{"id":"https://openalex.org/W3197763626","doi":"https://doi.org/10.21437/interspeech.2021-1356","title":"S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations","display_name":"S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197763626","doi":"https://doi.org/10.21437/interspeech.2021-1356","mag":"3197763626"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1356","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5084818946","display_name":"Jheng-Hao Lin","orcid":null},"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":"Jheng-hao Lin","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047521320","display_name":"Yist Y. Lin","orcid":"https://orcid.org/0009-0000-9054-1596"},"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":"Yist Y. Lin","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072923563","display_name":"Chung-Ming Chien","orcid":null},"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":"Chung-Ming Chien","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","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":true,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040508737"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":5.3199,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.9633177,"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":"836","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9898999929428101,"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":0.9696000218391418,"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/computer-science","display_name":"Computer science","score":0.7299371361732483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5864918231964111},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46606236696243286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.457872599363327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299371361732483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5864918231964111},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46606236696243286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.457872599363327}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1356","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"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":27,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W2518172956","https://openalex.org/W2785325870","https://openalex.org/W2808706139","https://openalex.org/W2888922217","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2945478979","https://openalex.org/W2954386831","https://openalex.org/W2972394484","https://openalex.org/W2972659941","https://openalex.org/W2972943112","https://openalex.org/W2982223350","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3082130377","https://openalex.org/W3096524539","https://openalex.org/W3096864844","https://openalex.org/W3096918678","https://openalex.org/W3097777922","https://openalex.org/W3127686677","https://openalex.org/W3143523927","https://openalex.org/W3161627112","https://openalex.org/W3161695192","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Any-to-any":[0],"voice":[1],"conversion":[2],"(VC)":[3],"aims":[4],"to":[5,13,39,52,62,79,95,127,135],"convert":[6],"the":[7,41,47,64,97,118],"timbre":[8],"of":[9,46],"utterances":[10],"from":[11,101],"and":[12,30,32,36,43,55,58,66,83,114,130,150,163],"any":[14],"speakers":[15],"seen":[16],"or":[17],"unseen":[18],"during":[19],"training.Various":[20],"any-to-any":[21],"VC":[22,119,134],"approaches":[23],"have":[24,177],"been":[25],"proposed":[26,105],"like":[27,88],"AUTOVC,":[28],"AdaINVC,":[29],"FragmentVC.AUTOVC,":[31],"AdaINVC":[33],"utilize":[34],"source":[35,54,65,113,162,171],"target":[37,56,67,115,164],"encoders":[38,51],"disentangle":[40],"content":[42,99,137],"speaker":[44,81],"information":[45,57],"features.Frag-mentVC":[48],"utilizes":[49,108],"two":[50],"encode":[53],"adopts":[59],"cross":[60],"attention":[61],"align":[63],"features":[68,74,87,110,116,165,176],"with":[69],"similar":[70],"phonetic":[71,98],"content.Moreover,":[72],"pretrained":[73],"are":[75],"adopted.AUTOVC":[76],"used":[77,92,132],"d-vector":[78],"extract":[80,96,136],"information,":[82,138],"self-supervised":[84],"learning":[85],"(SSL)":[86],"wav2vec":[89],"2.0":[90],"is":[91,125,139],"in":[93,133,180],"FragmentVC":[94],"information.Different":[100],"previous":[102],"works,":[103],"we":[104],"S2VC":[106],"that":[107,167,174],"Self-Supervised":[109],"as":[111,141,160,170],"both":[112,153,161],"for":[117,145],"model.Supervised":[120],"phoneme":[121],"posteriorgram":[122],"(PPG),":[123],"which":[124],"believed":[126],"be":[128],"speaker-independent":[129],"widely":[131],"chosen":[140],"a":[142],"strong":[143],"baseline":[144],"SSL":[146,157,175],"features.The":[147],"objective":[148],"evaluation":[149,152],"subjective":[151],"show":[154],"models":[155],"taking":[156,168],"feature":[158],"CPC":[159],"outperforms":[166],"PPG":[169],"feature,":[172],"suggesting":[173],"great":[178],"potential":[179],"improving":[181],"VC.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}