{"id":"https://openalex.org/W7077894856","doi":"https://doi.org/10.5281/zenodo.16955639","title":"HuBERT Ensemble Models for Singing Voice Deepfake Detection","display_name":"HuBERT Ensemble Models for Singing Voice Deepfake Detection","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W7077894856","doi":"https://doi.org/10.5281/zenodo.16955639"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.16955639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16955639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.16955639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Levine, Gabriel","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Levine, Gabriel","raw_affiliation_strings":["City University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thurlow, Drew","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096066","display_name":"Open Knowledge (United Kingdom)","ror":"https://ror.org/00thqng93","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210096066"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thurlow, Drew","raw_affiliation_strings":["Opening Ceremony Media"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Opening Ceremony Media","institution_ids":["https://openalex.org/I4210096066"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Levitan, Sarah Ita","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Levitan, Sarah Ita","raw_affiliation_strings":["City University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"last","author":{"id":null,"display_name":"Arfa, Jon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arfa, Jon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4185079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6686000227928162,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6686000227928162,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.029500000178813934,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.01940000057220459,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7591000199317932},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6717000007629395},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4749999940395355},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42160001397132874},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.41040000319480896},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4081000089645386},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.32409998774528503}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7591000199317932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465999722480774},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6717000007629395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6134999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4772999882698059},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3077000081539154},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C2780336059","wikidata":"https://www.wikidata.org/wiki/Q215558","display_name":"Vocal folds","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C553614217","wikidata":"https://www.wikidata.org/wiki/Q685884","display_name":"Vocal music","level":4,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.16955639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16955639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.16955639","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16955639","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"score":0.4059443473815918,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tools":[0],"for":[1,36,51],"singing":[2,60],"voice":[3],"synthesis":[4],"and":[5,17,43,55,84,137],"vocal":[6,56],"conversion":[7],"focused":[8],"on":[9],"music":[10,26,80],"have":[11],"greatly":[12],"improved":[13],"in":[14],"both":[15],"quality":[16],"ease":[18],"of":[19,25,66,78],"use,":[20],"leading":[21],"to":[22,38,126,141],"an":[23,128],"explosion":[24],"with":[27,113],"synthetic":[28,44,53,59,85,90],"vocals.":[29,45,86],"This":[30],"proliferation":[31],"has":[32],"made":[33],"it":[34],"difficult":[35],"listeners":[37],"discern":[39],"human":[40,83],"from":[41,110],"deepfake":[42],"While":[46],"there":[47],"are":[48],"robust":[49],"approaches":[50],"detecting":[52],"speech":[54,91,108],"spoofing,":[57],"identifying":[58],"voices":[61],"presents":[62],"a":[63,73,101,114],"unique":[64],"set":[65],"challenges.":[67],"In":[68],"this":[69,95,125],"paper,":[70],"we":[71],"present":[72],"new,":[74],"publicly":[75],"available":[76],"dataset":[77,140],"labeled":[79,139],"tracks":[81],"containing":[82],"We":[87,98,131],"evaluate":[88],"existing":[89],"detection":[92],"models":[93],"using":[94,117],"new":[96],"dataset.":[97],"also":[99],"introduce":[100],"novel":[102],"ensemble":[103],"approach":[104],"that":[105],"combines":[106],"high-level":[107],"representations":[109],"HuBERT":[111],"embeddings":[112],"CNN":[115],"classifier":[116],"traditional":[118],"low-level":[119],"audio":[120],"features.":[121],"Our":[122],"evaluation":[123],"confirms":[124],"be":[127],"effective":[129],"approach.":[130],"share":[132],"our":[133,138],"results,":[134],"trained":[135],"models,":[136],"encourage":[142],"future":[143],"research.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}