{"id":"https://openalex.org/W4416582474","doi":"https://doi.org/10.1109/lsp.2025.3636446","title":"Content-Aware Style Augmentation for Zero-Shot Voice Conversion With Short Target Speech","display_name":"Content-Aware Style Augmentation for Zero-Shot Voice Conversion With Short Target Speech","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4416582474","doi":"https://doi.org/10.1109/lsp.2025.3636446"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3636446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3636446","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":null,"display_name":"Hyeonjin Cha","orcid":"https://orcid.org/0009-0002-6374-2493"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonjin Cha","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0002-6374-2493","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074612173","display_name":"Seyun Um","orcid":"https://orcid.org/0000-0002-2229-6741"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seyun Um","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-2229-6741","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066878875","display_name":"Miseul Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Miseul Kim","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-2401-0495","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645544","display_name":"Changhwan Kim","orcid":"https://orcid.org/0000-0002-0626-730X"},"institutions":[{"id":"https://openalex.org/I1284277383","display_name":"Kia Motors (South Korea)","ror":"https://ror.org/05rv8ev82","country_code":"KR","type":"company","lineage":["https://openalex.org/I1284277383"]},{"id":"https://openalex.org/I49946491","display_name":"Hyundai Motors (South Korea)","ror":"https://ror.org/016kvft77","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522","https://openalex.org/I49946491"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changhwan Kim","raw_affiliation_strings":["Hyundai Motors Corporation, Seoul, South Korea","Hyundai Motors Corp, Seoul, South Korean"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hyundai Motors Corporation, Seoul, South Korea","institution_ids":["https://openalex.org/I1284277383","https://openalex.org/I49946491"]},{"raw_affiliation_string":"Hyundai Motors Corp, Seoul, South Korean","institution_ids":["https://openalex.org/I1284277383","https://openalex.org/I49946491"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082844687","display_name":"Seungshin Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I1284277383","display_name":"Kia Motors (South Korea)","ror":"https://ror.org/05rv8ev82","country_code":"KR","type":"company","lineage":["https://openalex.org/I1284277383"]},{"id":"https://openalex.org/I49946491","display_name":"Hyundai Motors (South Korea)","ror":"https://ror.org/016kvft77","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522","https://openalex.org/I49946491"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungshin Lee","raw_affiliation_strings":["Hyundai Motors Corporation, Seoul, South Korea","Hyundai Motors Corp, Seoul, South Korean"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hyundai Motors Corporation, Seoul, South Korea","institution_ids":["https://openalex.org/I1284277383","https://openalex.org/I49946491"]},{"raw_affiliation_string":"Hyundai Motors Corp, Seoul, South Korean","institution_ids":["https://openalex.org/I1284277383","https://openalex.org/I49946491"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6554-0783","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2699,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86586947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"33","issue":null,"first_page":"66","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.902899980545044,"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":0.902899980545044,"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/T10863","display_name":"Voice and Speech Disorders","score":0.039000000804662704,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.026399999856948853,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6870999932289124},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5855000019073486},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5041999816894531},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4927999973297119},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4909000098705292},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46050000190734863},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43619999289512634},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43619999289512634},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.38609999418258667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717000246047974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7562999725341797},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6870999932289124},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5041999816894531},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4927999973297119},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4909000098705292},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43619999289512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3747999966144562},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2840999960899353}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3636446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3636446","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1608166496","https://openalex.org/W2576309025","https://openalex.org/W3024869864","https://openalex.org/W3043140951","https://openalex.org/W3140429000","https://openalex.org/W3161695192","https://openalex.org/W3163568691","https://openalex.org/W3197659778","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W4225264140","https://openalex.org/W4225276642","https://openalex.org/W4225304461","https://openalex.org/W4225956675","https://openalex.org/W4297841574","https://openalex.org/W4322629454","https://openalex.org/W4372260053","https://openalex.org/W4385245566","https://openalex.org/W4385823264","https://openalex.org/W4385823432","https://openalex.org/W4392903591","https://openalex.org/W4393156634","https://openalex.org/W4401358097","https://openalex.org/W4401980889","https://openalex.org/W4402111360","https://openalex.org/W4402111617","https://openalex.org/W4408345987","https://openalex.org/W4409363098"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,63,88],"letter,":[2],"we":[3,90],"propose":[4],"a":[5,23,54,92],"neural":[6,30],"zero-shot":[7],"voice":[8],"conversion":[9],"(ZS-VC)":[10],"system":[11],"that":[12,81,94,111],"simultaneously":[13],"achieves":[14],"high":[15,45],"speaker":[16,39],"similarity":[17,40],"and":[18],"speech":[19,42,57,76],"intelligibility":[20],"by":[21],"incorporating":[22],"content-aware":[24],"style":[25,99],"generation":[26],"module.":[27],"Although":[28],"recent":[29],"ZS-VC":[31],"systems":[32],"have":[33],"shown":[34],"strong":[35],"performance":[36,46],"in":[37,47,126],"either":[38],"or":[41],"intelligibility,":[43],"attaining":[44],"both":[48,127],"remains":[49],"challenging,":[50],"especially":[51],"when":[52,115],"only":[53],"short":[55],"target":[56,75,97],"sample":[58],"is":[59],"available.":[60],"We":[61],"attribute":[62],"limitation":[64],"to":[65,78],"the":[66,70,74,83,96,112,118],"insufficient":[67],"content":[68,72,103],"problem\u2014where":[69],"linguistic":[71],"of":[73,82],"fails":[77],"fully":[79],"cover":[80],"source":[84],"speech.":[85],"To":[86],"address":[87],"issue,":[89],"introduce":[91],"method":[93],"augments":[95],"speaker's":[98],"features":[100],"for":[101],"underrepresented":[102],"using":[104],"self-supervised":[105],"feature":[106,119],"generation.":[107],"Experimental":[108],"results":[109],"demonstrate":[110],"proposed":[113],"system,":[114],"integrated":[116],"with":[117],"matching-based":[120],"approach":[121],"kNN-VC,":[122],"outperforms":[123],"existing":[124],"methods":[125],"key":[128],"metrics.":[129],"Demo":[130],"samples":[131],"are":[132],"available":[133],"at":[134],"https://hyeonjincha.github.io/.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-25T00:00:00"}