{"id":"https://openalex.org/W4381187661","doi":"https://doi.org/10.1145/3577163.3595112","title":"Synthesized Speech Attribution Using The Patchout Spectrogram Attribution Transformer","display_name":"Synthesized Speech Attribution Using The Patchout Spectrogram Attribution Transformer","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4381187661","doi":"https://doi.org/10.1145/3577163.3595112"},"language":"en","primary_location":{"id":"doi:10.1145/3577163.3595112","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577163.3595112","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577163.3595112","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/10.1145/3577163.3595112","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022400610","display_name":"Kratika Bhagtani","orcid":"https://orcid.org/0000-0001-7399-4876"},"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":"Kratika Bhagtani","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-7399-4876","affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062428716","display_name":"Emily R. Bartusiak","orcid":"https://orcid.org/0000-0002-8202-8853"},"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":"Emily R. Bartusiak","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0002-8202-8853","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/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":2.1779,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89598537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"157","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9991999864578247,"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":0.9991000294685364,"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":0.9105485677719116},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7406104803085327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7349972128868103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6889714002609253},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.6721349954605103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49109578132629395},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4561469256877899},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4158094525337219},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09942731261253357},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09931331872940063}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9105485677719116},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7406104803085327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7349972128868103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6889714002609253},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.6721349954605103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49109578132629395},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4561469256877899},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4158094525337219},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09942731261253357},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09931331872940063},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3577163.3595112","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577163.3595112","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577163.3595112","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:11311/1265884","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1265884","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:10.1145/3577163.3595112","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3577163.3595112","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3577163.3595112","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16"}],"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/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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4381187661.pdf","grobid_xml":"https://content.openalex.org/works/W4381187661.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2066452495","https://openalex.org/W2072065288","https://openalex.org/W2072473772","https://openalex.org/W2103869314","https://openalex.org/W2143597468","https://openalex.org/W2519091744","https://openalex.org/W2590129515","https://openalex.org/W2794045137","https://openalex.org/W2888728157","https://openalex.org/W2907295878","https://openalex.org/W2964243274","https://openalex.org/W3024920698","https://openalex.org/W3033711348","https://openalex.org/W3127781933","https://openalex.org/W3157576687","https://openalex.org/W3158663310","https://openalex.org/W3161011913","https://openalex.org/W3169317518","https://openalex.org/W3174758275","https://openalex.org/W4214896311","https://openalex.org/W4224986264","https://openalex.org/W4294975742","https://openalex.org/W4306705062","https://openalex.org/W4362684594","https://openalex.org/W4363671619"],"related_works":["https://openalex.org/W4310471687","https://openalex.org/W2115871458","https://openalex.org/W1991209043","https://openalex.org/W2161290483","https://openalex.org/W2100584800","https://openalex.org/W2205359483","https://openalex.org/W191286645","https://openalex.org/W4225280403","https://openalex.org/W4224263508","https://openalex.org/W769873483"],"abstract_inverted_index":{"The":[0],"malicious":[1],"use":[2,60],"of":[3,12,61],"synthetic":[4,51,71,101,126],"speech":[5,13,23,52,72,87,102,127],"has":[6],"increased":[7],"with":[8],"the":[9,37,45,59,106,113],"recent":[10],"availability":[11],"generation":[14,38,88],"tools.":[15],"It":[16],"is":[17,25,32,48],"important":[18],"to":[19,35,41],"determine":[20,36],"whether":[21],"a":[22,29,62],"signal":[24],"authentic":[26],"(spoken":[27],"by":[28],"human)":[30],"or":[31],"synthesized":[33],"and":[34,112,129],"method":[39,47,66,75,119],"used":[40],"create":[42],"it.":[43],"Identifying":[44],"synthesis":[46],"known":[49,76],"as":[50,77],"attribution.":[53,73],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"transformer":[63],"deep":[64,134],"learning":[65,135],"that":[67,117],"analyzes":[68],"mel-spectrograms":[69],"for":[70],"Our":[74],"Patchout":[78],"Spectrogram":[79],"Attribution":[80,110],"Transformer":[81],"(PSAT)":[82],"can":[83],"distinguish":[84],"new,":[85],"unseen":[86],"methods":[89],"from":[90],"those":[91],"seen":[92],"during":[93],"training.":[94],"PSAT":[95],"demonstrates":[96],"high":[97],"performance":[98],"in":[99,125],"attributing":[100],"signals.":[103],"Evaluation":[104],"on":[105],"DARPA":[107],"SemaFor":[108],"Audio":[109],"Dataset":[111,115],"ASVSpoof2019":[114],"shows":[116],"our":[118],"achieves":[120],"more":[121],"than":[122,132],"95%":[123],"accuracy":[124],"attribution":[128],"performs":[130],"better":[131],"existing":[133],"approaches.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2023-06-20T00:00:00"}
