{"id":"https://openalex.org/W4408356288","doi":"https://doi.org/10.1109/icassp49660.2025.10889396","title":"AdaptVC: High Quality Voice Conversion with Adaptive Learning","display_name":"AdaptVC: High Quality Voice Conversion with Adaptive Learning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356288","doi":"https://doi.org/10.1109/icassp49660.2025.10889396"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889396","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/A5101733121","display_name":"Jaehun Kim","orcid":"https://orcid.org/0000-0002-3200-0406"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaehun Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377802","display_name":"Ji\u2010Hoon Kim","orcid":"https://orcid.org/0000-0002-5212-1686"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ji-Hoon Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059450470","display_name":"Yeunju Choi","orcid":"https://orcid.org/0000-0003-2192-2680"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeunju Choi","raw_affiliation_strings":["Samsung Research,South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111922287","display_name":"Tan Dat Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tan Dat Nguyen","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021831317","display_name":"Seongkyu Mun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongkyu Mun","raw_affiliation_strings":["Samsung Research,South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Research,South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101733121"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.1366,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75753621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9729999899864197,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9625999927520752,"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":0.9550999999046326,"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":0.7127035856246948},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6509984731674194},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5514357089996338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127035856246948},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6509984731674194},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5514357089996338},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889396","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2752796333","https://openalex.org/W2962788625","https://openalex.org/W2972359262","https://openalex.org/W3015805741","https://openalex.org/W3099793224","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4225956675","https://openalex.org/W4312933868","https://openalex.org/W4319862209","https://openalex.org/W4385823432","https://openalex.org/W4392910802","https://openalex.org/W4392931276","https://openalex.org/W4393156644","https://openalex.org/W6759579507","https://openalex.org/W6762533536","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6795261426","https://openalex.org/W6795807602","https://openalex.org/W6796581206","https://openalex.org/W6802517614","https://openalex.org/W6802527329","https://openalex.org/W6803547063","https://openalex.org/W6804125026","https://openalex.org/W6805710207","https://openalex.org/W6846539466","https://openalex.org/W6846936884","https://openalex.org/W6847363464","https://openalex.org/W6858277493","https://openalex.org/W6867339092","https://openalex.org/W6936113694"],"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":{"The":[0,86],"goal":[1],"of":[2,10,18,74,115],"voice":[3,40],"conversion":[4],"is":[5,30],"to":[6,14,31,51,90,104,129,158],"transform":[7],"the":[8,24,37,43,53,100,110,132,147,159],"speech":[9,82,106,154],"a":[11,19,55,120,142],"source":[12,38],"speaker":[13,21,77,127],"sound":[15],"like":[16],"that":[17,107,146],"reference":[20,111,160],"while":[22],"preserving":[23],"original":[25],"content.":[26,116],"A":[27],"key":[28],"challenge":[29],"extract":[32],"disentangled":[33],"linguistic":[34],"content":[35,75],"from":[36,42,95],"and":[39,76,99,135,138,156],"style":[41],"reference.":[44],"While":[45],"existing":[46,151],"approaches":[47],"leverage":[48,119],"various":[49],"methods":[50],"isolate":[52],"two,":[54],"generalization":[56],"still":[57],"requires":[58],"further":[59,130],"attention,":[60],"especially":[61],"for":[62],"robustness":[63],"in":[64,141,153],"zero-shot":[65,143],"scenarios.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,118],"achieve":[71],"successful":[72],"disentanglement":[73],"features":[78,83,94],"by":[79],"tuning":[80],"self-supervised":[81,97],"with":[84,112,125],"adapters.":[85],"adapters":[87],"are":[88],"trained":[89],"dynamically":[91],"encode":[92],"nuanced":[93],"rich":[96],"features,":[98],"decoder":[101,124],"fuses":[102],"them":[103],"produce":[105],"accurately":[108],"resembles":[109],"minimal":[113],"loss":[114],"Moreover,":[117],"conditional":[121],"flow":[122],"matching":[123],"cross-attention":[126],"conditioning":[128],"boost":[131],"synthesis":[133],"quality":[134,155],"efficiency.":[136],"Subjective":[137],"objective":[139],"evaluations":[140],"scenario":[144],"demonstrate":[145],"proposed":[148],"method":[149],"outperforms":[150],"models":[152],"similarity":[157],"speech.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
