{"id":"https://openalex.org/W4408354890","doi":"https://doi.org/10.1109/icassp49660.2025.10889083","title":"Voice Conversion for Low-Resource Languages via Knowledge Transfer and Domain-Adversarial Training","display_name":"Voice Conversion for Low-Resource Languages via Knowledge Transfer and Domain-Adversarial Training","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354890","doi":"https://doi.org/10.1109/icassp49660.2025.10889083"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5054031088","display_name":"Huu Tuong Tu","orcid":"https://orcid.org/0000-0002-9820-1972"},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Huu Tuong Tu","raw_affiliation_strings":["VNPT AI, VNPT Group,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"VNPT AI, VNPT Group,Hanoi,Vietnam","institution_ids":["https://openalex.org/I4210095603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109648394","display_name":"Le Phuong Long","orcid":"https://orcid.org/0009-0008-2518-1043"},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Luong Thanh Long","raw_affiliation_strings":["VNPT AI, VNPT Group,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"VNPT AI, VNPT Group,Hanoi,Vietnam","institution_ids":["https://openalex.org/I4210095603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031373265","display_name":"Vu Phan Huan","orcid":null},"institutions":[{"id":"https://openalex.org/I138622004","display_name":"National Economics University","ror":"https://ror.org/021xbwv17","country_code":"VN","type":"education","lineage":["https://openalex.org/I138622004"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Vu Huan","raw_affiliation_strings":["National Economics University,Business AI Lab, College of Technology,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"National Economics University,Business AI Lab, College of Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I138622004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061450774","display_name":"Nguyen Thi Phuong Thao","orcid":"https://orcid.org/0000-0001-5742-8727"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Thi Phuong Thao","raw_affiliation_strings":["Hanoi University of Science and Technology,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nguyen Van Thang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Van Thang","raw_affiliation_strings":["VNPT AI, VNPT Group,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"VNPT AI, VNPT Group,Hanoi,Vietnam","institution_ids":["https://openalex.org/I4210095603"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072673139","display_name":"Nguy\u1ec5n Ti\u1ebfn C\u01b0\u1eddng","orcid":"https://orcid.org/0000-0003-4039-529X"},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Tien Cuong","raw_affiliation_strings":["VNPT AI, VNPT Group,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"VNPT AI, VNPT Group,Hanoi,Vietnam","institution_ids":["https://openalex.org/I4210095603"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101435787","display_name":"Nguy\u1ec5n Th\u1ecb Thu Trang","orcid":"https://orcid.org/0000-0002-5015-082X"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Nguyen Thi Thu Trang","raw_affiliation_strings":["Hanoi University of Science and Technology,Hanoi,Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,Hanoi,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5054031088"],"corresponding_institution_ids":["https://openalex.org/I4210095603"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01834382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9768000245094299,"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":0.9052000045776367,"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/adversarial-system","display_name":"Adversarial system","score":0.8103379607200623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7762317657470703},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5272649526596069},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5047186613082886},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.4987056255340576},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.48031753301620483},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4761652648448944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4024304151535034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3926442861557007},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.372183620929718},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.26645416021347046},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13852789998054504}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8103379607200623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762317657470703},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5272649526596069},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5047186613082886},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.4987056255340576},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.48031753301620483},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4761652648448944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4024304151535034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3926442861557007},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.372183620929718},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.26645416021347046},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13852789998054504},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889083","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2518172956","https://openalex.org/W2593414223","https://openalex.org/W2794506738","https://openalex.org/W2937020545","https://openalex.org/W2963830550","https://openalex.org/W3015434413","https://openalex.org/W3096524539","https://openalex.org/W3162414783","https://openalex.org/W3163475957","https://openalex.org/W3197659778","https://openalex.org/W3205878676","https://openalex.org/W3209984917","https://openalex.org/W4205582447","https://openalex.org/W4372260053","https://openalex.org/W4375869015","https://openalex.org/W4385823432","https://openalex.org/W4388181563","https://openalex.org/W4393156634","https://openalex.org/W6687506355","https://openalex.org/W6748150159","https://openalex.org/W6762987126","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,44],"(VC)":[2,45],"aims":[3],"to":[4,11,95],"transform":[5],"speech":[6,60],"from":[7,57,98,121],"a":[8,12,66,83],"source":[9,59,78],"speaker":[10,14,33,55,122,152],"target":[13],"while":[15,61],"preserving":[16,62],"the":[17,58,77,102,117,125,135,141],"original":[18],"linguistic":[19,63],"content.":[20],"However,":[21],"existing":[22,145],"VC":[23,86],"models":[24,46],"typically":[25],"require":[26],"large":[27],"annotated":[28,52,128],"datasets":[29],"containing":[30],"transcripts":[31],"and":[32,131,151],"labels,":[34],"posing":[35],"significant":[36,67],"challenges":[37],"for":[38,101,127],"low-resource":[39,85,105,136,155],"languages.":[40,106],"In":[41],"any-to-any":[42],"voice":[43],"that":[47,73,88,140],"do":[48],"not":[49],"rely":[50],"on":[51,134],"datasets,":[53],"disentangling":[54],"information":[56,97],"content":[64,120],"remains":[65],"challenge,":[68],"often":[69],"resulting":[70],"in":[71,147,154],"outputs":[72],"retain":[74],"attributes":[75],"of":[76,104,119,149],"speaker.":[79],"This":[80],"paper":[81],"introduces":[82],"novel":[84],"model":[87,143],"combines":[89],"knowledge":[90],"transfer":[91],"with":[92,113],"domain-adversarial":[93,114],"training":[94,115],"leverage":[96],"high-resource":[99],"languages":[100],"benefit":[103],"The":[107],"proposed":[108,142],"approach":[109],"utilizes":[110],"pretrained":[111],"models,":[112],"enabling":[116],"separation":[118],"identity":[123],"without":[124],"need":[126],"datasets.":[129],"Objective":[130],"subjective":[132],"evaluations":[133],"Vietnamese":[137],"language":[138],"demonstrate":[139],"outperforms":[144],"methods":[146],"terms":[148],"naturalness":[150],"similarity":[153],"scenarios.":[156],"Audio":[157],"samples":[158],"are":[159],"available":[160],"at:":[161],"https://huutuongtu.github.io/KTVC/index.html.":[162]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
