{"id":"https://openalex.org/W4406461839","doi":"https://doi.org/10.1109/slt61566.2024.10832284","title":"SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challenge","display_name":"SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challenge","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461839","doi":"https://doi.org/10.1109/slt61566.2024.10832284"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","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/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":true,"raw_author_name":"You Zhang","raw_affiliation_strings":["University of Rochester,Rochester,NY,USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","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,Rochester,NY,USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100556054","display_name":"Ryuichi Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichi Yamamoto","raw_affiliation_strings":["Nagoya University,Nagoya,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Nagoya,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Nagoya,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Nagoya,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"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,Rochester,NY,USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100384568"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":3.9641,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94771898,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"782","last_page":"787"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7705423831939697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6042041778564453},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5516331791877747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3327835202217102},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17062592506408691}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7705423831939697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6042041778564453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5516331791877747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3327835202217102},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17062592506408691},{"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/slt61566.2024.10832284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W3041870963","https://openalex.org/W3128666957","https://openalex.org/W3131786367","https://openalex.org/W3158762648","https://openalex.org/W3159302906","https://openalex.org/W3198020407","https://openalex.org/W3201773091","https://openalex.org/W3213029956","https://openalex.org/W3217401639","https://openalex.org/W4210870666","https://openalex.org/W4280572880","https://openalex.org/W4285345683","https://openalex.org/W4295682935","https://openalex.org/W4296068763","https://openalex.org/W4372260026","https://openalex.org/W4391021548","https://openalex.org/W4392120916","https://openalex.org/W4392908976","https://openalex.org/W4392909814","https://openalex.org/W4396814510","https://openalex.org/W4396817233","https://openalex.org/W4402111788","https://openalex.org/W4402112070","https://openalex.org/W4402112388","https://openalex.org/W4402112543","https://openalex.org/W4403791925","https://openalex.org/W4406461891","https://openalex.org/W6639480849","https://openalex.org/W6772925044","https://openalex.org/W6779090866","https://openalex.org/W6783867762","https://openalex.org/W6811340444","https://openalex.org/W6842173990","https://openalex.org/W6848578254","https://openalex.org/W6861998530","https://openalex.org/W6866083838","https://openalex.org/W6866747874"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","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"],"abstract_inverted_index":{"With":[0],"the":[1,8,17,74,79,93,108,118,123],"advancements":[2],"in":[3,29],"singing":[4,32,59,67],"voice":[5,68],"generation":[6],"and":[7,47,70,107,133],"growing":[9],"presence":[10],"of":[11],"AI":[12],"singers":[13],"on":[14],"media":[15],"platforms,":[16],"inaugural":[18],"Singing":[19],"Voice":[20],"Deepfake":[21],"Detection":[22],"(SVDD)":[23],"Challenge":[24],"aims":[25],"to":[26,62],"advance":[27],"research":[28],"identifying":[30],"AI-generated":[31],"voices":[33],"from":[34,87,99],"authentic":[35],"singers.":[36],"This":[37,125],"challenge":[38],"features":[39],"two":[40],"tracks:":[41],"a":[42,112],"controlled":[43],"setting":[44],"track":[45,51,55,76],"(CtrSVDD)":[46],"an":[48],"in-the-wild":[49],"scenario":[50],"(WildSVDD).":[52],"The":[53],"CtrSVDD":[54,94],"utilizes":[56],"publicly":[57],"available":[58],"vocal":[60],"data":[61,85],"generate":[63],"deepfakes":[64],"using":[65],"state-of-the-art":[66],"synthesis":[69],"conversion":[71],"systems.":[72],"Meanwhile,":[73],"WildSVDD":[75,119],"expands":[77],"upon":[78],"existing":[80],"SingFake":[81],"dataset,":[82],"which":[83],"includes":[84],"sourced":[86],"popular":[88],"user-generated":[89],"content":[90],"websites.":[91],"For":[92,117],"track,":[95,120],"we":[96,121],"received":[97],"submissions":[98],"47":[100],"teams,":[101],"with":[102],"37":[103],"surpassing":[104],"our":[105],"baselines":[106],"top":[109],"team":[110],"achieving":[111],"1.65%":[113],"equal":[114],"error":[115],"rate.":[116],"benchmarked":[122],"baselines.":[124],"paper":[126],"reviews":[127],"these":[128],"results,":[129],"discusses":[130],"key":[131],"findings,":[132],"outlines":[134],"future":[135],"directions":[136],"for":[137],"SVDD":[138],"research.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}