{"id":"https://openalex.org/W4406461891","doi":"https://doi.org/10.1109/slt61566.2024.10832226","title":"Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CTRSVDD) Challenge 2024","display_name":"Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CTRSVDD) Challenge 2024","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461891","doi":"https://doi.org/10.1109/slt61566.2024.10832226"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832226","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/A5114320033","display_name":"Anmol Guragain","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Anmol Guragain","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013047791","display_name":"Tianchi Liu","orcid":"https://orcid.org/0000-0003-3472-0703"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianchi Liu","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101773506","display_name":"Zihan Pan","orcid":"https://orcid.org/0000-0001-9927-9053"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zihan Pan","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101991100","display_name":"Qiongqiong Wang","orcid":"https://orcid.org/0000-0002-9903-0618"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qiongqiong Wang","raw_affiliation_strings":["Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR),Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114320033"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":4.7498,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95663417,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"774","last_page":"781"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.7796822786331177},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.7549338340759277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6586070656776428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.537003219127655},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22237375378608704},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.06776657700538635}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7796822786331177},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7549338340759277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6586070656776428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.537003219127655},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22237375378608704},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.06776657700538635},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832226","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":[{"display_name":"Gender equality","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2588445447","https://openalex.org/W2752782242","https://openalex.org/W2936802426","https://openalex.org/W2967606780","https://openalex.org/W2972594541","https://openalex.org/W2973164265","https://openalex.org/W2973181078","https://openalex.org/W3006808893","https://openalex.org/W3024869864","https://openalex.org/W3041870963","https://openalex.org/W3096084197","https://openalex.org/W3127781933","https://openalex.org/W3158663310","https://openalex.org/W3159302906","https://openalex.org/W3197580070","https://openalex.org/W3201773091","https://openalex.org/W3209984917","https://openalex.org/W3211424380","https://openalex.org/W4221154746","https://openalex.org/W4225527248","https://openalex.org/W4226264925","https://openalex.org/W4313306150","https://openalex.org/W4385822574","https://openalex.org/W4392903264","https://openalex.org/W4392904324","https://openalex.org/W4392908976","https://openalex.org/W4392909814","https://openalex.org/W4392909895","https://openalex.org/W4392910562","https://openalex.org/W4394744939","https://openalex.org/W4396817233","https://openalex.org/W4399597893","https://openalex.org/W4402111665","https://openalex.org/W4402111788","https://openalex.org/W4402111996","https://openalex.org/W4402112070","https://openalex.org/W4402112543","https://openalex.org/W4402115980","https://openalex.org/W4402116004","https://openalex.org/W4406461839","https://openalex.org/W4406495581","https://openalex.org/W6772925044","https://openalex.org/W6780218876","https://openalex.org/W6857495872","https://openalex.org/W6866747874","https://openalex.org/W6869055001"],"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":{"This":[0],"work":[1],"details":[2],"our":[3,108,118],"approach":[4,119],"to":[5,59,76],"achieving":[6],"a":[7,11,86],"leading":[8],"system":[9],"with":[10],"1.79%":[12],"pooled":[13],"equal":[14],"error":[15],"rate":[16],"(EER)":[17],"on":[18],"the":[19,23,69,100,105,115],"evaluation":[20],"set":[21],"of":[22,33,107,117],"Controlled":[24],"Singing":[25,51],"Voice":[26,52],"Deepfake":[27,53],"Detection":[28,54],"(CtrSVDD).":[29],"The":[30,50,125],"rapid":[31],"advancement":[32],"generative":[34],"AI":[35],"models":[36,75],"presents":[37],"significant":[38],"challenges":[39],"for":[40],"detecting":[41,121],"AI-generated":[42],"deepfake":[43,122],"singing":[44,79,123],"voices,":[45],"attracting":[46],"increased":[47],"research":[48],"attention.":[49],"(SVDD)":[55],"Challenge":[56],"2024":[57],"aims":[58],"address":[60],"this":[61,65],"complex":[62],"task.":[63],"In":[64],"work,":[66],"we":[67],"explore":[68],"ensemble":[70],"methods,":[71],"utilizing":[72],"speech":[73,101],"foundation":[74,102],"develop":[77],"robust":[78],"voice":[80],"anti-spoofing":[81],"systems.":[82,111],"We":[83],"also":[84],"introduce":[85],"novel":[87],"Squeeze-and-Excitation":[88],"Aggregation":[89],"(SEA)":[90],"method,":[91],"which":[92],"efficiently":[93],"and":[94],"effectively":[95],"integrates":[96],"representation":[97],"features":[98],"from":[99],"models,":[103],"surpassing":[104],"performance":[106],"other":[109],"individual":[110],"Evaluation":[112],"results":[113],"confirm":[114],"efficacy":[116],"in":[120],"voices.":[124],"codes":[126],"can":[127],"be":[128],"accessed":[129],"at":[130],"https://github.com/Anmol2059/SVDD2024.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}