{"id":"https://openalex.org/W3015699566","doi":"https://doi.org/10.1109/icassp40776.2020.9054534","title":"Multi-Speaker and Multi-Domain Emotional Voice Conversion Using Factorized Hierarchical Variational Autoencoder","display_name":"Multi-Speaker and Multi-Domain Emotional Voice Conversion Using Factorized Hierarchical Variational Autoencoder","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015699566","doi":"https://doi.org/10.1109/icassp40776.2020.9054534","mag":"3015699566"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5023316226","display_name":"Mohamed Elgaar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"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":["CA","KR"],"is_corresponding":true,"raw_author_name":"Mohamed Elgaar","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046603228","display_name":"Jungbae Park","orcid":"https://orcid.org/0000-0003-4104-5857"},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"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":["CA","KR"],"is_corresponding":false,"raw_author_name":"Jungbae Park","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075631319","display_name":"Sang Wan Lee","orcid":"https://orcid.org/0000-0001-6266-9613"},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"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":["CA","KR"],"is_corresponding":false,"raw_author_name":"Sang Wan Lee","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023316226"],"corresponding_institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"],"apc_list":null,"apc_paid":null,"fwci":1.6669,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84186965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7769","last_page":"7773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9995999932289124,"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/autoencoder","display_name":"Autoencoder","score":0.7739022374153137},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7555163502693176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7082433104515076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6325995922088623},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5364395380020142},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.44643816351890564},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4265049397945404},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41921207308769226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3772431015968323},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30752450227737427},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07498759031295776}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7739022374153137},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7555163502693176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7082433104515076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6325995922088623},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5364395380020142},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.44643816351890564},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4265049397945404},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41921207308769226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3772431015968323},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30752450227737427},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07498759031295776},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1588037970","https://openalex.org/W1666690886","https://openalex.org/W1959608418","https://openalex.org/W2077801020","https://openalex.org/W2096564043","https://openalex.org/W2146334809","https://openalex.org/W2149628368","https://openalex.org/W2161736993","https://openalex.org/W2163922914","https://openalex.org/W2608338293","https://openalex.org/W2752796333","https://openalex.org/W2753738274","https://openalex.org/W2758785877","https://openalex.org/W2887894196","https://openalex.org/W2899361462","https://openalex.org/W2902772991","https://openalex.org/W2943963359","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2962793481","https://openalex.org/W2962896155","https://openalex.org/W2963226019","https://openalex.org/W2963252329","https://openalex.org/W2963539064","https://openalex.org/W2963568578","https://openalex.org/W2963618559","https://openalex.org/W2963799213","https://openalex.org/W2963873807","https://openalex.org/W2972667718","https://openalex.org/W2972689158","https://openalex.org/W4289383906","https://openalex.org/W6635180523","https://openalex.org/W6636929691","https://openalex.org/W6640963894","https://openalex.org/W6718140377","https://openalex.org/W6737196085","https://openalex.org/W6744627333","https://openalex.org/W6745117592","https://openalex.org/W6755300632","https://openalex.org/W6755932049","https://openalex.org/W6756002706","https://openalex.org/W6762533536"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W4387098302","https://openalex.org/W3158195778","https://openalex.org/W4307861469","https://openalex.org/W2066496325","https://openalex.org/W2894697383","https://openalex.org/W2526960468"],"abstract_inverted_index":{"Due":[0],"to":[1,44,51,71,80,109],"the":[2,68,93,111],"complexity":[3],"of":[4,27,32,55,75,89,95,113,118],"emotional":[5,13,83],"features,":[6],"there":[7],"has":[8],"been":[9],"limited":[10],"success":[11],"in":[12,116],"voice":[14,33,84,121],"conversion.":[15],"One":[16],"major":[17],"challenge":[18],"is":[19],"that":[20],"conversion":[21],"between":[22],"more":[23],"than":[24],"two":[25],"kinds":[26],"emotions":[28],"often":[29],"accompanies":[30],"distortion":[31],"signal.The":[34],"factorized":[35],"hierarchical":[36],"variational":[37],"autoencoder":[38],"(FHVAE)":[39],"[1]":[40],"was":[41],"previously":[42],"shown":[43],"have":[45],"an":[46],"ability,":[47],"called":[48],"sequence-level":[49,57],"regularization,":[50],"generate":[52],"disentangled":[53,73,96],"representations":[54,74],"both":[56],"(such":[58],"as":[59],"speaker":[60],"identity)":[61],"and":[62,98,126],"segment-level":[63],"features.":[64],"This":[65],"study":[66],"exploits":[67],"FHVAE":[69],"pipeline":[70],"produce":[72],"emotion,":[76],"making":[77],"it":[78],"possible":[79],"greatly":[81],"facilitate":[82],"conversion.We":[85],"propose":[86],"three":[87,103],"versions":[88],"algorithms":[90],"for":[91],"improving":[92],"quality":[94],"representation":[97],"audio":[99,128],"synthesis.":[100],"We":[101],"conducted":[102],"mean":[104],"opinion":[105],"score":[106],"(MOS)":[107],"surveys":[108],"assess":[110],"performance":[112],"our":[114],"models":[115],"terms":[117],"1)":[119],"speaker\u2019s":[120],"preservation,":[122],"2)":[123],"emotion":[124],"conversion,":[125],"3)":[127],"naturalness.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}