{"id":"https://openalex.org/W4406462037","doi":"https://doi.org/10.1109/slt61566.2024.10832319","title":"Leveraging Diverse Semantic-Based Audio Pretrained Models for Singing Voice Conversion","display_name":"Leveraging Diverse Semantic-Based Audio Pretrained Models for Singing Voice Conversion","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406462037","doi":"https://doi.org/10.1109/slt61566.2024.10832319"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832319","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/A5100617727","display_name":"Xueyao Zhang","orcid":"https://orcid.org/0000-0003-2615-019X"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xueyao Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109797442","display_name":"Zihao Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Fang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102714342","display_name":"Yicheng Gu","orcid":"https://orcid.org/0000-0002-0506-3364"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Gu","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080204035","display_name":"Haopeng Chen","orcid":"https://orcid.org/0000-0002-4535-5038"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haopeng Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101257950","display_name":"Lexiao Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lexiao Zou","raw_affiliation_strings":["Shenzhen Research Institute of Big Data"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013313233","display_name":"J. S. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junan Zhang","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009337933","display_name":"Liumeng Xue","orcid":"https://orcid.org/0000-0003-2815-8494"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liumeng Xue","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100617727"],"corresponding_institution_ids":["https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73251954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"758","last_page":"765"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8153683543205261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7641175985336304},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6975459456443787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3464367985725403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3282032310962677},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1177002489566803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153683543205261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7641175985336304},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6975459456443787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3464367985725403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3282032310962677},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1177002489566803},{"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/slt61566.2024.10832319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832319","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2009226274","https://openalex.org/W2107860279","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2884225676","https://openalex.org/W2921857201","https://openalex.org/W2945478979","https://openalex.org/W2962784628","https://openalex.org/W2972812066","https://openalex.org/W3016007107","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3129651364","https://openalex.org/W3163568691","https://openalex.org/W3197478142","https://openalex.org/W3205154814","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226320669","https://openalex.org/W4283659485","https://openalex.org/W4287666817","https://openalex.org/W4287889585","https://openalex.org/W4296068763","https://openalex.org/W4307077171","https://openalex.org/W4311000453","https://openalex.org/W4312933868","https://openalex.org/W4366460484","https://openalex.org/W4372338328","https://openalex.org/W4379924545","https://openalex.org/W4385245566","https://openalex.org/W4386536196","https://openalex.org/W4391021724","https://openalex.org/W4391021798","https://openalex.org/W4392908976","https://openalex.org/W4392909515","https://openalex.org/W4406461271","https://openalex.org/W4406461681","https://openalex.org/W6762533536","https://openalex.org/W6780218876","https://openalex.org/W6783182287","https://openalex.org/W6784691655","https://openalex.org/W6787084273","https://openalex.org/W6839738141","https://openalex.org/W6846445453","https://openalex.org/W6847363464","https://openalex.org/W6851724922","https://openalex.org/W6852870047","https://openalex.org/W6859403842"],"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/W3204019825"],"abstract_inverted_index":{"Singing":[0,127],"Voice":[1,128],"Conversion":[2,129],"(SVC)":[3],"is":[4,19,112,161],"a":[5,31,39,45,126],"technique":[6],"that":[7,106,141],"enables":[8],"any":[9,13],"singer":[10],"to":[11,21,51,69],"perform":[12],"song.":[14],"To":[15],"achieve":[16],"this,":[17],"it":[18],"essential":[20],"obtain":[22],"speaker-agnostic":[23],"representations":[24],"from":[25],"the":[26,49,53,58,75,94,107,122],"source":[27],"audio,":[28],"which":[29,52],"poses":[30],"significant":[32],"challenge.":[33],"A":[34],"common":[35],"solution":[36],"involves":[37],"utilizing":[38],"semantic-based":[40,98],"audio":[41],"pretrained":[42,99],"model":[43,71],"as":[44],"feature":[46],"extractor":[47],"However,":[48],"degree":[50],"extracted":[54],"features":[55],"can":[56,115,143],"meet":[57],"SVC":[59,150],"requirements":[60],"remains":[61],"an":[62],"open":[63],"question.":[64],"This":[65],"includes":[66],"their":[67,78,83],"capability":[68],"accurately":[70],"melody":[72],"and":[73,82,114,146],"lyrics,":[74],"speaker-independency":[76],"of":[77,109],"underlying":[79],"acoustic":[80,87],"information,":[81],"robustness":[84],"for":[85,118],"in-the-wild":[86],"environments.":[88],"In":[89],"this":[90],"study,":[91],"we":[92,124],"investigate":[93],"knowledge":[95,108],"within":[96],"classical":[97],"models":[100,111],"in":[101,153],"much":[102],"detail.":[103],"We":[104],"discover":[105],"different":[110],"diverse":[113],"be":[116,144],"complementary":[117],"SVC.":[119],"Based":[120],"on":[121,132],"above,":[123],"design":[125],"framework":[130],"based":[131],"Diverse":[133],"Semantic-based":[134],"Feature":[135],"Fusion":[136],"(DSFF-SVC).":[137],"Experimental":[138],"results":[139],"demonstrate":[140],"DSFF-SVC":[142],"generalized":[145],"improve":[147],"various":[148],"existing":[149],"models,":[151],"particularly":[152],"challenging":[154],"real-world":[155],"conversion":[156],"tasks.":[157],"Our":[158],"demo":[159],"website":[160],"available":[162],"at":[163],"https://diversesemanticsvc.github.io/.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}