{"id":"https://openalex.org/W4393379886","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10476982","title":"FGSSAT : Unsupervised Fine-Grain Attribution of Unknown Speech Synthesizers Using Transformer Networks","display_name":"FGSSAT : Unsupervised Fine-Grain Attribution of Unknown Speech Synthesizers Using Transformer Networks","publication_year":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4393379886","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10476982"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf59524.2023.10476982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10476982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"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":["School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),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":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),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/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":["School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),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":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),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/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":["School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),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":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),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":["Informazione e Bioingegneria, Politecnico di Milano,Dipartimento di Elettronica,Milano,Italy","Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informazione e Bioingegneria, Politecnico di Milano,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":["School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),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":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab (VIPER),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":0.8712,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7741832,"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":"1135","last_page":"1140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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":0.9980999827384949,"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/T10860","display_name":"Speech and Audio Processing","score":0.9943000078201294,"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/T11309","display_name":"Music and Audio Processing","score":0.967199981212616,"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/transformer","display_name":"Transformer","score":0.6180120706558228},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5904061198234558},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5426822304725647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35300400853157043},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1623740792274475},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1292172074317932},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10754743218421936}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6180120706558228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5904061198234558},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5426822304725647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35300400853157043},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1623740792274475},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1292172074317932},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10754743218421936}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ieeeconf59524.2023.10476982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10476982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1265885","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1265885","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":null,"sustainable_development_goals":[],"awards":[{"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/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W1489991816","https://openalex.org/W1604034532","https://openalex.org/W1987971958","https://openalex.org/W2051224630","https://openalex.org/W2071128523","https://openalex.org/W2085487226","https://openalex.org/W2103869314","https://openalex.org/W2294798173","https://openalex.org/W2519091744","https://openalex.org/W2590129515","https://openalex.org/W2593116425","https://openalex.org/W2955054437","https://openalex.org/W2964243274","https://openalex.org/W3094502228","https://openalex.org/W3157576687","https://openalex.org/W3161011913","https://openalex.org/W3170179936","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W4206095984","https://openalex.org/W4207005592","https://openalex.org/W4214896311","https://openalex.org/W4226080084","https://openalex.org/W4294975742","https://openalex.org/W4360764515","https://openalex.org/W4362684594","https://openalex.org/W4372269174","https://openalex.org/W4381187661","https://openalex.org/W4392942164"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Synthetic":[0,107],"speech":[1,19,35,46,50,68,134,142,161],"generators":[2],"can":[3,9,65],"produce":[4],"high":[5],"quality":[6],"speech.":[7,23],"It":[8],"be":[10],"difficult":[11],"for":[12,28,88,122],"humans":[13],"to":[14,51,97],"perceptually":[15],"distinguish":[16],"between":[17],"synthesized":[18],"and":[20,115,120,135,138,143,158],"authentic":[21],"human":[22],"Identifying":[24],"the":[25,60,127],"synthesizer":[26,76],"used":[27],"generating":[29],"synthetic":[30,34,45],"speech,":[31],"known":[32,67,104,153],"as":[33,105],"attribution,":[36],"is":[37,48,103,113,170],"an":[38,74,171],"important":[39],"problem.":[40],"An":[41],"open":[42],"problem":[43],"in":[44,59],"attribution":[47,89],"attributing":[49],"new,":[52],"unknown":[53,75,79,91,99,149,164],"synthesizers,":[54,145],"which":[55,146,169],"are":[56],"not":[57],"present":[58],"training":[61],"set.":[62],"Existing":[63],"methods":[64],"identify":[66],"synthesizers":[69,92,137,154,165],"but":[70],"they":[71],"cannot":[72],"differentiate":[73],"from":[77,163],"another":[78],"synthesizer.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84],"describe":[85],"a":[86],"system":[87,102],"of":[90],"i.e.,":[93],"assigning":[94],"different":[95,98],"labels":[96],"synthesizers.":[100,150],"Our":[101,124],"Fine-Grain":[106],"Speech":[108],"Attribution":[109],"Transformer":[110],"(FGSSAT).":[111],"FGSSAT":[112,151],"unsupervised":[114],"uses":[116],"transformer,":[117],"dimensionality":[118],"reduction":[119],"clustering":[121],"attribution.":[123],"experiments":[125],"use":[126],"ASVspoof2019":[128],"dataset.":[129],"We":[130],"train":[131],"on":[132,140,173],"real":[133,141],"6":[136],"evaluate":[139],"17":[144],"include":[147],"11":[148],"identifies":[152],"with":[155,166],"99.6%":[156],"accuracy":[157],"classifies":[159],"all":[160],"generated":[162],"76.5%":[167],"accuracy,":[168],"improvement":[172],"existing":[174],"work.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}