{"id":"https://openalex.org/W3196643119","doi":"https://doi.org/10.21437/interspeech.2021-1253","title":"An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation","display_name":"An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196643119","doi":"https://doi.org/10.21437/interspeech.2021-1253","mag":"3196643119"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1253","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91583/91583.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051891413","display_name":"Xiangheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiangheng He","raw_affiliation_strings":["GLAM -Group on Language, Audio, & Music, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GLAM -Group on Language, Audio, & Music, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365536","display_name":"Junjie Chen","orcid":"https://orcid.org/0000-0002-0483-303X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junjie Chen","raw_affiliation_strings":["Department of Computer Science, The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054300849","display_name":"Georgios Rizos","orcid":"https://orcid.org/0000-0003-2483-5574"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Rizos","raw_affiliation_strings":["GLAM -Group on Language, Audio, & Music, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GLAM -Group on Language, Audio, & Music, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["GLAM -Group on Language, Audio, & Music, Imperial College London, UK","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GLAM -Group on Language, Audio, & Music, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2353,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79480485,"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":"821","last_page":"825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9923999905586243,"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":0.9442999958992004,"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/computer-science","display_name":"Computer science","score":0.6638153791427612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5915359258651733},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5721177458763123},{"id":"https://openalex.org/keywords/voice-communication","display_name":"Voice communication","score":0.5404461622238159},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.4651981592178345},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3207132816314697},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20288068056106567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638153791427612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5915359258651733},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5721177458763123},{"id":"https://openalex.org/C2983306500","wikidata":"https://www.wikidata.org/wiki/Q52946","display_name":"Voice communication","level":2,"score":0.5404461622238159},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.4651981592178345},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3207132816314697},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20288068056106567},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-1253","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:91583","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/91583","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91583/91583.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:91583","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/91583","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91583/91583.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3196643119.pdf"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W567437002","https://openalex.org/W1522301498","https://openalex.org/W1598253959","https://openalex.org/W2107860279","https://openalex.org/W2123771434","https://openalex.org/W2146334809","https://openalex.org/W2471520273","https://openalex.org/W2532494225","https://openalex.org/W2748699435","https://openalex.org/W2806000759","https://openalex.org/W2888922217","https://openalex.org/W2936764189","https://openalex.org/W2945478979","https://openalex.org/W2950542544","https://openalex.org/W2963539064","https://openalex.org/W2963808252","https://openalex.org/W2972544500","https://openalex.org/W2972640480","https://openalex.org/W2973135352","https://openalex.org/W2984972638","https://openalex.org/W3015805741","https://openalex.org/W3095169545","https://openalex.org/W3095666234","https://openalex.org/W3096939667","https://openalex.org/W3100378519","https://openalex.org/W3116986826","https://openalex.org/W3163573274","https://openalex.org/W4295521014","https://openalex.org/W4298289240"],"related_works":["https://openalex.org/W1967908900","https://openalex.org/W2160379050","https://openalex.org/W2053207518","https://openalex.org/W2603569513","https://openalex.org/W4289829928","https://openalex.org/W1915283592","https://openalex.org/W3176636053","https://openalex.org/W2603738923","https://openalex.org/W2417199973","https://openalex.org/W2375244391"],"abstract_inverted_index":{"Emotional":[0],"Voice":[1],"Conversion":[2],"(EVC)":[3],"aims":[4],"to":[5,15,155],"convert":[6],"the":[7,92,95,107,111,121,137,156,163],"emotional":[8,27,33,77],"style":[9,18],"of":[10,53,82,94,116,144],"a":[11,16,47,65,71],"source":[12],"speech":[13,134],"signal":[14],"target":[17],"while":[19],"preserving":[20],"its":[21],"content":[22],"and":[23,50,110,149],"speaker":[24],"identity":[25],"information.Previous":[26],"conversion":[28],"studies":[29],"do":[30],"not":[31],"disentangle":[32],"information":[34,37],"from":[35,79],"emotion-independent":[36],"that":[38,75,120,162],"should":[39],"be":[40],"preserved,":[41],"thus":[42],"transforming":[43],"it":[44],"all":[45],"in":[46,105,114,128,147,152],"monolithic":[48],"manner":[49],"generating":[51],"audio":[52],"low":[54],"quality,":[55],"with":[56,70,88],"linguistic":[57],"distortions.To":[58],"address":[59],"this":[60],"distortion":[61],"problem,":[62],"we":[63],"propose":[64],"novel":[66],"StarGAN":[67,139,158],"framework":[68],"along":[69],"two-stage":[72],"training":[73],"process":[74],"separates":[76],"features":[78],"those":[80],"independent":[81],"emotion":[83,135],"by":[84],"using":[85],"an":[86,142],"autoencoder":[87],"two":[89],"encoders":[90],"as":[91],"generator":[93],"Generative":[96],"Adversarial":[97],"Network":[98],"(GAN).The":[99],"proposed":[100,122,138,164],"model":[101,123,140,165],"achieves":[102,141],"favourable":[103],"results":[104],"both":[106],"objective":[108],"evaluation":[109,113],"subjective":[112],"terms":[115],"distortion,":[117],"which":[118,160],"reveals":[119],"can":[124],"effectively":[125],"reduce":[126],"distortion.Furthermore,":[127],"data":[129,170],"augmentation":[130],"experiments":[131],"for":[132,169],"end-to-end":[133],"recognition,":[136],"increase":[143],"2":[145],"%":[146,151],"Micro-F1":[148],"5":[150],"Macro-F1":[153],"compared":[154],"baseline":[157],"model,":[159],"indicates":[161],"is":[166],"more":[167],"valuable":[168],"augmentation.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
