{"id":"https://openalex.org/W4406521093","doi":"https://doi.org/10.1109/taffc.2025.3530920","title":"DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations Without Text Alignment","display_name":"DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations Without Text Alignment","publication_year":2025,"publication_date":"2025-01-17","ids":{"openalex":"https://openalex.org/W4406521093","doi":"https://doi.org/10.1109/taffc.2025.3530920"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2025.3530920","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3530920","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taffc.2025.3530920","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033088100","display_name":"Hyung-Seok Oh","orcid":"https://orcid.org/0000-0001-7229-8123"},"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"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Hyung-Seok Oh","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea","Department of Artificial Intelligence, Korea University, Seongbuk-gu, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7229-8123","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea","institution_ids":["https://openalex.org/I4210161052"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033958396","display_name":"Sang-Hoon Lee","orcid":"https://orcid.org/0000-0002-8925-4474"},"institutions":[{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]},{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Sang-Hoon Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea","Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon, South Korea","Department of Software and Computer Engineering and the Department of Artificial Intelligence, Ajou University, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8925-4474","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea","institution_ids":["https://openalex.org/I4210161052"]},{"raw_affiliation_string":"Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]},{"raw_affiliation_string":"Department of Software and Computer Engineering and the Department of Artificial Intelligence, Ajou University, South Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046627773","display_name":"Deok\u2013Hyeon Cho","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"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Deok-Hyeon Cho","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea","Department of Artificial Intelligence, Korea University, Seongbuk-gu, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-4673-9882","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea","institution_ids":["https://openalex.org/I4210161052"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2013Whan Lee","orcid":"https://orcid.org/0000-0002-6249-4996"},"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"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]},{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea","Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon, South Korea","Department of Artificial Intelligence, Korea University, Seongbuk-gu, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-6249-4996","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea","institution_ids":["https://openalex.org/I4210161052"]},{"raw_affiliation_string":"Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":{"value":2645,"currency":"USD","value_usd":2645},"fwci":14.7017,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.98685431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"16","issue":"3","first_page":"1660","last_page":"1674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9878000020980835,"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":0.9878000020980835,"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/T12031","display_name":"Speech and dialogue systems","score":0.9312000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.7446084022521973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5487551689147949},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47969433665275574},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.42663487792015076},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4172399640083313},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3982665538787842},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3841856122016907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3536328673362732},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16950061917304993},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1440727412700653}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.7446084022521973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5487551689147949},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47969433665275574},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.42663487792015076},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4172399640083313},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3982665538787842},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3841856122016907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3536328673362732},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16950061917304993},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1440727412700653}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2025.3530920","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3530920","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taffc.2025.3530920","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taffc.2025.3530920","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W2077801020","https://openalex.org/W2101105183","https://openalex.org/W2146334809","https://openalex.org/W2146879304","https://openalex.org/W2239141610","https://openalex.org/W2517513811","https://openalex.org/W2747874407","https://openalex.org/W2767118408","https://openalex.org/W2800822639","https://openalex.org/W2885820941","https://openalex.org/W2899361462","https://openalex.org/W2899877258","https://openalex.org/W2903739847","https://openalex.org/W2938833595","https://openalex.org/W2962793481","https://openalex.org/W2963300588","https://openalex.org/W2963426391","https://openalex.org/W2963539064","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W3008691130","https://openalex.org/W3015241559","https://openalex.org/W3015719316","https://openalex.org/W3015841875","https://openalex.org/W3095930733","https://openalex.org/W3096939667","https://openalex.org/W3140429000","https://openalex.org/W3142644187","https://openalex.org/W3146550708","https://openalex.org/W3162517041","https://openalex.org/W3174285493","https://openalex.org/W3197993066","https://openalex.org/W3198082505","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3210530853","https://openalex.org/W3213029956","https://openalex.org/W3215615641","https://openalex.org/W4205742757","https://openalex.org/W4221147462","https://openalex.org/W4224926192","https://openalex.org/W4225892118","https://openalex.org/W4225956675","https://openalex.org/W4226421465","https://openalex.org/W4226474318","https://openalex.org/W4255556797","https://openalex.org/W4285414384","https://openalex.org/W4296069352","https://openalex.org/W4306729455","https://openalex.org/W4313316128","https://openalex.org/W4322714819","https://openalex.org/W4323896824","https://openalex.org/W4361994820","https://openalex.org/W4366493008","https://openalex.org/W4372259784","https://openalex.org/W4385574033","https://openalex.org/W4385822372","https://openalex.org/W4385823135","https://openalex.org/W4390604258","https://openalex.org/W4392903036","https://openalex.org/W4392903174","https://openalex.org/W4396542467","https://openalex.org/W4402669711"],"related_works":["https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4245971243","https://openalex.org/W1922805944","https://openalex.org/W4253588120","https://openalex.org/W2383732295","https://openalex.org/W2942717012","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Emotional":[0],"voice":[1],"conversion":[2],"(EVC)":[3],"involves":[4],"modifying":[5],"various":[6],"acoustic":[7],"characteristics,":[8],"such":[9],"as":[10],"pitch":[11],"and":[12,37,100,141,151,165],"spectral":[13],"envelope,":[14],"to":[15,39,137],"match":[16],"a":[17,51,67,93,119],"desired":[18],"emotional":[19,101,108,116,127,167],"state":[20],"while":[21],"preserving":[22],"the":[23,58,83,107,111,125,134,139,144,170],"speaker\u2019s":[24],"identity.":[25],"Existing":[26],"EVC":[27,53],"methods":[28],"often":[29],"rely":[30],"on":[31],"text":[32,61,86],"transcriptions":[33],"or":[34,62,87],"time-alignment":[35],"information":[36,73],"struggle":[38],"handle":[40],"varying":[41],"speech":[42,76],"durations":[43],"effectively.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,91],"propose":[49],"DurFlex-EVC,":[50],"duration-flexible":[52],"framework":[54],"that":[55,70,96,123,155],"operates":[56],"without":[57],"need":[59,84],"for":[60,85],"alignment":[63],"information.":[64],"We":[65,113],"introduce":[66],"unit":[68],"aligner":[69],"models":[71],"contextual":[72],"by":[74],"aligning":[75],"with":[77],"discrete":[78],"units":[79],"representing":[80],"content,":[81],"eliminating":[82],"speech-text":[88],"alignment.":[89],"Additionally,":[90],"design":[92],"style":[94,128],"autoencoder":[95],"effectively":[97,161],"disentangles":[98],"content":[99],"style,":[102],"allowing":[103],"precise":[104],"manipulation":[105],"of":[106,110,143],"characteristics":[109],"speech.":[112,146,172],"further":[114],"enhance":[115],"expressiveness":[117,142,168],"through":[118],"hierarchical":[120,131],"stylize":[121],"encoder":[122],"applies":[124],"target":[126],"at":[129],"multiple":[130],"levels,":[132],"refining":[133],"stylization":[135],"process":[136],"improve":[138],"naturalness":[140],"converted":[145,171],"Experimental":[147],"results":[148],"from":[149],"subjective":[150],"objective":[152],"evaluations":[153],"demonstrate":[154],"our":[156],"approach":[157],"outperforms":[158],"baseline":[159],"models,":[160],"handling":[162],"duration":[163],"variability":[164],"enhancing":[166],"in":[169]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}