{"id":"https://openalex.org/W4287889585","doi":"https://doi.org/10.1109/jstsp.2022.3193761","title":"A Comparative Study of Self-Supervised Speech Representation Based Voice Conversion","display_name":"A Comparative Study of Self-Supervised Speech Representation Based Voice Conversion","publication_year":2022,"publication_date":"2022-07-25","ids":{"openalex":"https://openalex.org/W4287889585","doi":"https://doi.org/10.1109/jstsp.2022.3193761"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3193761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3193761","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3172-3335","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078898845","display_name":"Shu-Wen Yang","orcid":"https://orcid.org/0000-0001-5503-9410"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shu-Wen Yang","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-5503-9410","affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"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 Hayashi","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8782-4093","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, 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, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0994,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88843927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"16","issue":"6","first_page":"1308","last_page":"1318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7446705102920532},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6459240317344666},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6041432619094849},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5598811507225037},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5299079418182373},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43985143303871155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4374482035636902},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43532687425613403},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.4195294976234436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.108801931142807},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1004883348941803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446705102920532},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6459240317344666},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6041432619094849},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5598811507225037},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5299079418182373},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43985143303871155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4374482035636902},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43532687425613403},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.4195294976234436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.108801931142807},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1004883348941803},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2022.3193761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3193761","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1491700317","display_name":null,"funder_award_id":"JPNP20006","funder_id":"https://openalex.org/F4320321680","funder_display_name":"New Energy and Industrial Technology Development Organization"},{"id":"https://openalex.org/G4353531887","display_name":"Augmented speech communication using multi-modal signals with real-time, low-latency voice conversion","funder_award_id":"22KJ1519","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320321680","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W1959608418","https://openalex.org/W2022125261","https://openalex.org/W2046056978","https://openalex.org/W2048646122","https://openalex.org/W2100819376","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2124331435","https://openalex.org/W2156142001","https://openalex.org/W2187234408","https://openalex.org/W2403098732","https://openalex.org/W2471520273","https://openalex.org/W2518172956","https://openalex.org/W2532494225","https://openalex.org/W2576309025","https://openalex.org/W2595110011","https://openalex.org/W2752796333","https://openalex.org/W2786868129","https://openalex.org/W2801493797","https://openalex.org/W2808631503","https://openalex.org/W2889329491","https://openalex.org/W2897353073","https://openalex.org/W2902070858","https://openalex.org/W2903365642","https://openalex.org/W2962896155","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972374322","https://openalex.org/W2972659941","https://openalex.org/W2973049979","https://openalex.org/W2973108288","https://openalex.org/W2981087920","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W2996414377","https://openalex.org/W3015213852","https://openalex.org/W3015265920","https://openalex.org/W3015434413","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3025844872","https://openalex.org/W3041561163","https://openalex.org/W3081565196","https://openalex.org/W3083776549","https://openalex.org/W3091890228","https://openalex.org/W3092368332","https://openalex.org/W3094635600","https://openalex.org/W3097286738","https://openalex.org/W3098557217","https://openalex.org/W3099078140","https://openalex.org/W3101689408","https://openalex.org/W3140429000","https://openalex.org/W3160799772","https://openalex.org/W3161627112","https://openalex.org/W3161695192","https://openalex.org/W3197580070","https://openalex.org/W3197763626","https://openalex.org/W3198275944","https://openalex.org/W3198429080","https://openalex.org/W3198858531","https://openalex.org/W3207300132","https://openalex.org/W4210774711","https://openalex.org/W4244543785","https://openalex.org/W4247587863","https://openalex.org/W4249468441","https://openalex.org/W4285250921","https://openalex.org/W4297808394","https://openalex.org/W6640963894","https://openalex.org/W6739901393","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6795952400","https://openalex.org/W6840412704","https://openalex.org/W6844194202","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2006251942","https://openalex.org/W2364741597","https://openalex.org/W1492103595","https://openalex.org/W1864774435","https://openalex.org/W946352265","https://openalex.org/W3020787026","https://openalex.org/W2334479858","https://openalex.org/W2793786119","https://openalex.org/W1507702947","https://openalex.org/W2022062253"],"abstract_inverted_index":{"We":[0,83,96],"present":[1],"a":[2,56,102],"large-scale":[3],"comparative":[4],"study":[5],"of":[6,17,58,101,127],"self-supervised":[7],"speech":[8],"representation":[9],"(S3R)-based":[10],"voice":[11,77],"conversion":[12,78],"(VC).":[13],"In":[14],"the":[15,76,99,114,118,125,135],"context":[16],"recognition-synthesis":[18],"VC,":[19,74],"S3Rs":[20],"are":[21,38],"attractive":[22],"owing":[23],"to":[24,27],"their":[25],"potential":[26],"replace":[28],"expensive":[29],"supervised":[30],"representations":[31],"such":[32],"as":[33],"phonetic":[34],"posteriorgrams":[35],"(PPGs),":[36],"which":[37],"commonly":[39],"adopted":[40],"by":[41],"state-of-the-art":[42,121],"VC":[43,49,66,86,122,129],"systems.":[44],"Using":[45],"S3PRL-VC,":[46],"an":[47],"open-source":[48],"software":[50],"we":[51,54],"previously":[52],"developed,":[53],"provide":[55],"series":[57],"in-depth":[59],"objective":[60],"and":[61,71,94,108,130],"subjective":[62],"analyses":[63],"under":[64],"three":[65],"settings:":[67],"intra-/cross-lingual":[68],"any-to-one":[69],"(A2O)":[70],"any-to-any":[72],"(A2A)":[73],"using":[75],"challenge":[79],"2020":[80],"(VCC2020)":[81],"dataset.":[82],"investigated":[84],"S3R-based":[85,128],"in":[87,113],"various":[88],"aspects,":[89],"including":[90],"model":[91],"type,":[92],"multilinguality,":[93],"supervision.":[95],"also":[97,131],"studied":[98],"effect":[100],"post-discretization":[103],"process":[104],"with":[105,120],"k-means":[106],"clustering":[107],"showed":[109],"how":[110],"it":[111],"improves":[112],"A2A":[115],"setting.":[116],"Finally,":[117],"comparison":[119],"systems":[123],"demonstrates":[124],"competitiveness":[126],"sheds":[132],"light":[133],"on":[134],"possible":[136],"improving":[137],"directions.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-07-26T00:00:00"}