{"id":"https://openalex.org/W4375868976","doi":"https://doi.org/10.1109/icassp49357.2023.10096642","title":"TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion","display_name":"TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868976","doi":"https://doi.org/10.1109/icassp49357.2023.10096642"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5103110752","display_name":"Hyun Joon Park","orcid":"https://orcid.org/0000-0002-5308-6675"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyun Joon Park","raw_affiliation_strings":["Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101031336","display_name":"Seok Woo Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seok Woo Yang","raw_affiliation_strings":["Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046518803","display_name":"Jin Sob Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jin Sob Kim","raw_affiliation_strings":["Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001866594","display_name":"Woo-Seok Shin","orcid":"https://orcid.org/0000-0002-8475-4795"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wooseok Shin","raw_affiliation_strings":["Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024995454","display_name":"Sung Won Han","orcid":"https://orcid.org/0000-0002-0040-3542"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung Won Han","raw_affiliation_strings":["Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103110752"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":3.24,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93384101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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":0.9998999834060669,"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":0.9983999729156494,"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":0.994700014591217,"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/normalization","display_name":"Normalization (sociology)","score":0.8920513391494751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759416401386261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6275502443313599},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6038902997970581},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4125308394432068},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08014285564422607},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.059315264225006104}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8920513391494751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759416401386261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6275502443313599},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6038902997970581},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4125308394432068},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08014285564422607},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.059315264225006104},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2120605154","https://openalex.org/W2126143605","https://openalex.org/W2527729766","https://openalex.org/W2603777577","https://openalex.org/W2902070858","https://openalex.org/W2945478979","https://openalex.org/W2963371159","https://openalex.org/W2963539064","https://openalex.org/W2963609956","https://openalex.org/W2972659941","https://openalex.org/W3015338123","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3096524539","https://openalex.org/W3161627112","https://openalex.org/W3163475957","https://openalex.org/W3197659778","https://openalex.org/W3197763626","https://openalex.org/W3202267900","https://openalex.org/W3202767484","https://openalex.org/W4221146610","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6727697161","https://openalex.org/W6736996214","https://openalex.org/W6739901393","https://openalex.org/W6762533536","https://openalex.org/W6769767169","https://openalex.org/W6780218876","https://openalex.org/W6802029025","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2275988210","https://openalex.org/W2385621972","https://openalex.org/W1650162272","https://openalex.org/W2067459736","https://openalex.org/W203970584","https://openalex.org/W322646691","https://openalex.org/W2368779261","https://openalex.org/W2589098947","https://openalex.org/W2984591755","https://openalex.org/W4231964008"],"abstract_inverted_index":{"Voice":[0],"Conversion":[1],"(VC)":[2],"must":[3],"be":[4,73],"achieved":[5],"while":[6,91,133],"maintaining":[7,45],"the":[8,11,16,19,29,93,96,106,112,115,135,140],"content":[9,98,117],"of":[10,18,33,95,111,114],"source":[12,46,97,116],"speech":[13],"and":[14,35,48,65,88,118],"representing":[15],"characteristics":[17],"target":[20,49,85,119],"speaker.":[21],"The":[22,79],"existing":[23,141],"methods":[24],"do":[25],"not":[26],"simultaneously":[27],"satisfy":[28],"above":[30],"two":[31],"aspects":[32],"VC,":[34],"their":[36],"conversion":[37,90],"outputs":[38],"suffer":[39],"from":[40],"a":[41],"trade-off":[42,136],"problem":[43,137],"between":[44],"contents":[47],"characteristics.":[50],"In":[51],"this":[52],"study,":[53],"we":[54],"propose":[55],"Triple":[56],"Adaptive":[57],"Attention":[58],"Normalization":[59],"VC":[60,126,142],"(TriAAN-VC),":[61],"comprising":[62],"an":[63,66],"encoder-decoder":[64],"attention-based":[67],"adaptive":[68,81],"normalization":[69,82],"block,":[70],"that":[71,128],"can":[72],"applied":[74],"to":[75],"non-parallel":[76],"any-to-any":[77],"VC.":[78],"proposed":[80],"block":[83],"extracts":[84],"speaker":[86,120],"representations":[87],"achieves":[89,130],"minimizing":[92],"loss":[94],"with":[99],"siamese":[100],"loss.":[101],"We":[102],"evaluated":[103],"TriAAN-VC":[104,129],"on":[105],"VCTK":[107],"dataset":[108],"in":[109,139],"terms":[110],"maintenance":[113],"similarity.":[121],"Experimental":[122],"results":[123],"for":[124],"one-shot":[125],"suggest":[127],"state-of-the-art":[131],"performance":[132],"mitigating":[134],"encountered":[138],"methods.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}