912","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2363106653","https://openalex.org/W1975359510","https://openalex.org/W2375101025","https://openalex.org/W2898469868","https://openalex.org/W2069094726","https://openalex.org/W1833351015","https://openalex.org/W2088690926","https://openalex.org/W2289868279","https://openalex.org/W2156191292","https://openalex.org/W4221149301"],"abstract_inverted_index":{"Audio":[0,18],"signals":[1],"are":[2],"often":[3],"stored":[4],"and":[5,25,71,138],"transmitted":[6],"in":[7,36],"compressed":[8,38,70],"formats.":[9],"Among":[10],"the":[11,37,47,59,81,85,108,114],"many":[12],"available":[13],"audio":[14,39,52,62,73,99,131],"compression":[15,106],"schemes,":[16],"MPEG-1":[17],"Layer":[19],"III":[20],"(MP3)":[21],"is":[22,30,113],"very":[23],"popular":[24],"widely":[26],"used.":[27],"Since":[28],"MP3":[29,119,130,145],"lossy":[31],"it":[32],"leaves":[33],"characteristic":[34],"traces":[35],"which":[40,94,112],"can":[41],"be":[42],"used":[43],"forensically":[44],"to":[45,79,143],"expose":[46],"past":[48],"history":[49],"of":[50,61,69,84,97,118,128],"an":[51],"file.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"consider":[58],"scenario":[60],"signal":[63,100],"manipulation":[64],"done":[65],"by":[66],"temporal":[67,82,95,109,116],"splicing":[68],"uncompressed":[72],"signals.":[74],"We":[75,121],"propose":[76],"a":[77,98,126],"method":[78,92,124,134],"find":[80],"location":[83],"splices":[86],"based":[87],"on":[88,125],"transformer":[89],"networks.":[90],"Our":[91,133],"identifies":[93],"portions":[96],"have":[101],"undergone":[102],"single":[103],"or":[104],"multiple":[105],"at":[107],"frame":[110],"level,":[111],"smallest":[115],"unit":[117],"compression.":[120],"tested":[122],"our":[123],"dataset":[127],"486,743":[129],"clips.":[132],"achieved":[135],"higher":[136],"performance":[137],"demonstrated":[139],"robustness":[140],"with":[141,149],"respect":[142],"different":[144],"data":[146],"when":[147],"compared":[148],"existing":[150],"methods.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2022-04-03T00:00:00"}