{"id":"https://openalex.org/W4372338328","doi":"https://doi.org/10.1109/icassp49357.2023.10097147","title":"Self-Supervised Representations for Singing Voice Conversion","display_name":"Self-Supervised Representations for Singing Voice Conversion","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372338328","doi":"https://doi.org/10.1109/icassp49357.2023.10097147"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5076520549","display_name":"Tejas Jayashankar","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tejas Jayashankar","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057239023","display_name":"Jilong Wu","orcid":"https://orcid.org/0009-0007-8000-347X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jilong Wu","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003052411","display_name":"Leda Sar\u0131","orcid":"https://orcid.org/0000-0002-3754-1156"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leda Sari","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019683792","display_name":"David Kant","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Kant","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028956985","display_name":"Vimal Manohar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vimal Manohar","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102191169","display_name":"Qing He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing He","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5076520549"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":3.0695,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92965643,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9991000294685364,"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":0.8666091561317444},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7548980712890625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6958295106887817},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5964850187301636},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5834624767303467},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4892863929271698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4271862208843231},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16233113408088684}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8666091561317444},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7548980712890625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958295106887817},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5964850187301636},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5834624767303467},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4892863929271698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4271862208843231},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16233113408088684},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W1494198834","https://openalex.org/W2066598518","https://openalex.org/W2067709094","https://openalex.org/W2127141656","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2519091744","https://openalex.org/W2896457183","https://openalex.org/W2962866891","https://openalex.org/W2972812066","https://openalex.org/W2995181338","https://openalex.org/W3016007107","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3094843121","https://openalex.org/W3095948607","https://openalex.org/W3140429000","https://openalex.org/W3205154814","https://openalex.org/W3209059054","https://openalex.org/W4200629636","https://openalex.org/W4298580827","https://openalex.org/W6748409065","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6781414969","https://openalex.org/W6783867762","https://openalex.org/W6791823829","https://openalex.org/W6802329053","https://openalex.org/W6805485604"],"related_works":["https://openalex.org/W2118466154","https://openalex.org/W2118371117","https://openalex.org/W4247380401","https://openalex.org/W3112683371","https://openalex.org/W3113198510","https://openalex.org/W2464878701","https://openalex.org/W1918576746","https://openalex.org/W3176125119","https://openalex.org/W3013946943","https://openalex.org/W4307784074"],"abstract_inverted_index":{"A":[0],"singing":[1,49,93,136,175],"voice":[2,10,18,94,137,149,176],"conversion":[3,138,177],"model":[4,78,142],"converts":[5],"a":[6,20,76,88,119,147,155],"song":[7],"in":[8,133],"the":[9,17,39,61,134,141,171],"of":[11,19,122,145,173],"an":[12,109],"arbitrary":[13],"source":[14],"singer":[15,167],"to":[16,59,87],"target":[21],"singer.":[22],"Recently,":[23],"methods":[24,43],"that":[25,79,108,117,154,188],"leverage":[26],"self-supervised":[27,62,83],"audio":[28],"representations":[29,63,84],"such":[30],"as":[31,85],"HuBERT":[32],"and":[33,47,56,65,74,106,169,192],"Wav2Vec":[34,129],"2.0":[35,130],"have":[36],"helped":[37],"further":[38],"state-of-the-art.":[40],"Though":[41],"these":[42],"produce":[44],"more":[45],"natural":[46],"melodic":[48],"outputs,":[50],"they":[51],"often":[52],"rely":[53],"on":[54],"confusion":[55],"disentanglement":[57,72],"losses":[58],"render":[60],"speaker":[64],"pitch-invariant.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"circumvent":[71],"training":[73],"propose":[75],"new":[77],"leverages":[80],"ASR":[81,127],"fine-tuned":[82,128],"inputs":[86],"HiFi-GAN":[89],"neural":[90],"vocoder":[91],"for":[92],"conversion.":[95],"We":[96,151],"experiment":[97],"with":[98],"different":[99,190],"f":[100,110,157],"<inf":[101,111,158],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[102,112,159],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>":[103,113,160],"encoding":[104],"schemes":[105],"show":[107,153],"harmonic":[114],"generation":[115],"module":[116],"uses":[118],"parallel":[120],"bank":[121],"transposed":[123],"convolutions":[124],"(PBTC)":[125],"alongside":[126],"features":[131],"results":[132,180],"best":[135],"quality.":[139],"Additionally,":[140],"is":[143],"capable":[144],"making":[146],"spoken":[148],"sing.":[150],"also":[152],"simple":[156],"shifting":[161],"scheme":[162],"during":[163],"inference":[164],"helps":[165],"retain":[166],"identity":[168],"bolsters":[170],"performance":[172],"our":[174],"model.":[178],"Our":[179],"are":[181],"backed":[182],"up":[183],"by":[184],"extensive":[185],"MOS":[186],"studies":[187],"compare":[189],"ablations":[191],"baselines.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}