{"id":"https://openalex.org/W3094723376","doi":"https://doi.org/10.1109/access.2020.3034253","title":"One-Shot Voice Conversion Algorithm Based on Representations Separation","display_name":"One-Shot Voice Conversion Algorithm Based on Representations Separation","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3094723376","doi":"https://doi.org/10.1109/access.2020.3034253","mag":"3094723376"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3034253","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3034253","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09240913.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09240913.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101691370","display_name":"Chunhui Deng","orcid":"https://orcid.org/0000-0001-8297-9934"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chunhui Deng","raw_affiliation_strings":["School of Computer Engineering, Guangzhou College, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Guangzhou College, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383094","display_name":"Ying Chen","orcid":"https://orcid.org/0000-0002-9325-2543"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056693481","display_name":"Huifang Deng","orcid":"https://orcid.org/0000-0001-6394-4496"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifang Deng","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101691370"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2651,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63951191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"196578","last_page":"196586"},"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":0.9972000122070312,"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":0.9908000230789185,"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":0.79364013671875},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7447078227996826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.738220751285553},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6803698539733887},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5673149228096008},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5533549189567566},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.47866782546043396},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4765494465827942},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45734119415283203},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4159048795700073},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3929206430912018},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3262813091278076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79364013671875},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7447078227996826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.738220751285553},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6803698539733887},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5673149228096008},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5533549189567566},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.47866782546043396},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4765494465827942},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45734119415283203},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4159048795700073},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3929206430912018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3262813091278076},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3034253","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3034253","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09240913.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:58def36bec43484587972d6de4d26b1c","is_oa":true,"landing_page_url":"https://doaj.org/article/58def36bec43484587972d6de4d26b1c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 196578-196586 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3034253","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3034253","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09240913.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1521441577","display_name":null,"funder_award_id":"2015KTSCX183","funder_id":"https://openalex.org/F4320326279","funder_display_name":"Department of Education of Guangdong Province"},{"id":"https://openalex.org/G7564191759","display_name":null,"funder_award_id":"x2js-F8150310","funder_id":"https://openalex.org/F4320323059","funder_display_name":"South China University of Technology"}],"funders":[{"id":"https://openalex.org/F4320323059","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50"},{"id":"https://openalex.org/F4320326279","display_name":"Department of Education of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094723376.pdf","grobid_xml":"https://content.openalex.org/works/W3094723376.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W196920580","https://openalex.org/W1494198834","https://openalex.org/W1523372075","https://openalex.org/W1592940279","https://openalex.org/W1973685422","https://openalex.org/W2035962301","https://openalex.org/W2136166660","https://openalex.org/W2151262064","https://openalex.org/W2187089797","https://openalex.org/W2362406295","https://openalex.org/W2406026380","https://openalex.org/W2519091744","https://openalex.org/W2608338293","https://openalex.org/W2726515241","https://openalex.org/W2774848319","https://openalex.org/W2808706139","https://openalex.org/W2889329491","https://openalex.org/W2897353073","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2949382160","https://openalex.org/W2962788625","https://openalex.org/W2962896155","https://openalex.org/W2963432880","https://openalex.org/W2963539064","https://openalex.org/W2963830550","https://openalex.org/W3099078140","https://openalex.org/W6608098027","https://openalex.org/W6631309588","https://openalex.org/W6635329185","https://openalex.org/W6713268904","https://openalex.org/W6746801104","https://openalex.org/W6752888775","https://openalex.org/W6762533536"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W3141593045","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Voice":[0],"Conversion":[1],"(VC)":[2],"is":[3,67,89,120,210,246,258],"a":[4,38,48,103,123,127,144,162],"method":[5,257,271],"of":[6,41,62,86,107,122,137,155,234,240,277],"converting":[7],"the":[8,13,19,29,50,57,63,71,76,82,115,134,138,151,156,168,172,177,185,202,213,231,241,268,275,278,283,293],"source":[9,20,72,139],"speaker's":[10,15,21,243],"speech":[11,16,22,74],"into":[12],"target":[14,77,152,157,242],"without":[17],"changing":[18],"content.":[23],"The":[24,118,130,147,165,207],"current":[25,64],"VC":[26,105],"methods":[27],"have":[28],"following":[30],"problems:":[31],"(1)":[32],"they":[33],"are":[34,53],"only":[35],"applicable":[36],"to":[37,44,94,175,220,226],"limited":[39],"number":[40],"speakers,":[42,46],"not":[43,68],"any":[45],"as":[47,212],"result,":[49],"application":[51],"scenarios":[52],"greatly":[54],"restricted;":[55],"(2)":[56],"representation":[58,170,174,239],"(feature)":[59],"separation(RS)":[60],"effect":[61],"mainstream":[65],"technology":[66],"ideal":[69],"on":[70],"speaker":[73,78,128,140,148,153,158,163,173,187,203,214,217,238,285],"and":[75,80,91,126,142,160,171,230,245,250,290],"speech;":[79],"(3)":[81],"voice":[83,141,159],"conversion":[84],"quality":[85,276],"most":[87],"models":[88],"unsatisfactory,":[90],"hence":[92],"needs":[93,219],"be":[95,221],"improved.":[96],"Therefore,":[97],"in":[98,223,296],"this":[99,181],"paper,":[100,182],"we":[101,183],"constructed":[102],"one-shot":[104],"model":[106,189,208,228,233],"Representation":[108],"Separation,":[109],"called":[110],"RS-VC":[111,227,252,263,291],"model,":[112,287],"implemented":[113],"by":[114,200],"encoder-decoder":[116],"structure.":[117],"encoder":[119,125,132,149,218],"composed":[121],"content":[124,131,135,145,169],"encoder.":[129,215],"separates":[133,150],"information":[136,154],"generates":[143,161],"representation.":[146,164],"decoder":[166],"synthesizes":[167],"generate":[176],"converted":[178,279],"voice.":[179,280],"In":[180],"obtained":[184],"optimized":[186],"verification":[188,204,286],"SVIGEN2E":[190,209],"(Speaker":[191],"Verification":[192],"with":[193,282],"Instance":[194],"Normalization":[195],"using":[196],"Generalized":[197],"End-to-End":[198],"loss)":[199],"improving":[201],"(SV)":[205],"model.":[206,253,264],"used":[211,247],"This":[216],"trained":[222],"advance":[224],"prior":[225],"training,":[229],"pre-trained":[232],"SVINGE2E":[235,289],"directly":[236],"extracts":[237],"voice,":[244],"for":[248,261],"training":[249,256,262,270],"testing":[251],"A":[254],"progressive":[255,269],"proposed":[259],"then":[260],"Experiments":[265],"show":[266],"that":[267],"can":[272],"effectively":[273],"improve":[274],"Compared":[281],"basic":[284],"both":[288],"deliver":[292],"impressive":[294],"improvements":[295],"EER":[297],"(Equal":[298],"Error":[299],"Rate).":[300]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
