{"id":"https://openalex.org/W3207300132","doi":"https://doi.org/10.1109/icassp43922.2022.9746430","title":"S3PRL-VC: Open-Source Voice Conversion Framework with Self-Supervised Speech Representations","display_name":"S3PRL-VC: Open-Source Voice Conversion Framework with Self-Supervised Speech Representations","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207300132","doi":"https://doi.org/10.1109/icassp43922.2022.9746430","mag":"3207300132"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746430","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/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/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,Taiwan","National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, 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,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/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"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":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","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":6,"corresponding_author_ids":["https://openalex.org/A5000377034"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":2.9226,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92478931,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6552","last_page":"6556"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.9970999956130981,"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":0.7570374011993408},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.734551191329956},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5706647634506226},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5666057467460632},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5358406901359558},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49398261308670044},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4843350648880005},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4708259403705597},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4300246238708496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40477097034454346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3811257779598236},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.19984349608421326},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10903874039649963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570374011993408},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.734551191329956},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5706647634506226},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5666057467460632},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5358406901359558},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49398261308670044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4843350648880005},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4708259403705597},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4300246238708496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40477097034454346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3811257779598236},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.19984349608421326},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10903874039649963},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746430","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2120605154","https://openalex.org/W2156142001","https://openalex.org/W2518172956","https://openalex.org/W2527729766","https://openalex.org/W2595110011","https://openalex.org/W2801493797","https://openalex.org/W2808706139","https://openalex.org/W2889329491","https://openalex.org/W2963403868","https://openalex.org/W2963432880","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3025844872","https://openalex.org/W3036601975","https://openalex.org/W3081565196","https://openalex.org/W3082130377","https://openalex.org/W3083776549","https://openalex.org/W3092028330","https://openalex.org/W3092368332","https://openalex.org/W3098403858","https://openalex.org/W3099782249","https://openalex.org/W3140429000","https://openalex.org/W3161627112","https://openalex.org/W3161695192","https://openalex.org/W3185312023","https://openalex.org/W3197580070","https://openalex.org/W3197763626","https://openalex.org/W3198275944","https://openalex.org/W4210774711","https://openalex.org/W4244543785","https://openalex.org/W4247587863","https://openalex.org/W4249468441","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6752888775","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6840412704","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"S3PRL-VC,":[3],"an":[4,80],"open-source":[5],"voice":[6],"conversion":[7],"(VC)":[8],"framework":[9],"based":[10],"on":[11,66],"the":[12,16,32,67,121,137,143,150,155],"S3PRL":[13],"toolkit.":[14],"In":[15,54],"context":[17],"of":[18,61,126],"recognition-synthesis":[19],"VC,":[20,76],"self-supervised":[21],"speech":[22],"representation":[23,35],"(S3R)":[24],"is":[25,46,114,160],"valuable":[26],"in":[27,70,97,120,124,131],"its":[28],"potential":[29],"to":[30,147],"replace":[31],"expensive":[33],"supervised":[34,100],"adopted":[36],"by":[37,64],"state-of-the-art":[38,130],"VC":[39,45,156],"systems.":[40],"Moreover,":[41],"we":[42,57,110],"claim":[43],"that":[44,112],"a":[47,59],"good":[48],"probing":[49],"task":[50],"for":[51],"S3R":[52,113,151],"analysis.":[53],"this":[55],"work,":[56],"provide":[58,86],"series":[60],"in-depth":[62],"analyses":[63],"benchmarking":[65],"two":[68],"tasks":[69],"VCC2020,":[71],"namely":[72],"intra-/cross-lingual":[73],"any-to-one":[74],"(A2O)":[75],"as":[77,79,140,142],"well":[78,141],"any-to-any":[81],"(A2A)":[82],"setting.":[83],"We":[84,135],"also":[85,94,154],"comparisons":[87],"between":[88],"not":[89,148],"only":[90,149],"different":[91],"S3Rs":[92],"but":[93,153],"top":[95,118],"systems":[96,119],"VCC2020":[98,117],"with":[99,116],"representations.":[101],"Systematic":[102],"objective":[103],"and":[104,109,128],"subjective":[105],"evaluation":[106],"were":[107],"conducted,":[108],"show":[111],"comparable":[115],"A2O":[122],"setting":[123],"terms":[125],"similarity,":[127],"achieves":[129],"S3R-based":[132],"A2A":[133],"VC.":[134],"believe":[136],"extensive":[138],"analysis,":[139],"toolkit":[144],"itself,":[145],"contribute":[146],"community":[152],"community.":[157],"The":[158],"codebase":[159],"now":[161],"open-sourced":[162],"<sup":[163],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[164],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[165],".":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}