{"id":"https://openalex.org/W3163475957","doi":"https://doi.org/10.1109/icassp39728.2021.9414257","title":"Again-VC: A One-Shot Voice Conversion Using Activation Guidance and Adaptive Instance Normalization","display_name":"Again-VC: A One-Shot Voice Conversion Using Activation Guidance and Adaptive Instance Normalization","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163475957","doi":"https://doi.org/10.1109/icassp39728.2021.9414257","mag":"3163475957"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5101535357","display_name":"Yen-Hao Chen","orcid":"https://orcid.org/0000-0002-5456-8393"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yen-Hao Chen","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017182348","display_name":"Da-Yi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Da-Yi Wu","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101804850","display_name":"Tsung-Han Wu","orcid":"https://orcid.org/0000-0002-5071-0583"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsung-Han Wu","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101535357"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":11.1998,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.9871923,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5954","last_page":"5958"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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":0.7972586750984192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7867188453674316},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7306948304176331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.710008978843689},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7034993171691895},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5763424038887024},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4491262435913086},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43671610951423645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35806211829185486},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3365135192871094}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7972586750984192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867188453674316},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7306948304176331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.710008978843689},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7034993171691895},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5763424038887024},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4491262435913086},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43671610951423645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35806211829185486},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3365135192871094},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":44,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2532494225","https://openalex.org/W2603777577","https://openalex.org/W2608338293","https://openalex.org/W2752796333","https://openalex.org/W2774848319","https://openalex.org/W2889061305","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2947196194","https://openalex.org/W2949281321","https://openalex.org/W2962788625","https://openalex.org/W2962896155","https://openalex.org/W2963539064","https://openalex.org/W2963799213","https://openalex.org/W2963830550","https://openalex.org/W2964121744","https://openalex.org/W2970006822","https://openalex.org/W2970351109","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W2998572311","https://openalex.org/W3012437242","https://openalex.org/W3015434413","https://openalex.org/W3015805741","https://openalex.org/W3020570669","https://openalex.org/W3034794073","https://openalex.org/W3096524539","https://openalex.org/W3102628737","https://openalex.org/W4288337064","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6640963894","https://openalex.org/W6746801104","https://openalex.org/W6762533536","https://openalex.org/W6767111847","https://openalex.org/W6772349387","https://openalex.org/W6776390925"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2556771176"],"abstract_inverted_index":{"Recently,":[0],"voice":[1,32],"conversion":[2],"(VC)":[3],"has":[4],"been":[5],"widely":[6],"studied.":[7],"Many":[8],"VC":[9,86,138],"systems":[10],"use":[11],"disentangle-based":[12],"learning":[13],"techniques":[14],"to":[15,38],"separate":[16],"the":[17,20,31,35,41,46,52,59,63,75,119,122,126,130,141,146],"speaker":[18,36,47,127],"and":[19,91,105,125],"linguistic":[21],"content":[22,53,64,117],"information":[23,37,48,69,114],"from":[24,49],"a":[25,67,102,106,109],"speech":[26,132],"signal.":[27],"Subsequently,":[28],"they":[29],"convert":[30],"by":[33],"changing":[34],"that":[39],"of":[40,101,129,145],"target":[42],"speaker.":[43],"To":[44],"prevent":[45],"leaking":[50],"into":[51],"embeddings,":[54,118],"previous":[55],"works":[56],"either":[57],"reduce":[58],"dimension":[60],"or":[61,148],"quantize":[62],"embedding":[65],"as":[66,112],"strong":[68],"bottleneck.":[70],"These":[71],"mechanisms":[72],"somehow":[73],"hurt":[74],"synthesis":[76,123],"quality.":[77],"In":[78],"this":[79],"work,":[80],"we":[81],"propose":[82],"AGAIN-VC,":[83],"an":[84,97,113],"innovative":[85],"system":[87,139],"using":[88],"Activation":[89],"Guidance":[90],"Adaptive":[92],"Instance":[93],"Normalization.":[94],"AGAIN-VC":[95],"is":[96,133],"auto-encoder-based":[98],"model,":[99],"comprising":[100],"single":[103],"encoder":[104],"decoder.":[107],"With":[108],"proper":[110],"activation":[111],"bottleneck":[115],"on":[116],"trade-off":[120],"between":[121],"quality":[124],"similarity":[128],"converted":[131],"improved":[134],"drastically.":[135],"This":[136],"one-shot":[137],"obtains":[140],"best":[142],"performance":[143],"regardless":[144],"subjective":[147],"objective":[149],"evaluations.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":10}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}