{"id":"https://openalex.org/W4392909515","doi":"https://doi.org/10.1109/icassp48485.2024.10446066","title":"Neural Concatenative Singing Voice Conversion: Rethinking Concatenation-Based Approach for One-Shot Singing Voice Conversion","display_name":"Neural Concatenative Singing Voice Conversion: Rethinking Concatenation-Based Approach for One-Shot Singing Voice Conversion","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909515","doi":"https://doi.org/10.1109/icassp48485.2024.10446066"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699660","display_name":"Li Xu","orcid":"https://orcid.org/0000-0003-2954-3271"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["Tencent PCG,ARC Lab","ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"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","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","The Chinese University of Hong Kong, Hong Kong SAR, China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["Tencent PCG,ARC Lab","ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12577","last_page":"12581"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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":0.9939000010490417,"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":0.9921000003814697,"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":0.9240989089012146},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.8568482398986816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.73809814453125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6274958848953247},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2671694755554199},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.08851882815361023},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07556670904159546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06818157434463501}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9240989089012146},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8568482398986816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.73809814453125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6274958848953247},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2671694755554199},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.08851882815361023},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07556670904159546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06818157434463501}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1741199358","https://openalex.org/W1999838901","https://openalex.org/W2067709094","https://openalex.org/W2402356521","https://openalex.org/W2593414223","https://openalex.org/W2726515241","https://openalex.org/W2760103357","https://openalex.org/W2808631503","https://openalex.org/W2972812066","https://openalex.org/W2990440871","https://openalex.org/W3015338123","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3092028330","https://openalex.org/W3095948607","https://openalex.org/W3096429957","https://openalex.org/W3097152652","https://openalex.org/W3170751106","https://openalex.org/W3197943112","https://openalex.org/W3199364993","https://openalex.org/W3203407300","https://openalex.org/W3209984917","https://openalex.org/W4206908380","https://openalex.org/W4221151538","https://openalex.org/W4224927653","https://openalex.org/W4226320669","https://openalex.org/W4283731195","https://openalex.org/W4285345683","https://openalex.org/W4319862652","https://openalex.org/W4375869411","https://openalex.org/W4385823432","https://openalex.org/W6637576829","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2373577936","https://openalex.org/W2390529913","https://openalex.org/W4387678054","https://openalex.org/W3095575180","https://openalex.org/W2142368101","https://openalex.org/W2389596151","https://openalex.org/W2372249404","https://openalex.org/W4221148444"],"abstract_inverted_index":{"Any-to-any":[0],"singing":[1],"voice":[2,100],"conversion":[3,101],"(SVC)":[4],"is":[5,102],"confronted":[6],"with":[7,109],"the":[8,19,22,67,123,134,143,146,151,164,169],"challenge":[9],"of":[10,41],"\"timbre":[11,152],"leakage\"":[12,153],"issue":[13,154],"caused":[14,155],"by":[15,104,156],"inadequate":[16],"disentanglement":[17],"between":[18],"content":[20],"and":[21,53,79,95,131,180],"speaker":[23,171],"timbre.":[24],"To":[25],"address":[26],"this":[27,29],"issue,":[28],"study":[30],"introduces":[31],"NeuCoSVC,":[32],"a":[33,42,48,54,114],"novel":[34],"neural":[35,49],"concatenative":[36],"SVC":[37,176],"framework.":[38],"It":[39],"consists":[40],"self-supervised":[43],"learning":[44],"(SSL)":[45],"representation":[46],"extractor,":[47],"harmonic":[50,68,81,93,129],"signal":[51,69],"generator,":[52],"waveform":[55],"synthesizer.":[56],"The":[57,86],"SSL":[58,64,91,107,119,140],"extractor":[59],"condenses":[60],"audio":[61],"into":[62],"fixed-dimensional":[63],"features,":[65,92],"while":[66,126],"generator":[70],"leverages":[71],"linear":[72],"time-varying":[73],"filters":[74],"to":[75],"produce":[76],"both":[77],"raw":[78,128],"filtered":[80],"signals":[82,130],"for":[83],"pitch":[84],"information.":[85,97],"synthesizer":[87],"reconstructs":[88],"waveforms":[89],"using":[90],"signals,":[94],"loudness":[96,132],"During":[98],"inference,":[99],"performed":[103],"substituting":[105],"source":[106,135],"features":[108,120,141],"their":[110],"nearest":[111],"counterparts":[112],"from":[113,122,133,142],"matching":[115],"pool":[116],"which":[117],"comprises":[118],"extracted":[121],"reference":[124,144],"audio,":[125,145],"preserving":[127],"audio.":[136],"By":[137],"directly":[138],"utilizing":[139],"proposed":[147,165],"framework":[148],"effectively":[149],"resolves":[150],"previous":[157],"disentanglement-based":[158,170],"approaches.":[159],"Experimental":[160],"results":[161],"demonstrate":[162],"that":[163],"NeuCoSVC":[166],"system":[167],"outperforms":[168],"embedding":[172],"approach":[173],"in":[174],"one-shot":[175],"across":[177],"intra-language,":[178],"cross-language,":[179],"cross-domain":[181],"evaluations.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}