{"id":"https://openalex.org/W4391021548","doi":"https://doi.org/10.1109/asru57964.2023.10389779","title":"A Comparative Study of Voice Conversion Models With Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023","display_name":"A Comparative Study of Voice Conversion Models With Large-Scale Speech and Singing Data: The T13 Systems for the Singing Voice Conversion Challenge 2023","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021548","doi":"https://doi.org/10.1109/asru57964.2023.10389779"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389779","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":"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/A5100669485","display_name":"Ryuichi Yamamoto","orcid":"https://orcid.org/0000-0003-0299-5470"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]},{"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":"Ryuichi Yamamoto","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan","LINE Corp., Japan"],"raw_orcid":null,"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"]},{"raw_affiliation_string":"LINE Corp., Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066881979","display_name":"Reo Yoneyama","orcid":"https://orcid.org/0000-0001-9686-4783"},"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":"Reo Yoneyama","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"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"],"raw_orcid":null,"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/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":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"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":"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"],"raw_orcid":null,"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":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9944999814033508,"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":0.9944999814033508,"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":0.9366098642349243},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6906057596206665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6816102266311646},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4680836796760559},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20565849542617798},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0546720027923584}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9366098642349243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6906057596206665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6816102266311646},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4680836796760559},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20565849542617798},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0546720027923584},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389779","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2067709094","https://openalex.org/W2519648275","https://openalex.org/W2747070883","https://openalex.org/W2765486990","https://openalex.org/W2921857201","https://openalex.org/W2963035245","https://openalex.org/W2972359262","https://openalex.org/W3041870963","https://openalex.org/W3095948607","https://openalex.org/W3158762648","https://openalex.org/W3159302906","https://openalex.org/W3170751106","https://openalex.org/W3181854487","https://openalex.org/W3205154814","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4225956675","https://openalex.org/W4226320669","https://openalex.org/W4285345683","https://openalex.org/W4287889585","https://openalex.org/W4296068763","https://openalex.org/W4297841714","https://openalex.org/W4320459320","https://openalex.org/W4372262501","https://openalex.org/W4372338328","https://openalex.org/W4382322852","https://openalex.org/W6631190155","https://openalex.org/W6745289305","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6757817989","https://openalex.org/W6772925044","https://openalex.org/W6779090866","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6790220310","https://openalex.org/W6803547063","https://openalex.org/W6838843145","https://openalex.org/W6839738141","https://openalex.org/W6840412704","https://openalex.org/W6840815571","https://openalex.org/W6846936884","https://openalex.org/W6847363464","https://openalex.org/W6849956205","https://openalex.org/W6854646373","https://openalex.org/W6936113694"],"related_works":["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","https://openalex.org/W1501596003"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3,104,126],"systems":[4],"(denoted":[5],"as":[6],"T13)":[7],"for":[8,57,85,113,141],"the":[9,83,114,122],"singing":[10,22,78],"voice":[11,23,66],"conversion":[12,24,67],"challenge":[13],"(SVCC)":[14],"2023.":[15],"For":[16],"both":[17],"in-domain":[18],"and":[19,29,77,92,110],"cross-domain":[20,116,142],"English":[21],"(SVC)":[25],"tasks":[26],"(Task":[27,118],"1":[28,91],"Task":[30,90,93],"2),":[31,119],"we":[32,60,81],"adopt":[33],"a":[34,46,63],"recognition-synthesis":[35],"approach":[36],"with":[37,45],"self-supervised":[38],"learning-based":[39],"representation.":[40],"To":[41],"achieve":[42],"data-efficient":[43],"SVC":[44,117],"limited":[47],"amount":[48],"of":[49,75,89,125],"target":[50,87],"singer/speaker\u2019s":[51],"data":[52],"(150":[53],"to":[54],"160":[55],"utterances":[56],"SVCC":[58,100],"2023),":[59],"first":[61],"train":[62],"diffusion-based":[64],"any-to-any":[65],"model":[68,84],"using":[69,135],"publicly":[70],"available":[71],"large-scale":[72],"750":[73],"hours":[74],"speech":[76],"data.":[79],"Then,":[80],"fine-tune":[82],"each":[86],"singer/speaker":[88],"2.":[94],"Large-scale":[95],"listening":[96],"tests":[97],"conducted":[98],"by":[99],"2023":[101],"show":[102,133],"that":[103,134],"T13":[105],"system":[106],"achieves":[107],"competitive":[108],"naturalness":[109],"speaker":[111],"similarity":[112],"harder":[115],"which":[120],"implies":[121],"generalization":[123],"ability":[124],"proposed":[127],"method.":[128],"Our":[129],"objective":[130],"evaluation":[131],"results":[132],"large":[136],"datasets":[137],"is":[138],"particularly":[139],"beneficial":[140],"SVC.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}