{"id":"https://openalex.org/W4225892118","doi":"https://doi.org/10.1109/taslp.2022.3156757","title":"Duration Controllable Voice Conversion via Phoneme-Based Information Bottleneck","display_name":"Duration Controllable Voice Conversion via Phoneme-Based Information Bottleneck","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4225892118","doi":"https://doi.org/10.1109/taslp.2022.3156757"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3156757","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3156757","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09729483.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09729483.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033958396","display_name":"Sang-Hoon Lee","orcid":"https://orcid.org/0000-0002-8925-4474"},"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":"Sang-Hoon Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8925-4474","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022436571","display_name":"Hyeong-Rae Noh","orcid":"https://orcid.org/0000-0003-4511-0839"},"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":"Hyeong-Rae Noh","raw_affiliation_strings":["Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-4511-0839","affiliations":[{"raw_affiliation_string":"Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060931534","display_name":"Woo-Jeoung Nam","orcid":"https://orcid.org/0000-0002-6548-4486"},"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":"Woo-Jeoung Nam","raw_affiliation_strings":["Department of Computer and Radio Communications Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6548-4486","affiliations":[{"raw_affiliation_string":"Department of Computer and Radio Communications Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011014617","display_name":"Seong\u2010Whan 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"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Whan Lee","raw_affiliation_strings":["Department of Artificial Intelligence, Korea University, Seoul, South Korea","Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-6249-4996","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"Department of Brain and Cognitive Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033958396"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":3.4683,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93341198,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"1173","last_page":"1183"},"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":0.9994000196456909,"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":0.9932000041007996,"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/duration","display_name":"Duration (music)","score":0.8655654191970825},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6960868835449219},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5955947637557983},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5347543954849243},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.41629162430763245},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.26998037099838257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20987439155578613},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.1048542857170105},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09684422612190247},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.05134722590446472}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8655654191970825},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6960868835449219},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5955947637557983},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5347543954849243},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.41629162430763245},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26998037099838257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20987439155578613},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.1048542857170105},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09684422612190247},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.05134722590446472}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3156757","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3156757","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09729483.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3156757","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3156757","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09729483.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2953128317","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320321373","funder_display_name":"Korea University"},{"id":"https://openalex.org/G8176700800","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8436554242","display_name":null,"funder_award_id":"2019-0-00079","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225892118.pdf","grobid_xml":"https://content.openalex.org/works/W4225892118.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1977362459","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2105160541","https://openalex.org/W2107860279","https://openalex.org/W2120605154","https://openalex.org/W2471520273","https://openalex.org/W2502312327","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2547364378","https://openalex.org/W2666408839","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2885820941","https://openalex.org/W2897353073","https://openalex.org/W2899877258","https://openalex.org/W2902070858","https://openalex.org/W2903739847","https://openalex.org/W2911708970","https://openalex.org/W2937579788","https://openalex.org/W2938583109","https://openalex.org/W2946555236","https://openalex.org/W2962788625","https://openalex.org/W2962793481","https://openalex.org/W2962896155","https://openalex.org/W2963539064","https://openalex.org/W2963609956","https://openalex.org/W2963767194","https://openalex.org/W2963796886","https://openalex.org/W2964243274","https://openalex.org/W2972659941","https://openalex.org/W2972667718","https://openalex.org/W2996414377","https://openalex.org/W2998115938","https://openalex.org/W3013020904","https://openalex.org/W3015282541","https://openalex.org/W3015805741","https://openalex.org/W3091928890","https://openalex.org/W3096442195","https://openalex.org/W3096567388","https://openalex.org/W3098557217","https://openalex.org/W3099078140","https://openalex.org/W3101689408","https://openalex.org/W3118753411","https://openalex.org/W3163475957","https://openalex.org/W3214606349","https://openalex.org/W6679436768","https://openalex.org/W6685777803","https://openalex.org/W6724804524","https://openalex.org/W6727697161","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6762533536","https://openalex.org/W6763832098","https://openalex.org/W6776390925","https://openalex.org/W6778823374","https://openalex.org/W6784545093","https://openalex.org/W6790622591","https://openalex.org/W6804125026"],"related_works":["https://openalex.org/W4401325445","https://openalex.org/W2622284819","https://openalex.org/W1504394672","https://openalex.org/W3089381707","https://openalex.org/W4285254085","https://openalex.org/W3034190530","https://openalex.org/W2741297526","https://openalex.org/W4295728955","https://openalex.org/W3129794609","https://openalex.org/W2949033103"],"abstract_inverted_index":{"Several":[0],"voice":[1,98],"conversion":[2,73,99],"(VC)":[3],"methods":[4,74],"using":[5],"a":[6,10,26,94,117,135,151,155,169,174],"simple":[7],"autoencoder":[8],"with":[9,45,80,150,173],"carefully":[11],"designed":[12],"information":[13,24,31,49,67,119,123],"bottleneck":[14,32,124],"have":[15],"recently":[16],"been":[17],"studied.":[18],"In":[19,69,89,142],"general,":[20],"they":[21],"extract":[22],"content":[23],"from":[25],"given":[27],"speech":[28,115,165],"through":[29,116],"the":[30,34,37,42,46,52,62,81,87,105,110,113,147,164,180],"between":[33],"encoder":[35],"and":[36,108,139,154],"decoder,":[38],"providing":[39],"it":[40],"to":[41,50,128],"decoder":[43],"along":[44],"target":[47],"speaker":[48],"generate":[51],"converted":[53,114],"speech.":[54],"However,":[55],"their":[56],"performance":[57],"is":[58],"highly":[59],"dependent":[60],"on":[61],"downsampling":[63,132],"factor":[64],"of":[65,83,112,179],"an":[66,130],"bottleneck.":[68,120],"addition,":[70],"such":[71,85],"frame-by-frame":[72],"cannot":[75],"convert":[76],"speaking":[77,106],"styles":[78],"associated":[79],"length":[82],"utterance,":[84],"as":[86],"duration.":[88],"this":[90],"paper,":[91],"we":[92],"propose":[93],"novel":[95],"duration":[96,166],"controllable":[97],"(DCVC)":[100],"model,":[101],"which":[102],"can":[103,160],"transfer":[104],"style":[107],"control":[109,163],"speed":[111],"phoneme-based":[118],"The":[121],"proposed":[122],"does":[125],"not":[126],"need":[127],"find":[129],"appropriate":[131],"factor,":[133],"achieving":[134,168],"better":[136],"audio":[137],"quality":[138],"VC":[140,176],"performance.":[141],"our":[143],"experiments,":[144],"DCVC":[145],"outperformed":[146],"baseline":[148],"models":[149],"3.78":[152],"MOS":[153],"3.83":[156],"similarity":[157],"score.":[158],"It":[159],"also":[161],"smoothly":[162],"while":[167],"39.35x":[170],"speedup":[171],"compared":[172],"Seq2seq-based":[175],"in":[177],"terms":[178],"inference":[181],"speed.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}