{"id":"https://openalex.org/W4408352902","doi":"https://doi.org/10.1109/icassp49660.2025.10890068","title":"FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion","display_name":"FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352902","doi":"https://doi.org/10.1109/icassp49660.2025.10890068"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5018617522","display_name":"Alef Iury Siqueira Ferreira","orcid":"https://orcid.org/0000-0002-9119-6357"},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alef Iury Ferreira","raw_affiliation_strings":["AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019858243","display_name":"Lucas Rafael Stefanel Gris","orcid":"https://orcid.org/0000-0002-2099-5004"},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas Rafael Gris","raw_affiliation_strings":["AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Augusto Da Rosa","orcid":null},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Augusto Da Rosa","raw_affiliation_strings":["AKCIT Federal University of Goias,Goiânia,Goi\u00e1s,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AKCIT Federal University of Goias,Goiânia,Goi\u00e1s,Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057639095","display_name":"Frederico Santos de Oliveira","orcid":"https://orcid.org/0000-0002-5885-6747"},"institutions":[{"id":"https://openalex.org/I1283613182","display_name":"Universidade Tecnol\u00f3gica Federal do Paran\u00e1","ror":"https://ror.org/002v2kq79","country_code":"BR","type":"education","lineage":["https://openalex.org/I1283613182"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Frederico Oliveira","raw_affiliation_strings":["Federal Technological University of Paraná,Medianeira,Paran\u00e1,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal Technological University of Paraná,Medianeira,Paran\u00e1,Brazil","institution_ids":["https://openalex.org/I1283613182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025318789","display_name":"Edresson Casanova","orcid":"https://orcid.org/0000-0003-0160-7173"},"institutions":[{"id":"https://openalex.org/I32725510","display_name":"Universidade Federal de Mato Grosso","ror":"https://ror.org/01mqvjv41","country_code":"BR","type":"education","lineage":["https://openalex.org/I32725510"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edresson Casanova","raw_affiliation_strings":["Federal University of Mato Grosso,Cuiabá,Mato Grosso,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Mato Grosso,Cuiabá,Mato Grosso,Brazil","institution_ids":["https://openalex.org/I32725510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042137704","display_name":"Rafael Sousa","orcid":"https://orcid.org/0000-0001-9394-522X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafael Sousa","raw_affiliation_strings":["NVIDIA,São Paulo,S\u00e3o Paulo,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,São Paulo,S\u00e3o Paulo,Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arnaldo Junior","orcid":null},"institutions":[{"id":"https://openalex.org/I879563668","display_name":"Universidade Estadual Paulista (Unesp)","ror":"https://ror.org/00987cb86","country_code":"BR","type":"education","lineage":["https://openalex.org/I879563668"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Arnaldo Junior","raw_affiliation_strings":["São Paulo State University,São Paulo,S\u00e3o Paulo,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"São Paulo State University,São Paulo,S\u00e3o Paulo,Brazil","institution_ids":["https://openalex.org/I879563668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024062827","display_name":"Anderson S. Soares","orcid":"https://orcid.org/0000-0001-9701-0819"},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Anderson Soares","raw_affiliation_strings":["AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil","institution_ids":["https://openalex.org/I68106152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080739504","display_name":"Arlindo Rodrigues Galv\u00e3o Filho","orcid":"https://orcid.org/0000-0003-2151-8039"},"institutions":[{"id":"https://openalex.org/I68106152","display_name":"Universidade Federal de Goi\u00e1s","ror":"https://ror.org/0039d5757","country_code":"BR","type":"education","lineage":["https://openalex.org/I68106152"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Arlindo Galv\u00e3o Filho","raw_affiliation_strings":["AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AKCIT Federal University of Goiás,Goiânia,Goi\u00e1s,Brazil","institution_ids":["https://openalex.org/I68106152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6768,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79095425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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":0.9955999851226807,"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":0.9837999939918518,"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":0.983299970626831,"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/zero","display_name":"Zero (linguistics)","score":0.6289252042770386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6276824474334717},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6209904551506042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6059302091598511},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4176604151725769},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1958387792110443},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13617736101150513},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10973945260047913},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06276360154151917}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6289252042770386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6276824474334717},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6209904551506042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6059302091598511},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4176604151725769},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1958387792110443},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13617736101150513},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10973945260047913},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06276360154151917},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1995945562","https://openalex.org/W2808631503","https://openalex.org/W2963242190","https://openalex.org/W3016007107","https://openalex.org/W3163573274","https://openalex.org/W3170751106","https://openalex.org/W3198020407","https://openalex.org/W3198533616","https://openalex.org/W3205154814","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221151538","https://openalex.org/W4221153221","https://openalex.org/W4224073284","https://openalex.org/W4226320669","https://openalex.org/W4285345683","https://openalex.org/W4296068763","https://openalex.org/W4372260053","https://openalex.org/W4372338328","https://openalex.org/W4385822304","https://openalex.org/W4385822740","https://openalex.org/W4385823191","https://openalex.org/W4386058741","https://openalex.org/W4391021719","https://openalex.org/W4391021772","https://openalex.org/W4391827396","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6750489868","https://openalex.org/W6757202746","https://openalex.org/W6767245602","https://openalex.org/W6772349387","https://openalex.org/W6786611447","https://openalex.org/W6796464841","https://openalex.org/W6796684895","https://openalex.org/W6805710207","https://openalex.org/W6839738141","https://openalex.org/W6847430118","https://openalex.org/W6852909395"],"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],"presents":[2],"FreeSVC,":[3],"a":[4,71],"promising":[5],"multilingual":[6,72],"singing":[7,61],"voice":[8,62],"conversion":[9,63],"approach":[10],"that":[11,70],"leverages":[12],"an":[13,43],"enhanced":[14],"VITS":[15],"model":[16],"with":[17],"Speaker-invariant":[18],"Clustering":[19],"(SPIN)":[20],"for":[21,55,77],"better":[22],"content":[23,73],"representation":[24],"and":[25,41,84],"the":[26],"State-of-the-Art":[27],"(SOTA)":[28],"speaker":[29,45,49],"encoder":[30,46],"ECAPA2.":[31],"FreeSVC":[32,58],"incorporates":[33],"trainable":[34],"language":[35],"embeddings":[36],"to":[37,47],"handle":[38],"multiple":[39],"languages":[40],"employs":[42],"advanced":[44],"disentangle":[48],"characteristics":[50],"from":[51],"linguistic":[52],"content.":[53],"Designed":[54],"zero-shot":[56],"learning,":[57],"enables":[59],"cross-lingual":[60],"without":[64],"extensive":[65],"language-specific":[66],"training.":[67],"We":[68],"demonstrate":[69],"extractor":[74],"is":[75],"crucial":[76],"optimal":[78],"cross-language":[79],"conversion.":[80],"Our":[81],"source":[82],"code":[83],"models":[85],"are":[86],"publicly":[87],"available1.":[88]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}