{"id":"https://openalex.org/W4391021724","doi":"https://doi.org/10.1109/asru57964.2023.10389671","title":"The Singing Voice Conversion Challenge 2023","display_name":"The Singing Voice Conversion Challenge 2023","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021724","doi":"https://doi.org/10.1109/asru57964.2023.10389671"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013549148","display_name":"Lester Phillip Violeta","orcid":"https://orcid.org/0000-0001-9118-2994"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lester Phillip Violeta","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"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":"Songxiang Liu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000377034"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":7.1621,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97788561,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7708620429039001},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7291457056999207},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6910461187362671},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6504761576652527},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6232749819755554},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5331043004989624},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4980049133300781},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4896431565284729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34167665243148804},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06947502493858337}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708620429039001},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7291457056999207},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6910461187362671},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6504761576652527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6232749819755554},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5331043004989624},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4980049133300781},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4896431565284729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34167665243148804},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06947502493858337},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389671","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389671","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1590808459","https://openalex.org/W2022125261","https://openalex.org/W2022241205","https://openalex.org/W2052871313","https://openalex.org/W2056852181","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2403098732","https://openalex.org/W2473388484","https://openalex.org/W2576309025","https://openalex.org/W2962780374","https://openalex.org/W2963035245","https://openalex.org/W2972812066","https://openalex.org/W2973071600","https://openalex.org/W2990440871","https://openalex.org/W3012498027","https://openalex.org/W3016007107","https://openalex.org/W3016243847","https://openalex.org/W3025192522","https://openalex.org/W3081753361","https://openalex.org/W3095948607","https://openalex.org/W3096567388","https://openalex.org/W3098557217","https://openalex.org/W3118753411","https://openalex.org/W3160799772","https://openalex.org/W3163568691","https://openalex.org/W3163793923","https://openalex.org/W3170751106","https://openalex.org/W3181854487","https://openalex.org/W3196667132","https://openalex.org/W3197580070","https://openalex.org/W3202278141","https://openalex.org/W3209984917","https://openalex.org/W4224927653","https://openalex.org/W4225956675","https://openalex.org/W4226320669","https://openalex.org/W4235201968","https://openalex.org/W4280572880","https://openalex.org/W4287889585","https://openalex.org/W4297841773","https://openalex.org/W4311000453","https://openalex.org/W4372262501","https://openalex.org/W4372346850","https://openalex.org/W6628615481","https://openalex.org/W6781547035","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6802142237","https://openalex.org/W6838843145","https://openalex.org/W6839738141","https://openalex.org/W6840412704","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W4387098302","https://openalex.org/W2626699140","https://openalex.org/W3165080709","https://openalex.org/W2948317131","https://openalex.org/W4288365855","https://openalex.org/W2327130486"],"abstract_inverted_index":{"We":[0,133],"present":[1],"the":[2,6,44,46,100,115,130],"latest":[3],"iteration":[4],"of":[5,151],"voice":[7,22,39],"conversion":[8,23,40],"challenge":[9,45,66],"(VCC)":[10],"series,":[11],"a":[12,28,83,109,155],"bi-annual":[13],"scientific":[14],"event":[15],"aiming":[16],"to":[17,37,107,142],"compare":[18],"and":[19,62,72,146],"understand":[20],"different":[21],"(VC)":[24],"systems":[25],"based":[26],"on":[27],"common":[29],"dataset.":[30],"This":[31],"year":[32],"we":[33,75,88],"shifted":[34],"our":[35],"focus":[36],"singing":[38],"(SVC),":[41],"thus":[42],"named":[43],"Singing":[47],"Voice":[48],"Conversion":[49],"Challenge":[50],"(SVCC).":[51],"A":[52],"new":[53],"database":[54],"was":[55,67,97,105],"constructed":[56],"for":[57,69,91],"two":[58,70],"tasks,":[59,93],"namely":[60],"in-domain":[61,126],"cross-domain":[63,121],"SVC.":[64],"The":[65],"run":[68],"months,":[71],"in":[73,129],"total":[74],"received":[76],"26":[77],"submissions,":[78],"including":[79],"2":[80],"baselines.":[81],"Through":[82],"large-scale":[84],"crowd-sourced":[85],"listening":[86],"test,":[87],"observed":[89],"that":[90,148],"both":[92],"although":[94],"human-level":[95],"naturalness":[96],"achieved":[98],"by":[99],"top":[101],"system,":[102],"no":[103],"team":[104],"able":[106,141],"obtain":[108],"similarity":[110,131],"score":[111],"as":[112,114,119],"high":[113],"target":[116],"speakers.":[117],"Also,":[118],"expected,":[120],"SVC":[122],"is":[123],"harder":[124],"than":[125],"SVC,":[127],"especially":[128],"aspect.":[132],"also":[134],"investigated":[135],"whether":[136],"existing":[137],"objective":[138],"measurements":[139],"were":[140],"predict":[143],"perceptual":[144],"performance,":[145],"found":[147],"only":[149],"few":[150],"them":[152],"could":[153],"reach":[154],"significant":[156],"correlation.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}