{"id":"https://openalex.org/W4405709643","doi":"https://doi.org/10.1109/iscslp63861.2024.10800547","title":"RobustSVC: HuBERT-Based Melody Extractor and Adversarial Learning for Robust Singing Voice Conversion","display_name":"RobustSVC: HuBERT-Based Melody Extractor and Adversarial Learning for Robust Singing Voice Conversion","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709643","doi":"https://doi.org/10.1109/iscslp63861.2024.10800547"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5059286427","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0003-3316-0417"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112937772","display_name":"Xintao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xintao Zhao","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053479642","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0001-6926-8118"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Chen","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093470868","display_name":"Binzhu Sha","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binzhu Sha","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102424493","display_name":"Zhiwei Lin","orcid":"https://orcid.org/0000-0003-0389-4444"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Lin","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100667025","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-6527-5502"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University,Shenzhen","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059286427"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72818289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"164","last_page":"168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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":0.996999979019165,"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":0.9941999912261963,"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":0.9868999719619751,"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":0.791527509689331},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.7872756719589233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7107610702514648},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6977183222770691},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6932290196418762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3836510181427002},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32042640447616577},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12463459372520447},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12418913841247559}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.791527509689331},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.7872756719589233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107610702514648},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6977183222770691},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6932290196418762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3836510181427002},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32042640447616577},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12463459372520447},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12418913841247559},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1590808459","https://openalex.org/W2007023536","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2921857201","https://openalex.org/W2964243274","https://openalex.org/W3016007107","https://openalex.org/W3016243847","https://openalex.org/W3097777922","https://openalex.org/W3163568691","https://openalex.org/W3205154814","https://openalex.org/W3206189675","https://openalex.org/W3210530853","https://openalex.org/W4225322394","https://openalex.org/W4285345683","https://openalex.org/W4296068763","https://openalex.org/W4372260250","https://openalex.org/W4372340947","https://openalex.org/W4386158910","https://openalex.org/W4391021724","https://openalex.org/W4391021798","https://openalex.org/W6729110096","https://openalex.org/W6778215197","https://openalex.org/W6781547035","https://openalex.org/W6783867762","https://openalex.org/W6786824797","https://openalex.org/W6857514821"],"related_works":["https://openalex.org/W2502115930","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","https://openalex.org/W1501596003"],"abstract_inverted_index":{"Singing":[0],"voice":[1],"conversion":[2],"(SVC)":[3],"is":[4,130],"hindered":[5],"by":[6,96],"noise":[7,61],"sensitivity":[8],"due":[9],"to":[10,58,118],"the":[11,22,30,68,73,97,102],"use":[12,111],"of":[13,72],"non-robust":[14,103],"methods":[15,56,140],"for":[16,29,43],"extracting":[17],"pitch":[18],"and":[19,70,110,132,136,144],"energy":[20],"during":[21],"inference.":[23],"As":[24],"clean":[25,93,145],"signals":[26],"are":[27],"key":[28],"source":[31,36],"audio":[32],"in":[33,122,141],"SVC,":[34],"music":[35,51],"separation":[37],"preprocessing":[38],"offers":[39],"a":[40,83,106],"viable":[41],"solution":[42],"handling":[44],"noisy":[45,90,143],"audio,":[46],"like":[47],"singing":[48],"with":[49,105,115],"background":[50],"(BGM).":[52],"However,":[53],"current":[54],"separating":[55],"struggle":[57],"fully":[59],"remove":[60],"or":[62],"excessively":[63],"suppress":[64],"signal":[65],"components,":[66],"affecting":[67],"naturalness":[69,137],"similarity":[71,135],"processed":[74],"audio.":[75],"To":[76],"tackle":[77],"this,":[78],"our":[79],"study":[80],"introduces":[81],"RobustSVC,":[82],"novel":[84],"any-to-one":[85],"SVC":[86],"framework":[87],"that":[88,128],"converts":[89],"vocals":[91,94],"into":[92],"sung":[95],"target":[98],"singer.":[99],"We":[100],"replace":[101],"feature":[104],"HuBERT-based":[107],"melody":[108],"extractor":[109],"adversarial":[112],"training":[113],"mechanisms":[114],"three":[116],"discriminators":[117],"reduce":[119],"information":[120],"leakage":[121],"self-supervised":[123],"representations.":[124],"Experimental":[125],"results":[126],"show":[127],"RobustSVC":[129],"noise-robust":[131],"achieves":[133],"higher":[134],"than":[138],"baseline":[139],"both":[142],"vocal":[146],"conditions.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}