{"id":"https://openalex.org/W3048203730","doi":"https://doi.org/10.21437/interspeech.2020-1862","title":"Unsupervised Cross-Domain Singing Voice Conversion","display_name":"Unsupervised Cross-Domain Singing Voice Conversion","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3048203730","doi":"https://doi.org/10.21437/interspeech.2020-1862","mag":"3048203730"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1862","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.02830","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038017098","display_name":"Adam Polyak","orcid":"https://orcid.org/0000-0003-2563-2111"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Adam Polyak","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078102229","display_name":"Lior Wolf","orcid":"https://orcid.org/0000-0001-5578-8892"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lior Wolf","raw_affiliation_strings":["Tel Aviv University, Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tel Aviv University, Tel Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070563684","display_name":"Yaniv Taigman","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yaniv Taigman","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"801","last_page":"805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9987999796867371,"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":0.8617258071899414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7845760583877563},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7508970499038696},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.678134024143219},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5367075204849243},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.524442732334137},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45074209570884705},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4448947310447693},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4167361557483673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40557175874710083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3915986120700836},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3757881224155426},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12052267789840698}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8617258071899414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845760583877563},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7508970499038696},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.678134024143219},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5367075204849243},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.524442732334137},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45074209570884705},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4448947310447693},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4167361557483673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40557175874710083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3915986120700836},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3757881224155426},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12052267789840698},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1862","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.02830","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.02830","pdf_url":"https://arxiv.org/pdf/2008.02830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3048203730","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2008.02830.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.02830","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.02830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.02830","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.02830","pdf_url":"https://arxiv.org/pdf/2008.02830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3048203730.pdf","grobid_xml":"https://content.openalex.org/works/W3048203730.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W1565658805","https://openalex.org/W1590808459","https://openalex.org/W2066598518","https://openalex.org/W2067709094","https://openalex.org/W2107740512","https://openalex.org/W2130086727","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2408435475","https://openalex.org/W2516406502","https://openalex.org/W2520160253","https://openalex.org/W2527729766","https://openalex.org/W2584032004","https://openalex.org/W2593414223","https://openalex.org/W2747874407","https://openalex.org/W2888169323","https://openalex.org/W2898148140","https://openalex.org/W2921857201","https://openalex.org/W2939354923","https://openalex.org/W2949382160","https://openalex.org/W2962739369","https://openalex.org/W2962866891","https://openalex.org/W2962882868","https://openalex.org/W2962883485","https://openalex.org/W2963103134","https://openalex.org/W2963175743","https://openalex.org/W2963216553","https://openalex.org/W2963300588","https://openalex.org/W2963399829","https://openalex.org/W2963534259","https://openalex.org/W2963568710","https://openalex.org/W2963685250","https://openalex.org/W2963782041","https://openalex.org/W2963821905","https://openalex.org/W2963975282","https://openalex.org/W2964307104","https://openalex.org/W2970006822","https://openalex.org/W2972812066","https://openalex.org/W2973215447","https://openalex.org/W2989708046","https://openalex.org/W2994689640","https://openalex.org/W2995233853","https://openalex.org/W3015338123","https://openalex.org/W3015499232","https://openalex.org/W3015645837","https://openalex.org/W3016007107","https://openalex.org/W3016243847","https://openalex.org/W3026010363"],"related_works":["https://openalex.org/W3095948607","https://openalex.org/W3207038517","https://openalex.org/W2921857201","https://openalex.org/W2964819890","https://openalex.org/W3109050852","https://openalex.org/W3015225476","https://openalex.org/W3041199652","https://openalex.org/W2057745663","https://openalex.org/W2972812066","https://openalex.org/W2937242376","https://openalex.org/W1499139979","https://openalex.org/W3155036195","https://openalex.org/W2935701729","https://openalex.org/W2932319787","https://openalex.org/W1588437207","https://openalex.org/W3167007286","https://openalex.org/W2516392987","https://openalex.org/W2009226274","https://openalex.org/W3095436719","https://openalex.org/W182406043"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,38],"wav-to-wav":[3],"generative":[4,43],"model":[5,70],"for":[6,24],"the":[7,25,48,107],"task":[8,26],"of":[9,27],"singing":[10,67],"voice":[11],"conversion":[12],"from":[13,59],"any":[14,78],"identity.":[15],"Our":[16],"method":[17,104],"utilizes":[18],"both":[19],"an":[20,74],"acoustic":[21],"model,":[22],"trained":[23,54],"automatic":[28],"speech":[29,65],"recognition,":[30],"together":[31],"with":[32],"melody":[33],"extracted":[34],"features":[35],"to":[36,47,55],"drive":[37],"waveform-based":[39],"generator.":[40],"The":[41,69,89],"proposed":[42,90],"architecture":[44],"is":[45,71,92],"invariant":[46],"speaker's":[49],"identity":[50],"and":[51,94],"can":[52,95],"be":[53],"generate":[56,96],"target":[57],"singers":[58],"unlabeled":[60],"training":[61],"data,":[62],"using":[63],"either":[64],"or":[66,86],"sources.":[68],"optimized":[72],"in":[73,98],"end-to-end":[75],"fashion":[76],"without":[77],"manual":[79],"supervision,":[80],"such":[81],"as":[82],"lyrics,":[83],"musical":[84],"notes":[85],"parallel":[87],"samples.":[88],"approach":[91],"fully-convolutional":[93],"audio":[97,114],"real-time.":[99],"Experiments":[100],"show":[101],"that":[102],"our":[103],"significantly":[105],"outperforms":[106],"baseline":[108],"methods":[109],"while":[110],"generating":[111],"convincingly":[112],"better":[113],"samples":[115],"than":[116],"alternative":[117],"attempts.":[118]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
