{"id":"https://openalex.org/W4393372892","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10477041","title":"Transformer Ensemble for Synthesized Speech Detection","display_name":"Transformer Ensemble for Synthesized Speech Detection","publication_year":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4393372892","doi":"https://doi.org/10.1109/ieeeconf59524.2023.10477041"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf59524.2023.10477041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10477041","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/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":["School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab,West Lafayette,IN","Video and Image Processing Lab, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab,West Lafayette,IN","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Video and Image Processing Lab, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","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,West Lafayette,IN","Video and Image Processing Lab, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab,West Lafayette,IN","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Video and Image Processing Lab, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN","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,West Lafayette,IN","Video and Image Processing Lab, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab,West Lafayette,IN","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Video and Image Processing Lab, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"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,West Lafayette,IN","Video and Image Processing Lab, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University,Video and Image Processing Lab,West Lafayette,IN","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Video and Image Processing Lab, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":1.45,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86469072,"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":"1100","last_page":"1105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9839000105857849,"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":0.9839000105857849,"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":0.9639999866485596,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6986806988716125},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5888482332229614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.56800377368927},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41438359022140503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37254446744918823},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.321992963552475},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3203028440475464},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1626690924167633},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11430051922798157},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09351229667663574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6986806988716125},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5888482332229614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.56800377368927},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41438359022140503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37254446744918823},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.321992963552475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3203028440475464},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1626690924167633},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11430051922798157},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09351229667663574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf59524.2023.10477041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59524.2023.10477041","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"}],"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/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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1976526581","https://openalex.org/W2026988473","https://openalex.org/W2064675550","https://openalex.org/W2068149370","https://openalex.org/W2103869314","https://openalex.org/W2593116425","https://openalex.org/W2747872086","https://openalex.org/W2801171099","https://openalex.org/W2888728157","https://openalex.org/W2914393402","https://openalex.org/W2955054437","https://openalex.org/W2982058372","https://openalex.org/W3033711348","https://openalex.org/W3045635324","https://openalex.org/W3093231216","https://openalex.org/W3159778524","https://openalex.org/W3160614129","https://openalex.org/W3163573274","https://openalex.org/W3170179936","https://openalex.org/W3180160903","https://openalex.org/W3188310116","https://openalex.org/W3196974791","https://openalex.org/W3199074910","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W4210366369","https://openalex.org/W4214896311","https://openalex.org/W4224986264","https://openalex.org/W4225288420","https://openalex.org/W4294975742","https://openalex.org/W4360764515","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6757817989","https://openalex.org/W6765397690","https://openalex.org/W6776384377","https://openalex.org/W6795062860","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6810556107","https://openalex.org/W6945259040"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2166690696","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"As":[0],"voice":[1],"synthesis":[2],"systems":[3],"and":[4,57],"deep":[5],"learning":[6],"tools":[7],"continue":[8],"to":[9,44],"improve,":[10],"so":[11],"does":[12],"the":[13,104],"possibility":[14],"that":[15,25,65,80,109],"synthesized":[16,31,46,70,99,114],"speech":[17,34,71,100,115],"can":[18,81],"be":[19],"used":[20],"for":[21,97],"nefarious":[22],"purposes.":[23],"Methods":[24],"determine":[26],"if":[27],"audio":[28,93,120],"signals":[29],"contain":[30],"or":[32],"authentic":[33],"are":[35],"needed.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40,74,87,107],"investigate":[41],"three":[42],"transformers":[43,79],"detect":[45],"speech:":[47],"Compact":[48],"Convolutional":[49],"Transformer":[50,55,61],"(CCT),":[51],"Patchout":[52],"faSt":[53],"Spectrogram":[54,60],"(PaSST),":[56],"Self-Supervised":[58],"Audio":[59],"(SSAST).":[62],"We":[63],"show":[64],"each":[66],"transformer":[67,111],"independently":[68],"detects":[69,113],"well.":[72],"Then,":[73],"propose":[75],"an":[76,92],"ensemble":[77,112],"of":[78,91,119],"provide":[82],"even":[83,122],"better":[84],"performance.":[85],"Finally,":[86],"explore":[88],"how":[89],"much":[90],"signal":[94],"is":[95],"needed":[96],"high":[98],"detection.":[101],"Evaluated":[102],"on":[103,123],"ASVspoof2019":[105],"dataset,":[106],"demonstrate":[108],"our":[110],"from":[116],"shorter":[117],"segments":[118],"signals,":[121],"a":[124],"highly":[125],"imbalanced":[126],"dataset.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}