{"id":"https://openalex.org/W4410536451","doi":"https://doi.org/10.1109/access.2025.3571728","title":"A Comparative Study of Deep Audio Models for Spectrogram- and Waveform-Based SingFake Detection","display_name":"A Comparative Study of Deep Audio Models for Spectrogram- and Waveform-Based SingFake Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4410536451","doi":"https://doi.org/10.1109/access.2025.3571728"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3571728","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3571728","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3571728","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Minh Nguyen-Duc","orcid":"https://orcid.org/0009-0003-1091-0809"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh Nguyen-Duc","raw_affiliation_strings":["Department of Artificial Intelligence, FPT University, Da Nang, Vietnam","Department of Artificial Intelligence, FPT University, Danang, Vietnam"],"raw_orcid":"https://orcid.org/0009-0003-1091-0809","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, FPT University, Da Nang, Vietnam","institution_ids":["https://openalex.org/I109689652"]},{"raw_affiliation_string":"Department of Artificial Intelligence, FPT University, Danang, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016461160","display_name":"Luong Vuong Nguyen","orcid":"https://orcid.org/0000-0002-4680-1984"},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Luong Vuong Nguyen","raw_affiliation_strings":["Department of Artificial Intelligence, FPT University, Da Nang, Vietnam","Department of Artificial Intelligence, FPT University, Danang, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-4680-1984","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, FPT University, Da Nang, Vietnam","institution_ids":["https://openalex.org/I109689652"]},{"raw_affiliation_string":"Department of Artificial Intelligence, FPT University, Danang, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117613150","display_name":"Huy Nguyen-Ho-Nhat","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huy Nguyen-Ho-Nhat","raw_affiliation_strings":["Department of Artificial Intelligence, FPT University, Da Nang, Vietnam","Department of Artificial Intelligence, FPT University, Danang, Vietnam"],"raw_orcid":"https://orcid.org/0009-0009-9263-1574","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, FPT University, Da Nang, Vietnam","institution_ids":["https://openalex.org/I109689652"]},{"raw_affiliation_string":"Department of Artificial Intelligence, FPT University, Danang, Vietnam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004618448","display_name":"Tri\u2010Hai Nguyen","orcid":"https://orcid.org/0000-0002-2132-2290"},"institutions":[{"id":"https://openalex.org/I4210123993","display_name":"Van Lang University","ror":"https://ror.org/02ryrf141","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210123993"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tri-Hai Nguyen","raw_affiliation_strings":["Faculty of Information Technology, School of Technology, Van Lang University, Ho Chi Minh City, Vietnam","School of Technology, Faculty of Information Technology, Van Lang University, Ho Chi Minh City, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-2132-2290","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, School of Technology, Van Lang University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I4210123993"]},{"raw_affiliation_string":"School of Technology, Faculty of Information Technology, Van Lang University, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I4210123993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069645890","display_name":"O\u2010Joun Lee","orcid":"https://orcid.org/0000-0001-8921-5443"},"institutions":[{"id":"https://openalex.org/I87111246","display_name":"Catholic University of Korea","ror":"https://ror.org/01fpnj063","country_code":"KR","type":"education","lineage":["https://openalex.org/I87111246"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"O-Joun Lee","raw_affiliation_strings":["Department of Artificial Intelligence, The Catholic University of Korea, Bucheon, Republic of Korea","Department of Artificial Intelligence, The Catholic University of Korea, Bucheon, Rep. of Korea"],"raw_orcid":"https://orcid.org/0000-0001-8921-5443","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, The Catholic University of Korea, Bucheon, Republic of Korea","institution_ids":["https://openalex.org/I87111246"]},{"raw_affiliation_string":"Department of Artificial Intelligence, The Catholic University of Korea, Bucheon, Rep. of Korea","institution_ids":["https://openalex.org/I87111246"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":4.2561,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94144394,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"95739","last_page":"95752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9872999787330627,"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":0.9872999787330627,"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":0.98089998960495,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9710999727249146,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9492359757423401},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.696295976638794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6835674047470093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6346510052680969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44461116194725037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3636709451675415},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14321693778038025},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.054321348667144775}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9492359757423401},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.696295976638794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6835674047470093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6346510052680969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44461116194725037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3636709451675415},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14321693778038025},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.054321348667144775}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3571728","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3571728","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b332e5dcd312403a9d701cbbaa1fc501","is_oa":true,"landing_page_url":"https://doaj.org/article/b332e5dcd312403a9d701cbbaa1fc501","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 95739-95752 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3571728","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3571728","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1810503114","display_name":null,"funder_award_id":"2022R1F1A1065516","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6823960655","display_name":null,"funder_award_id":"M-2024-B0002-00046","funder_id":"https://openalex.org/F4320321379","funder_display_name":"Catholic University of Korea"},{"id":"https://openalex.org/G7345021322","display_name":null,"funder_award_id":"M-2025-B0002-00053","funder_id":"https://openalex.org/F4320321379","funder_display_name":"Catholic University of Korea"}],"funders":[{"id":"https://openalex.org/F4320321379","display_name":"Catholic University of Korea","ror":"https://ror.org/01fpnj063"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W94094186","https://openalex.org/W172260869","https://openalex.org/W1183662111","https://openalex.org/W1494198834","https://openalex.org/W2165084404","https://openalex.org/W2176804518","https://openalex.org/W2593116425","https://openalex.org/W2970737019","https://openalex.org/W2972717745","https://openalex.org/W2989571531","https://openalex.org/W3024657687","https://openalex.org/W3153983935","https://openalex.org/W3170179936","https://openalex.org/W3196974791","https://openalex.org/W3197358873","https://openalex.org/W3204116061","https://openalex.org/W3209059054","https://openalex.org/W3213726885","https://openalex.org/W4205523283","https://openalex.org/W4213449918","https://openalex.org/W4225092315","https://openalex.org/W4225420087","https://openalex.org/W4297841787","https://openalex.org/W4309327109","https://openalex.org/W4312743281","https://openalex.org/W4380987202","https://openalex.org/W4385483249","https://openalex.org/W4385822660","https://openalex.org/W4385823015","https://openalex.org/W4385823150","https://openalex.org/W4386914595","https://openalex.org/W4391892641","https://openalex.org/W4400610317","https://openalex.org/W4402112070","https://openalex.org/W4402112543","https://openalex.org/W4406461839","https://openalex.org/W4406461891","https://openalex.org/W4406803348","https://openalex.org/W4407388754","https://openalex.org/W4408144899","https://openalex.org/W4408352236","https://openalex.org/W4408354362","https://openalex.org/W4408355777","https://openalex.org/W4409487087","https://openalex.org/W6730279316","https://openalex.org/W6752254909","https://openalex.org/W6770434673","https://openalex.org/W6772449258","https://openalex.org/W6777843394","https://openalex.org/W6803394801","https://openalex.org/W6838929754","https://openalex.org/W6847363464","https://openalex.org/W6855841490","https://openalex.org/W6866083838","https://openalex.org/W6870788587","https://openalex.org/W6873568832","https://openalex.org/W6874294372","https://openalex.org/W6880941374","https://openalex.org/W6882330110"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W2942893872","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,21],"singing":[3,13,159],"voice":[4],"synthesis":[5],"have":[6],"significantly":[7],"improved":[8],"the":[9,37,92,138,144],"quality":[10],"of":[11,40,57,148],"artificial":[12],"voices,":[14],"raising":[15],"concerns":[16],"about":[17],"their":[18],"potential":[19],"misuse":[20],"generating":[22],"deepfake":[23,158],"singing,":[24,41],"or":[25],"\"singfake\"":[26],"voices.":[27],"Detecting":[28],"these":[29,96],"synthetic":[30],"voices":[31],"presents":[32],"unique":[33],"challenges":[34],"due":[35],"to":[36,154],"complex":[38],"nature":[39],"which":[42],"involves":[43],"pitch,":[44],"timbre,":[45],"and":[46,75,77,87,104,135,146,168],"accompaniment":[47],"variations.":[48],"In":[49],"this":[50],"study,":[51],"we":[52],"conduct":[53],"a":[54],"comparative":[55],"analysis":[56],"two":[58,99],"model":[59],"types":[60],"for":[61,164],"singfake":[62],"detection:":[63],"(1)":[64],"models":[65,79,97,116],"utilizing":[66],"Log-Mel":[67],"spectrograms,":[68],"such":[69,126],"as":[70,127],"Audio":[71],"Spectrogram":[72],"Transformer":[73],"(AST)":[74],"Whisper,":[76],"(2)":[78],"that":[80,114],"process":[81],"raw":[82],"waveform":[83],"inputs,":[84],"including":[85],"UniSpeech-SAT":[86],"HuBERT.":[88],"Our":[89,151],"experiments":[90],"on":[91,122],"SingFake":[93],"dataset":[94],"evaluate":[95],"under":[98],"input":[100],"conditions\u2014separated":[101],"vocal":[102],"tracks":[103],"full":[105],"song":[106],"mixtures\u2014across":[107],"different":[108],"test":[109],"subsets.":[110],"The":[111],"results":[112],"indicate":[113],"spectrogram-based":[115],"generally":[117],"outperform":[118],"waveform-based":[119],"models,":[120],"notably":[121],"unseen":[123],"singers.":[124],"Metrics":[125],"Precision,":[128],"Recall,":[129],"F1-score,":[130],"Equal":[131],"Error":[132],"Rate":[133],"(EER),":[134],"Area":[136],"Under":[137],"Curve":[139],"(AUC)":[140],"provide":[141],"insights":[142],"into":[143],"strengths":[145],"weaknesses":[147],"each":[149],"approach.":[150],"findings":[152],"contribute":[153],"developing":[155],"more":[156],"effective":[157],"detection":[160],"methods,":[161],"with":[162],"implications":[163],"security,":[165],"media":[166],"authentication,":[167],"digital":[169],"content":[170],"protection.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}