{"id":"https://openalex.org/W4381161978","doi":"https://doi.org/10.1145/3577163.3595104","title":"Extracting Efficient Spectrograms From MP3 Compressed Speech Signals for Synthetic Speech Detection","display_name":"Extracting Efficient Spectrograms From MP3 Compressed Speech Signals for Synthetic Speech Detection","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4381161978","doi":"https://doi.org/10.1145/3577163.3595104"},"language":"en","primary_location":{"id":"doi:10.1145/3577163.3595104","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577163.3595104","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577163.3595104","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3577163.3595104","any_repository_has_fulltext":null},"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, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6054-5801","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055125973","display_name":"Amit Kumar Singh Yadav","orcid":"https://orcid.org/0000-0001-6464-7688"},"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":"Amit Kumar Singh Yadav","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6464-7688","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"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, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1990-9869","affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"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, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0406-0222","affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, 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, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-2909-7323","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, 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":1.45,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84571228,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9987000226974487,"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/spectrogram","display_name":"Spectrogram","score":0.9258905649185181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832025289535522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7311579585075378},{"id":"https://openalex.org/keywords/spec#","display_name":"Spec#","score":0.5996708273887634},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5867159366607666},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5686579346656799},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5567415356636047},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5240153074264526},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.5084718465805054},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.46587133407592773},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4417494535446167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35457777976989746},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.29330527782440186},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2116982340812683},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.10400566458702087},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09895506501197815},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09605485200881958}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9258905649185181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832025289535522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7311579585075378},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.5996708273887634},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5867159366607666},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5686579346656799},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5567415356636047},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5240153074264526},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.5084718465805054},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.46587133407592773},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4417494535446167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35457777976989746},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.29330527782440186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2116982340812683},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.10400566458702087},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09895506501197815},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09605485200881958},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3577163.3595104","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577163.3595104","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577163.3595104","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1265883","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1265883","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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3577163.3595104","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577163.3595104","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577163.3595104","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1579019551","display_name":null,"funder_award_id":"FA8750-20-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8140536623","display_name":null,"funder_award_id":"FA8750-20-2-1004","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320309036","display_name":"Purdue University","ror":"https://ror.org/02dqehb95"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381161978.pdf","grobid_xml":"https://content.openalex.org/works/W4381161978.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W94094186","https://openalex.org/W220935706","https://openalex.org/W1597562062","https://openalex.org/W1972475755","https://openalex.org/W2030318818","https://openalex.org/W2036326986","https://openalex.org/W2052384514","https://openalex.org/W2076608692","https://openalex.org/W2117539524","https://openalex.org/W2128301448","https://openalex.org/W2130436112","https://openalex.org/W2158698691","https://openalex.org/W2172065531","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2571081683","https://openalex.org/W2604292070","https://openalex.org/W2766465839","https://openalex.org/W2793428453","https://openalex.org/W2889387262","https://openalex.org/W2964121744","https://openalex.org/W2982083293","https://openalex.org/W2989571531","https://openalex.org/W3097079238","https://openalex.org/W3126967250","https://openalex.org/W3127806559","https://openalex.org/W3128666957","https://openalex.org/W3131786367","https://openalex.org/W3171302872","https://openalex.org/W3180160903","https://openalex.org/W3197123936","https://openalex.org/W3205798727","https://openalex.org/W4221149301","https://openalex.org/W4224986264","https://openalex.org/W4225420087","https://openalex.org/W4226346368","https://openalex.org/W6891850991"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W82005754","https://openalex.org/W2334448276","https://openalex.org/W3210733254"],"abstract_inverted_index":{"Many":[0],"speech":[1,15,22,30,54,112,121,132,156,163,170],"signals":[2],"are":[3],"compressed":[4,53,60],"with":[5],"MP3":[6,42,52,93,104],"to":[7,32,46,128,148,155,193,203],"reduce":[8,77],"the":[9,18,21,29,39,48,51,59,64,78,98,103,119,150,160,167,179],"data":[10],"rate.":[11],"In":[12],"many":[13],"synthetic":[14,120,169],"detection":[16,171,182],"methods":[17],"spectrogram":[19,49,81],"of":[20,41,50,80,92,152,188],"signal":[23,31,133],"is":[24,126,134,190],"used.":[25],"This":[26],"usually":[27],"requires":[28],"be":[33,201],"fully":[34,57,161],"decompressed.":[35],"We":[36,62,115,141],"show":[37],"that":[38],"design":[40],"compression":[43,206],"allows":[44],"one":[45],"approximate":[47],"efficiently":[55],"without":[56],"decoding":[58,94],"speech.":[61],"denote":[63],"spectograms":[65],"obtained":[66],"using":[67],"our":[68],"proposed":[69],"approach":[70],"by":[71,83,102],"Efficient":[72],"Spectrograms":[73],"(E-Specs).":[74],"E-Spec":[75,96,117,153,165,189,199],"can":[76,200],"complexity":[79],"computation":[82,187],"~77.60":[84],"percentage":[85],"points":[86],"(p.p.)":[87],"and":[88],"save":[89],"~37.87":[90],"p.p.":[91],"time.":[95],"bypasses":[97],"reconstruction":[99],"artifacts":[100],"introduced":[101],"synthesis":[105],"filterbank,":[106],"which":[107],"makes":[108],"it":[109,176],"useful":[110],"in":[111,118],"forensics":[113],"tasks.":[114],"tested":[116],"detection,":[122],"where":[123],"a":[124,131,139],"detector":[125],"asked":[127],"determine":[129],"whether":[130],"synthesized":[135],"or":[136],"recorded":[137],"from":[138,159],"human.":[140],"examined":[142],"4":[143],"different":[144],"neural":[145],"network":[146],"architectures":[147],"evaluate":[149],"performance":[151,172,183],"compared":[154],"features":[157],"extracted":[158],"decoded":[162],"signal.":[164],"achieved":[166,178],"best":[168,180],"for":[173],"3":[174],"architectures;":[175],"also":[177],"overall":[181],"across":[184],"architectures.":[185],"The":[186],"an":[191],"approximation":[192],"Short":[194],"Time":[195],"Fourier":[196],"Transform":[197],"(STFT).":[198],"extended":[202],"other":[204],"audio":[205],"methods.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}