{"id":"https://openalex.org/W4408352811","doi":"https://doi.org/10.1109/icassp49660.2025.10888953","title":"kNN-SVC: Robust Zero-Shot Singing Voice Conversion with Additive Synthesis and Concatenation Smoothness Optimization","display_name":"kNN-SVC: Robust Zero-Shot Singing Voice Conversion with Additive Synthesis and Concatenation Smoothness Optimization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352811","doi":"https://doi.org/10.1109/icassp49660.2025.10888953"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888953","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/A5113182213","display_name":"Keren Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keren Shao","raw_affiliation_strings":["University of California San Diego,La Jolla,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego,La Jolla,USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451980","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-8357-3741"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["University of California San Diego,La Jolla,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego,La Jolla,USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085677838","display_name":"Matthew Baas","orcid":"https://orcid.org/0000-0003-3001-6292"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Matthew Baas","raw_affiliation_strings":["Stellenbosch University,Stellenbosch,South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Stellenbosch,South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042278809","display_name":"Shlomo Dubnov","orcid":"https://orcid.org/0000-0003-0222-1125"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":["University of California San Diego,La Jolla,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego,La Jolla,USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9987999796867371,"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":0.9987999796867371,"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":0.9980000257492065,"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":0.982200026512146,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.7587669491767883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.648449182510376},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6167678833007812},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6119274497032166},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.5868456959724426},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.48688092827796936},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3260366916656494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19026121497154236},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1642303466796875},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.14673930406570435}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7587669491767883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.648449182510376},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6167678833007812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6119274497032166},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.5868456959724426},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.48688092827796936},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3260366916656494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19026121497154236},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1642303466796875},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.14673930406570435},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888953","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/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2067709094","https://openalex.org/W2972812066","https://openalex.org/W3016007107","https://openalex.org/W3025192522","https://openalex.org/W3098557217","https://openalex.org/W3163568691","https://openalex.org/W3170751106","https://openalex.org/W3196667132","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4221151538","https://openalex.org/W4226320669","https://openalex.org/W4285345683","https://openalex.org/W4375869015","https://openalex.org/W4385823432","https://openalex.org/W4391021724","https://openalex.org/W4392909515","https://openalex.org/W6771763809","https://openalex.org/W6839738141","https://openalex.org/W6854940191"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W2390529913","https://openalex.org/W3095575180","https://openalex.org/W2142368101","https://openalex.org/W2389596151","https://openalex.org/W2372249404","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W2367547137","https://openalex.org/W2354994102"],"abstract_inverted_index":{"Robustness":[0],"is":[1],"critical":[2],"in":[3,34,77,134],"zero-shot":[4],"singing":[5],"voice":[6],"conversion":[7],"(SVC).":[8],"This":[9],"paper":[10],"introduces":[11],"two":[12],"novel":[13],"methods":[14],"to":[15,53,64,120],"strengthen":[16],"the":[17,20,45,58,62,96,100,110,129],"robustness":[18],"of":[19,99,131],"kNN-VC":[21,69,111],"framework":[22,112],"for":[23,113],"SVC.":[24,78,137],"First,":[25],"kNN-VC\u2019s":[26],"core":[27],"representation,":[28],"WavLM,":[29,48],"lacks":[30],"harmonic":[31],"emphasis,":[32],"resulting":[33,59],"dull":[35],"sounds":[36],"and":[37,51,94],"ringing":[38],"artifacts.":[39],"To":[40,79],"address":[41],"this,":[42],"we":[43,82],"leverage":[44],"bijection":[46],"between":[47],"pitch":[49],"contours,":[50],"spectrograms":[52],"perform":[54],"additive":[55],"synthesis,":[56],"integrating":[57],"waveform":[60],"into":[61],"model":[63],"mitigate":[65],"these":[66,132],"issues.":[67],"Second,":[68],"overlooks":[70],"concatenative":[71,122],"smoothness,":[72,81],"a":[73,84],"key":[74],"perceptual":[75],"factor":[76],"enhance":[80],"propose":[83],"new":[85],"distance":[86],"metric":[87],"that":[88],"filters":[89],"out":[90],"unsuitable":[91],"kNN":[92],"candidates":[93,101],"optimize":[95],"summing":[97],"weights":[98],"during":[102],"inference.":[103],"Although":[104],"our":[105],"techniques":[106],"are":[107,117],"built":[108],"on":[109],"implementation":[114],"convenience,":[115],"they":[116],"broadly":[118],"applicable":[119],"general":[121],"neural":[123],"synthesis":[124],"models.":[125],"Experimental":[126],"results":[127],"validate":[128],"effectiveness":[130],"modifications":[133],"achieving":[135],"robust":[136],"Demo:":[138],"http://knnsvc.com.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
