{"id":"https://openalex.org/W3015241559","doi":"https://doi.org/10.1109/icassp40776.2020.9054579","title":"Stargan for Emotional Speech Conversion: Validated by Data Augmentation of End-To-End Emotion Recognition","display_name":"Stargan for Emotional Speech Conversion: Validated by Data Augmentation of End-To-End Emotion Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015241559","doi":"https://doi.org/10.1109/icassp40776.2020.9054579","mag":"3015241559"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054579","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":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91702/91702.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Georgios Rizos","raw_affiliation_strings":["GLAM\u2013Group on Language, Audio and Music, Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"GLAM\u2013Group on Language, Audio and Music, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030891676","display_name":"Alice Baird","orcid":"https://orcid.org/0000-0002-7003-5650"},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alice Baird","raw_affiliation_strings":["ZD.B Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"ZD.B Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108879971","display_name":"Max Elliott","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":"Max Elliott","raw_affiliation_strings":["GLAM\u2013Group on Language, Audio and Music, Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"GLAM\u2013Group on Language, Audio and 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/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":"Bjorn Schuller","raw_affiliation_strings":["GLAM\u2013Group on Language, Audio and Music, Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"GLAM\u2013Group on Language, Audio and Music, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054300849"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":4.8687,"has_fulltext":true,"cited_by_count":109,"citation_normalized_percentile":{"value":0.96051603,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3502","last_page":"3506"},"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/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.7591124176979065},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7438521981239319},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6986050009727478},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6293602585792542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5908967852592468},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.549310564994812},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5000543594360352},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.49916696548461914},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4979541301727295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49195596575737},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.4866786599159241},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.45973527431488037},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4373036324977875},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.42182859778404236},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24634546041488647},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09940019249916077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591124176979065},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7438521981239319},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6986050009727478},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6293602585792542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5908967852592468},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.549310564994812},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5000543594360352},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.49916696548461914},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4979541301727295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49195596575737},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.4866786599159241},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.45973527431488037},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4373036324977875},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42182859778404236},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24634546041488647},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09940019249916077},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054579","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"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:91702","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/91702","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91702/91702.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:91702","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/91702","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91702/91702.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":[{"id":"https://openalex.org/G1219560291","display_name":null,"funder_award_id":"Economic","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2144436181","display_name":null,"funder_award_id":"HJ-253479","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"},{"id":"https://openalex.org/G3697185943","display_name":null,"funder_award_id":"2021037","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4115941747","display_name":null,"funder_award_id":"Ministry of Education","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320322728","display_name":"Bayerisches Staatsministerium f\u00fcr Bildung und Kultus, Wissenschaft und Kunst","ror":"https://ror.org/01a44gd51"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015241559.pdf","grobid_xml":"https://content.openalex.org/works/W3015241559.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W567437002","https://openalex.org/W1598253959","https://openalex.org/W1947595512","https://openalex.org/W1993267429","https://openalex.org/W2032254851","https://openalex.org/W2099471712","https://openalex.org/W2123771434","https://openalex.org/W2146334809","https://openalex.org/W2471520273","https://openalex.org/W2517513811","https://openalex.org/W2740504963","https://openalex.org/W2748699435","https://openalex.org/W2770173563","https://openalex.org/W2921059071","https://openalex.org/W2936764189","https://openalex.org/W2936774411","https://openalex.org/W2937977583","https://openalex.org/W2962793481","https://openalex.org/W2962879692","https://openalex.org/W2963539064","https://openalex.org/W2963767194","https://openalex.org/W2972640480","https://openalex.org/W2984972638","https://openalex.org/W4254718357","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W6635996524","https://openalex.org/W6735913928","https://openalex.org/W6746638498","https://openalex.org/W6761745632"],"related_works":["https://openalex.org/W4387301579","https://openalex.org/W4385421777","https://openalex.org/W2971552217","https://openalex.org/W4305042383","https://openalex.org/W2546649374","https://openalex.org/W4380854332","https://openalex.org/W2184859701","https://openalex.org/W4386232293","https://openalex.org/W4379781104","https://openalex.org/W2382178633"],"abstract_inverted_index":{"In":[0,26],"this":[1],"paper,":[2],"we":[3,29,39,114],"propose":[4],"an":[5,64],"adversarial":[6,61],"network":[7,62],"implementation":[8],"for":[9,73,129],"speech":[10,22],"emotion":[11],"conversion":[12],"as":[13,47,49],"a":[14,20,43,57,77,93,98,105,127],"data":[15,54,74],"augmentation":[16],"method,":[17],"validated":[18],"by":[19,55],"multi-class":[21],"affect":[23],"recognition":[24],"task.":[25],"our":[27,117],"setting,":[28],"do":[30],"not":[31],"assume":[32],"the":[33,51,90,110,134],"availability":[34],"of":[35,109,121,137],"parallel":[36],"data,":[37],"and":[38,80,86,139],"additionally":[40],"make":[41],"it":[42],"priority":[44],"to":[45,89],"exploit":[46],"much":[48],"possible":[50],"available":[52],"training":[53],"adopting":[56],"cycle-consistent,":[58],"class-conditional":[59],"generative":[60],"with":[63],"auxiliary":[65],"domain":[66],"classifier.":[67],"Our":[68],"generated":[69],"samples":[70,118],"are":[71,119,141],"valuable":[72],"augmentation,":[75],"achieving":[76],"corresponding":[78],"2%":[79],"6%":[81],"absolute":[82],"increase":[83],"in":[84,92,131],"Micro-":[85],"MacroF1":[87],"compared":[88],"baseline":[91],"3-class":[94],"classification":[95],"paradigm":[96],"using":[97],"deep,":[99],"end-to-end":[100],"network.":[101],"We":[102],"finally":[103],"perform":[104],"human":[106],"perception":[107],"evaluation":[108],"samples,":[111],"through":[112],"which":[113],"conclude":[115],"that":[116],"indicative":[120],"their":[122],"target":[123],"emotion,":[124],"albeit":[125],"showing":[126],"tendency":[128],"confusion":[130],"cases":[132],"where":[133],"emotional":[135],"attribute":[136],"valence":[138],"arousal":[140],"inconsistent.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":50},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}