{"id":"https://openalex.org/W4392908976","doi":"https://doi.org/10.1109/icassp48485.2024.10448184","title":"SingFake: Singing Voice Deepfake Detection","display_name":"SingFake: Singing Voice Deepfake Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908976","doi":"https://doi.org/10.1109/icassp48485.2024.10448184"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5104268516","display_name":"Yongyi Zang","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongyi Zang","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384568","display_name":"You Zhang","orcid":"https://orcid.org/0000-0002-4649-278X"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Zhang","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004301078","display_name":"Mojtaba Heydari","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mojtaba Heydari","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":19.2935,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.99672802,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"12156","last_page":"12160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.989300012588501,"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/T11309","display_name":"Music and Audio Processing","score":0.989300012588501,"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/T10860","display_name":"Speech and Audio Processing","score":0.972599983215332,"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":0.9588000178337097,"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/singing","display_name":"Singing","score":0.7887529134750366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7294480800628662},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5482178926467896},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20534008741378784}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7887529134750366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7294480800628662},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5482178926467896},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20534008741378784},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G4392250869","display_name":"Collaborative Research: FW-HTF-R: Toward an Ecosystem of Artificial Intelligence-Powered Music Production (TEAMuP)","funder_award_id":"2222129","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4863407681","display_name":"NRT-HDR: Interdisciplinary Graduate Training in the Science, Technology, and Applications of Augmented and Virtual Reality","funder_award_id":"1922591","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337430","display_name":"National Institute of Justice","ror":"https://ror.org/00v8p7w89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W3026777299","https://openalex.org/W3127781933","https://openalex.org/W3157070662","https://openalex.org/W3158663310","https://openalex.org/W3158762648","https://openalex.org/W3198482860","https://openalex.org/W3198837656","https://openalex.org/W3199957557","https://openalex.org/W3201773091","https://openalex.org/W3207340675","https://openalex.org/W4225527248","https://openalex.org/W4297841787","https://openalex.org/W4298310324","https://openalex.org/W4372184039","https://openalex.org/W4372260250","https://openalex.org/W4372347465","https://openalex.org/W4381198892","https://openalex.org/W4392909814","https://openalex.org/W6766320909","https://openalex.org/W6780218876","https://openalex.org/W6842368590"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683"],"abstract_inverted_index":{"The":[0,189],"rise":[1],"of":[2,89,92,97],"singing":[3,22,39,54,74,185],"voice":[4,16,55,75,186],"synthesis":[5,36],"presents":[6],"critical":[7],"challenges":[8,169],"to":[9,123],"artists":[10],"and":[11,44,94,177,192],"industry":[12],"stakeholders":[13],"over":[14],"unauthorized":[15],"usage.":[17],"Unlike":[18],"synthesized":[19,21],"speech,":[20],"voices":[23,40],"are":[24,195],"typically":[25],"released":[26],"in":[27,101],"songs":[28],"containing":[29],"strong":[30],"background":[31],"music":[32],"that":[33],"may":[34],"hide":[35],"artifacts.":[37],"Additionally,":[38],"present":[41,81],"different":[42,62],"acoustic":[43],"linguistic":[45],"characteristics":[46],"from":[47,64,104],"speech":[48,66,127,132,144],"utterances.":[49,133],"These":[50],"unique":[51],"properties":[52],"make":[53],"deepfake":[56,76,98,187],"detection":[57,77],"a":[58,109],"relevant":[59],"but":[60],"significantly":[61,139],"problem":[63],"synthetic":[65],"detection.":[67,188],"In":[68],"this":[69],"work,":[70],"we":[71],"propose":[72],"the":[73,83,113],"task.":[78],"We":[79,107,119,134],"first":[80,84],"SingFake,":[82,150],"curated":[85],"in-the-wild":[86],"dataset":[87,191],"consisting":[88],"28.93":[90],"hours":[91,96],"bonafide":[93],"29.40":[95],"song":[99,157],"clips":[100],"five":[102],"languages":[103],"40":[105],"singers.":[106],"provide":[108],"train/validation/test":[110],"split":[111],"where":[112],"test":[114,145],"sets":[115],"include":[116],"various":[117],"scenarios.":[118],"then":[120],"use":[121],"SingFake":[122,190],"evaluate":[124],"four":[125],"state-of-the-art":[126],"countermeasure":[128],"systems":[129,137,160],"trained":[130,148],"on":[131,143,149],"find":[135],"these":[136,159],"lag":[138],"behind":[140],"their":[141],"performance":[142],"data.":[146],"When":[147],"either":[151],"using":[152],"separated":[153],"vocal":[154],"tracks":[155],"or":[156],"mixtures,":[158],"show":[161],"substantial":[162],"improvement.":[163],"However,":[164],"our":[165],"evaluations":[166],"also":[167],"identify":[168],"associated":[170],"with":[171],"unseen":[172],"singers,":[173],"communication":[174],"codecs,":[175],"languages,":[176],"musical":[178],"contexts,":[179],"calling":[180],"for":[181],"dedicated":[182],"research":[183],"into":[184],"related":[193],"resources":[194],"available1.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":13}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}