{"id":"https://openalex.org/W3180160903","doi":"https://doi.org/10.2352/issn.2470-1173.2021.4.mwsf-273","title":"Frequency Domain-Based Detection of Generated Audio","display_name":"Frequency Domain-Based Detection of Generated Audio","publication_year":2021,"publication_date":"2021-01-18","ids":{"openalex":"https://openalex.org/W3180160903","doi":"https://doi.org/10.2352/issn.2470-1173.2021.4.mwsf-273","mag":"3180160903"},"language":"en","primary_location":{"id":"doi:10.2352/issn.2470-1173.2021.4.mwsf-273","is_oa":true,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2021.4.mwsf-273","pdf_url":"https://library.imaging.org/admin/apis/public/api/sandbox/website/downloadArticle/ei/33/4/art00004","source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://library.imaging.org/admin/apis/public/api/sandbox/website/downloadArticle/ei/33/4/art00004","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emily R. Bartusiak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089688702","display_name":"Edward J. Delp","orcid":"https://orcid.org/0000-0002-2909-7323"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward J. Delp","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3191,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.82606386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"4","first_page":"273","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9419999718666077,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9161999821662903,"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":0.9297232627868652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7346052527427673},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6289750933647156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6108074188232422},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5407045483589172},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5368398427963257},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48044702410697937},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.468313068151474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44807034730911255},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44787484407424927},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4299180507659912},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.41900312900543213},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4172575771808624},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.21220475435256958},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15200448036193848},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12727949023246765},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1212630569934845},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07663634419441223}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9297232627868652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346052527427673},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6289750933647156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6108074188232422},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5407045483589172},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5368398427963257},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48044702410697937},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.468313068151474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44807034730911255},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44787484407424927},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4299180507659912},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.41900312900543213},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4172575771808624},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.21220475435256958},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15200448036193848},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12727949023246765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1212630569934845},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07663634419441223},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2352/issn.2470-1173.2021.4.mwsf-273","is_oa":true,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2021.4.mwsf-273","pdf_url":"https://library.imaging.org/admin/apis/public/api/sandbox/website/downloadArticle/ei/33/4/art00004","source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.2352/issn.2470-1173.2021.4.mwsf-273","is_oa":true,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2021.4.mwsf-273","pdf_url":"https://library.imaging.org/admin/apis/public/api/sandbox/website/downloadArticle/ei/33/4/art00004","source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2064323827","https://openalex.org/W4214896311","https://openalex.org/W4360764600","https://openalex.org/W2289868279","https://openalex.org/W2793814466","https://openalex.org/W4315836293","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4243888788"],"abstract_inverted_index":{"Attackers":[0],"may":[1],"manipulate":[2],"audio":[3,53,80,88],"with":[4,102],"the":[5,43,79,83,87],"intent":[6],"of":[7,14,25,39,45,77],"presenting":[8],"falsified":[9],"reports,":[10],"changing":[11],"an":[12],"opinion":[13],"a":[15,37,49,103],"public":[16],"figure,":[17],"and":[18,21,73,96,99,115],"winning":[19],"influence":[20],"power.":[22],"The":[23],"prevalence":[24],"inauthentic":[26],"multimedia":[27],"continues":[28],"to":[29,35,55],"rise,":[30],"so":[31],"it":[32],"is":[33],"imperative":[34],"develop":[36],"set":[38],"tools":[40],"that":[41,51],"determines":[42],"legitimacy":[44],"media.":[46],"We":[47],"present":[48],"method":[50],"analyzes":[52],"signals":[54,81,89,114],"determine":[56],"whether":[57],"they":[58],"contain":[59],"real":[60],"human":[61,65,112],"voices":[62,66,68],"or":[63],"fake":[64],"(i.e.,":[67],"generated":[69],"by":[70],"neural":[71],"acoustic":[72],"waveform":[74],"models).":[75],"Instead":[76],"analyzing":[78],"directly,":[82],"proposed":[84],"approach":[85,122],"converts":[86],"into":[90],"spectrogram":[91],"images":[92],"displaying":[93],"frequency,":[94],"intensity,":[95],"temporal":[97],"content":[98],"evaluates":[100],"them":[101],"Convolutional":[104],"Neural":[105],"Network":[106],"(CNN).":[107],"Trained":[108],"on":[109,126],"both":[110],"genuine":[111],"voice":[113,117],"synthesized":[116],"signals,":[118],"we":[119],"show":[120],"our":[121],"achieves":[123],"high":[124],"accuracy":[125],"this":[127],"classification":[128],"task.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-24T06:17:17.354583","created_date":"2025-10-10T00:00:00"}