{"id":"https://openalex.org/W4225273935","doi":"https://doi.org/10.1109/icassp43922.2022.9746562","title":"K-Converter: An Unsupervised Singing Voice Conversion System","display_name":"K-Converter: An Unsupervised Singing Voice Conversion System","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225273935","doi":"https://doi.org/10.1109/icassp43922.2022.9746562"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746562","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5100386104","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0002-2674-1638"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101863403","display_name":"Peng Yang","orcid":"https://orcid.org/0009-0005-3449-5843"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Yang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065801415","display_name":"Jinba Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinba Xiao","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624455","display_name":"Ye Bai","orcid":"https://orcid.org/0000-0001-5533-6909"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Bai","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112489758","display_name":"Hao Che","orcid":"https://orcid.org/0009-0001-9852-320X"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Che","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801745840"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"6662","last_page":"6666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9995999932289124,"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":0.9994999766349792,"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/singing","display_name":"Singing","score":0.8076534867286682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6211174726486206},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5872622728347778},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1644260287284851},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07269993424415588}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8076534867286682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6211174726486206},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5872622728347778},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1644260287284851},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07269993424415588}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746562","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1590808459","https://openalex.org/W2067709094","https://openalex.org/W2191779130","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2471520273","https://openalex.org/W2774848319","https://openalex.org/W2921857201","https://openalex.org/W2945478979","https://openalex.org/W2972659941","https://openalex.org/W2972812066","https://openalex.org/W3015338123","https://openalex.org/W3016007107","https://openalex.org/W3016243847","https://openalex.org/W3047855478","https://openalex.org/W3082910224","https://openalex.org/W3095948607","https://openalex.org/W3163568691","https://openalex.org/W3197541421","https://openalex.org/W6631190155","https://openalex.org/W6681102450","https://openalex.org/W6712902469","https://openalex.org/W6746801104","https://openalex.org/W6762533536","https://openalex.org/W6781414969","https://openalex.org/W6781547035","https://openalex.org/W6783382068","https://openalex.org/W6797523486"],"related_works":["https://openalex.org/W4391375266","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","https://openalex.org/W2366077683"],"abstract_inverted_index":{"Singing":[0],"voice":[1,7,11],"conversion":[2],"(SVC)":[3],"converts":[4],"a":[5,56],"singer\u2019s":[6],"to":[8,59,111,118,136,169],"another":[9],"one\u2019s":[10],"while":[12],"preserving":[13],"the":[14,61,84,94,102,121,127,130,138],"linguistic":[15],"content.":[16],"Recently,":[17],"some":[18],"SVC":[19,39],"systems":[20,40],"rely":[21],"on":[22],"supervised":[23],"phonetic":[24],"features":[25],"extracted":[26],"from":[27],"pre-trained":[28],"automatic":[29],"speech":[30,161],"recognition":[31],"(ASR)":[32],"models,":[33],"increasing":[34],"system":[35,58,156],"complexity.":[36],"Some":[37],"end-toend":[38],"use":[41],"adversarial":[42,72],"training,":[43],"which":[44,82,116],"causes":[45],"instability":[46],"during":[47],"optimization.":[48],"To":[49],"address":[50],"these":[51],"issues,":[52],"we":[53],"present":[54],"K-Converter,":[55],"simple":[57],"disentangle":[60],"timbre,":[62],"pitch,":[63],"and":[64,123,147,163],"content":[65,131,139],"information":[66,114,125],"without":[67],"any":[68],"manual":[69],"supervision":[70],"or":[71],"training.":[73],"First,":[74],"low":[75],"quefrencies":[76],"of":[77,126,144],"mel-frequency":[78],"cepstral":[79],"coefficients":[80],"(MFCC),":[81],"remove":[83],"glottal":[85],"excitation":[86],"mainly,":[87],"are":[88],"used":[89,98],"as":[90],"input":[91],"representations.":[92],"And":[93],"pitch-shift":[95],"augmentation":[96],"is":[97,108,134],"for":[99],"further":[100],"disentangling":[101],"pitch.":[103],"Second,":[104],"an":[105,113],"encoder":[106,142],"network":[107],"carefully":[109],"designed":[110],"construct":[112],"bottleneck,":[115],"learns":[117],"break":[119],"up":[120],"pitch":[122],"timbre":[124,164],"source.":[128],"Third,":[129],"consistency":[132],"loss":[133],"introduced":[135],"keep":[137],"consistent":[140],"between":[141],"outputs":[143],"source":[145],"utterances":[146],"reconstructed":[148],"ones.":[149],"Experimental":[150],"results":[151],"show":[152],"that":[153],"our":[154],"proposed":[155],"performs":[157],"well":[158],"in":[159],"both":[160],"naturalness":[162],"similarity,":[165],"with":[166],"better":[167],"robustness":[168],"comparisons.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
