{"id":"https://openalex.org/W4415293230","doi":"https://doi.org/10.1109/tcss.2025.3603008","title":"SSL-VC: One-Shot Voice Conversion Through Self-Supervised Learning","display_name":"SSL-VC: One-Shot Voice Conversion Through Self-Supervised Learning","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W4415293230","doi":"https://doi.org/10.1109/tcss.2025.3603008"},"language":null,"primary_location":{"id":"doi:10.1109/tcss.2025.3603008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2025.3603008","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"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 Transactions on Computational Social Systems","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/A5102000320","display_name":"Chenglong Jiang","orcid":"https://orcid.org/0009-0007-3935-9482"},"institutions":[{"id":"https://openalex.org/I4210100070","display_name":"Guangzhou Mechanical Engineering Research Institute (China)","ror":"https://ror.org/0114hcc46","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210100070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Jiang","raw_affiliation_strings":["GHT Company Ltd., Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-3935-9482","affiliations":[{"raw_affiliation_string":"GHT Company Ltd., Guangzhou, China","institution_ids":["https://openalex.org/I4210100070"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linrong Pan","orcid":"https://orcid.org/0009-0007-0726-012X"},"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":"Linrong Pan","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-0726-012X","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":"middle","author":{"id":"https://openalex.org/A5101828088","display_name":"Ying Gao","orcid":"https://orcid.org/0000-0002-8925-8192"},"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 Gao","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8925-8192","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":"middle","author":{"id":"https://openalex.org/A5104282791","display_name":"Kuanghua Su","orcid":null},"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":"Kuanghua Su","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-8212-9751","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":"middle","author":{"id":null,"display_name":"Gaoze Hou","orcid":"https://orcid.org/0009-0004-5953-9163"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoze Hou","raw_affiliation_strings":["School of Environmental and Ecological Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0009-0004-5953-9163","affiliations":[{"raw_affiliation_string":"School of Environmental and Ecological Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992","https://openalex.org/I4210092944"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007941489","display_name":"Xiping Hu","orcid":"https://orcid.org/0000-0002-4952-699X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiping Hu","raw_affiliation_strings":["School of Medical Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4952-699X","affiliations":[{"raw_affiliation_string":"School of Medical Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1469678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"1","first_page":"856","last_page":"867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9898999929428101,"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":0.9898999929428101,"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/leverage","display_name":"Leverage (statistics)","score":0.5210999846458435},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4196999967098236},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4009000062942505},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.39899998903274536},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.38420000672340393},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3594000041484833},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3244999945163727},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3149999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458999752998352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6632999777793884},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4196999967098236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41339999437332153},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3046000003814697},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcss.2025.3603008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2025.3603008","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"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 Transactions on Computational Social Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1574447377","https://openalex.org/W2532494225","https://openalex.org/W2946555236","https://openalex.org/W2962788625","https://openalex.org/W2963830550","https://openalex.org/W2972659941","https://openalex.org/W2973049979","https://openalex.org/W3024869864","https://openalex.org/W3083423753","https://openalex.org/W3140429000","https://openalex.org/W3144810982","https://openalex.org/W3196475561","https://openalex.org/W3197659778","https://openalex.org/W3198104520","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226132755","https://openalex.org/W4294311176","https://openalex.org/W4296068587","https://openalex.org/W4297841714","https://openalex.org/W4319586549","https://openalex.org/W4327661848","https://openalex.org/W4372260053","https://openalex.org/W4372260509","https://openalex.org/W4372347381","https://openalex.org/W4375868962","https://openalex.org/W4385823135","https://openalex.org/W4386113956","https://openalex.org/W4389011027","https://openalex.org/W4392903591"],"related_works":[],"abstract_inverted_index":{"Currently,":[0],"the":[1,14,22,25,59,94,99,106,124,128,136,140,150,156,164,208,211],"prevailing":[2],"approach":[3,111],"in":[4,199],"voice":[5],"conversion":[6],"(VC)":[7],"involves":[8],"separating":[9],"clearer":[10],"linguistic":[11,79,117,202],"information":[12,39,80,118],"from":[13,81,93],"source":[15],"audio":[16,47],"and":[17,50,91,162,170,174,181,191],"then":[18],"reconstructing":[19],"it":[20,65,195],"with":[21,74],"identity":[23],"of":[24,89,101,120,127,159,210],"target":[26],"speaker.":[27],"However,":[28],"existing":[29],"methods,":[30,41],"whether":[31],"employing":[32],"in-formation":[33],"perturbation":[34],"techniques":[35],"or":[36],"carefully":[37],"designed":[38,84],"bottleneck":[40],"encounter":[42],"challenges":[43],"related":[44],"to":[45,77,96,114],"unsatisfactory":[46],"separation":[48],"effects":[49],"insufficient":[51],"robustness.":[52],"This":[53,110],"article":[54],"introduces":[55],"a":[56,67,153],"VC":[57,146,190],"through":[58],"self-supervised":[60,68],"learning":[61,165],"method":[62],"(SSL-VC).":[63],"First,":[64],"utilizes":[66],"speech":[69,95,183],"representation":[70],"(S-SSR)":[71],"extraction":[72],"network":[73],"decoupling":[75],"(Decp-SSEN)":[76],"disentangle":[78],"speech.":[82],"The":[83],"prosodic":[85,212],"encoder":[86],"extracts":[87],"features":[88,161],"pitch":[90],"energy":[92],"compensate":[97],"for":[98,152],"loss":[100],"nonlinguistic":[102],"details":[103],"incurred":[104],"during":[105],"Decp-SSEN":[107],"disentangling":[108],"process.":[109],"allows":[112],"us":[113],"obtain":[115],"richer":[116,201],"independent":[119],"speaker":[121,192],"identity,":[122],"guaranteeing":[123],"robust":[125],"performance":[126],"model.":[129],"Second,":[130],"we":[131],"leverage":[132],"high-level":[133],"S-SSR":[134],"as":[135],"intermediate":[137,160],"feature,":[138],"replacing":[139],"traditional":[141],"Mel-spectrogram.":[142],"Built":[143],"an":[144],"end-to-end":[145],"pipeline":[147],"that":[148,186],"eliminates":[149],"need":[151],"vocoder,":[154],"enhancing":[155],"expression":[157],"level":[158],"reducing":[163],"difficulty":[166],"gap":[167],"between":[168],"real":[169],"predicted":[171],"features.":[172],"Subjective":[173],"objective":[175],"experiments":[176,205],"conducted":[177],"on":[178],"both":[179],"seen":[180],"unseen":[182],"corpus":[184],"demonstrate":[185],"SSL-VC":[187],"achieves":[188],"high-quality":[189],"similarity.":[193],"Moreover,":[194],"outperforms":[196],"state-of-the-art":[197],"methods":[198],"extracting":[200],"information.":[203],"Ablation":[204],"further":[206],"scrutinize":[207],"indispensability":[209],"encoder.":[213]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-18T00:00:00"}