{"id":"https://openalex.org/W4401980889","doi":"https://doi.org/10.1109/taslp.2024.3439996","title":"RefXVC: Cross-Lingual Voice Conversion With Enhanced Reference Leveraging","display_name":"RefXVC: Cross-Lingual Voice Conversion With Enhanced Reference Leveraging","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401980889","doi":"https://doi.org/10.1109/taslp.2024.3439996"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3439996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3439996","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language 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/A5070281927","display_name":"Mingyang Zhang","orcid":"https://orcid.org/0000-0002-7945-0535"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Zhang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7945-0535","affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846956","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0002-8520-8227"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075486968","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0002-3665-700X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["Speech & Audio team, ByteDance AI Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech & Audio team, ByteDance AI Lab, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0003-4449-1174"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Speech & Audio team, ByteDance AI Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4449-1174","affiliations":[{"raw_affiliation_string":"Speech & Audio team, ByteDance AI Lab, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446849","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0002-6096-9943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["Speech & Audio team, ByteDance AI Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech & Audio team, ByteDance AI Lab, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9675,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87783045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"4146","last_page":"4156"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9933000206947327,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9922000169754028,"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":0.5889694690704346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4117175340652466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5889694690704346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4117175340652466}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3439996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3439996","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2258073437","display_name":null,"funder_award_id":"B10120210117-KP02","funder_id":"https://openalex.org/F3953416623","funder_display_name":"Chinese University of Hong Kong, Shenzhen"},{"id":"https://openalex.org/G2799040894","display_name":null,"funder_award_id":"62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F3953416623","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W152891837","https://openalex.org/W1535240601","https://openalex.org/W1995193944","https://openalex.org/W2046056978","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2130290868","https://openalex.org/W2167127461","https://openalex.org/W2171019095","https://openalex.org/W2187089797","https://openalex.org/W2288577906","https://openalex.org/W2518172956","https://openalex.org/W2890964092","https://openalex.org/W2932022923","https://openalex.org/W2937579788","https://openalex.org/W2938583109","https://openalex.org/W2948978827","https://openalex.org/W2962788625","https://openalex.org/W2962883485","https://openalex.org/W2962896155","https://openalex.org/W2972374322","https://openalex.org/W2972659941","https://openalex.org/W2990413709","https://openalex.org/W3002433751","https://openalex.org/W3008297462","https://openalex.org/W3015213852","https://openalex.org/W3015434413","https://openalex.org/W3015805741","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3016250102","https://openalex.org/W3024869864","https://openalex.org/W3034781633","https://openalex.org/W3090474612","https://openalex.org/W3094785744","https://openalex.org/W3095012670","https://openalex.org/W3096831136","https://openalex.org/W3097001834","https://openalex.org/W3097152652","https://openalex.org/W3100378519","https://openalex.org/W3154451338","https://openalex.org/W3160799772","https://openalex.org/W3163475957","https://openalex.org/W3204116061","https://openalex.org/W3207300132","https://openalex.org/W3209059054","https://openalex.org/W3211224152","https://openalex.org/W3211358952","https://openalex.org/W4210834095","https://openalex.org/W4221155333","https://openalex.org/W4287854499","https://openalex.org/W4297808394","https://openalex.org/W4313679638","https://openalex.org/W4367281575","https://openalex.org/W4372260053","https://openalex.org/W4385823264","https://openalex.org/W4388296047","https://openalex.org/W4391021367","https://openalex.org/W6739901393","https://openalex.org/W6743229011","https://openalex.org/W6745697700","https://openalex.org/W6752888775","https://openalex.org/W6754221396","https://openalex.org/W6760861152","https://openalex.org/W6762533536","https://openalex.org/W6768021236","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6795807602","https://openalex.org/W6803378298","https://openalex.org/W6809623261","https://openalex.org/W6844194202","https://openalex.org/W6846936884","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6936113694","https://openalex.org/W7019176487"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"RefXVC,":[3],"a":[4,71,85,89,109,123],"method":[5,52,128],"for":[6,37],"cross-lingual":[7,149],"voice":[8,150],"conversion":[9,17],"(XVC)":[10],"that":[11,43,99],"leverages":[12],"reference":[13,146],"information":[14,147],"to":[15,28,60,117],"improve":[16],"performance.":[18],"Previous":[19],"XVC":[20],"works":[21],"generally":[22],"take":[23],"an":[24],"average":[25],"speaker":[26,31,58,139],"embedding":[27],"condition":[29],"the":[30,38,62,100,120,142],"identity,":[32],"which":[33],"does":[34],"not":[35,105],"account":[36],"changing":[39],"timbre":[40,63,74,86],"of":[41,122,134,144],"speech":[42,66,136],"occurs":[44],"with":[45],"different":[46,78],"pronunciations.":[47],"To":[48],"address":[49],"this,":[50],"our":[51,94],"uses":[53],"both":[54,135],"global":[55],"and":[56,75,80,88,111,138],"local":[57],"embeddings":[59],"capture":[61,119],"changes":[64],"during":[65],"conversion.":[67,151],"Additionally,":[68],"we":[69,97,113],"observed":[70],"connection":[72],"between":[73],"pronunciation":[76,90],"in":[77,102,108,132,148],"languages":[79],"utilized":[81],"this":[82],"by":[83],"incorporating":[84],"encoder":[87],"matching":[91],"network":[92],"into":[93],"model.":[95],"Furthermore,":[96],"found":[98],"variation":[101],"tones":[103],"is":[104],"adequately":[106],"reflected":[107],"sentence,":[110],"therefore,":[112],"used":[114],"multiple":[115],"references":[116],"better":[118],"range":[121],"speaker's":[124],"voice.":[125],"The":[126],"proposed":[127],"outperformed":[129],"existing":[130],"systems":[131],"terms":[133],"quality":[137],"similarity,":[140],"highlighting":[141],"effectiveness":[143],"leveraging":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}