{"id":"https://openalex.org/W4214896311","doi":"https://doi.org/10.1109/ieeeconf53345.2021.9723142","title":"Synthesized Speech Detection Using Convolutional Transformer-Based Spectrogram Analysis","display_name":"Synthesized Speech Detection Using Convolutional Transformer-Based Spectrogram Analysis","publication_year":2021,"publication_date":"2021-10-31","ids":{"openalex":"https://openalex.org/W4214896311","doi":"https://doi.org/10.1109/ieeeconf53345.2021.9723142"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf53345.2021.9723142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf53345.2021.9723142","pdf_url":null,"source":{"id":"https://openalex.org/S4363607877","display_name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","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":"2021 55th Asilomar Conference on Signals, Systems, and Computers","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/2205.01800","any_repository_has_fulltext":true},"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":["Purdue University,Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering,West Lafayette,IN,USA","Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering,West Lafayette,IN,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, IN, USA","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":["Purdue University,Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering,West Lafayette,IN,USA","Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Video and Image Processing Lab (VIPER) School of Electrical and Computer Engineering,West Lafayette,IN,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, IN, USA","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":2.0514,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89805214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1426","last_page":"1430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9966999888420105,"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":0.9966999888420105,"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":0.993399977684021,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9848999977111816,"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/spectrogram","display_name":"Spectrogram","score":0.9385969042778015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773451566696167},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.752399206161499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6845435500144958},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.658186674118042},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4978952407836914},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47944870591163635},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4593970477581024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3002338111400604},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08774477243423462},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.05856969952583313}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9385969042778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773451566696167},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.752399206161499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6845435500144958},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.658186674118042},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4978952407836914},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47944870591163635},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4593970477581024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3002338111400604},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08774477243423462},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.05856969952583313},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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:10.1109/ieeeconf53345.2021.9723142","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf53345.2021.9723142","pdf_url":null,"source":{"id":"https://openalex.org/S4363607877","display_name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","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":"2021 55th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.01800","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.01800","pdf_url":"https://arxiv.org/pdf/2205.01800","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.01800","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.01800","pdf_url":"https://arxiv.org/pdf/2205.01800","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":[],"awards":[],"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":42,"referenced_works":["https://openalex.org/W1536990986","https://openalex.org/W1923358586","https://openalex.org/W1976526581","https://openalex.org/W2062826588","https://openalex.org/W2064675550","https://openalex.org/W2090431713","https://openalex.org/W2103869314","https://openalex.org/W2122111042","https://openalex.org/W2184242386","https://openalex.org/W2314633289","https://openalex.org/W2747872086","https://openalex.org/W2783089003","https://openalex.org/W2801171099","https://openalex.org/W2888728157","https://openalex.org/W2896457183","https://openalex.org/W2911424785","https://openalex.org/W2914424550","https://openalex.org/W2940618856","https://openalex.org/W2950098109","https://openalex.org/W2955054437","https://openalex.org/W2982058372","https://openalex.org/W3019584399","https://openalex.org/W3033711348","https://openalex.org/W3036576316","https://openalex.org/W3094502228","https://openalex.org/W3157506437","https://openalex.org/W3159778524","https://openalex.org/W3180160903","https://openalex.org/W3198123200","https://openalex.org/W3199074910","https://openalex.org/W4232336823","https://openalex.org/W4239510810","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6765397690","https://openalex.org/W6776384377","https://openalex.org/W6784333009","https://openalex.org/W6795062860","https://openalex.org/W6795140394","https://openalex.org/W6834694846"],"related_works":["https://openalex.org/W4214896311","https://openalex.org/W1840351222","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"Synthesized":[0,24],"speech":[1,18,25,37,60,69,84,157],"is":[2,62],"common":[3],"today":[4],"due":[5],"to":[6,42,56,106,122],"the":[7,48,51,72],"prevalence":[8],"of":[9,50,74,128],"virtual":[10],"assistants,":[11],"easy-to-use":[12],"tools":[13],"for":[14,30,82,114],"generating":[15],"and":[16,20,39,96,140,155],"modifying":[17],"signals,":[19,144],"remote":[21],"work":[22],"practices.":[23],"can":[26],"also":[27],"be":[28],"used":[29,113],"nefarious":[31],"purposes,":[32],"including":[33],"creating":[34],"a":[35,59,77,89,100,103,129],"purported":[36],"signal":[38,61,130],"attributing":[40],"it":[41],"someone":[43],"who":[44],"did":[45],"not":[46],"speak":[47],"content":[49],"signal.":[52],"We":[53],"need":[54],"methods":[55],"detect":[57],"if":[58],"synthesized.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,145],"analyze":[68],"signals":[70,139],"in":[71],"form":[73],"spectrograms":[75],"with":[76,109],"Compact":[78],"Convolutional":[79],"Transformer":[80],"(CCT)":[81],"synthesized":[83,141,156],"detection.":[85],"A":[86],"CCT":[87,117,149],"utilizes":[88],"convolutional":[90],"layer":[91],"that":[92,147],"introduces":[93],"inductive":[94],"biases":[95],"shared":[97],"weights":[98],"into":[99],"network,":[101],"allowing":[102],"transformer":[104],"architecture":[105],"perform":[107],"well":[108],"fewer":[110],"data":[111],"samples":[112],"training.":[115],"The":[116],"uses":[118],"an":[119],"attention":[120],"mechanism":[121],"incorporate":[123],"information":[124],"from":[125],"all":[126],"parts":[127],"under":[131],"analysis.":[132],"Trained":[133],"on":[134],"both":[135],"genuine":[136,154],"human":[137,142],"voice":[138,143],"demonstrate":[146],"our":[148],"approach":[150],"successfully":[151],"differentiates":[152],"between":[153],"signals.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}