{"id":"https://openalex.org/W3118242141","doi":"https://doi.org/10.21437/ssw.2021-13","title":"EmoCat: Language-agnostic Emotional Voice Conversion","display_name":"EmoCat: Language-agnostic Emotional Voice Conversion","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3118242141","doi":"https://doi.org/10.21437/ssw.2021-13","mag":"3118242141"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.05695","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050653844","display_name":"Bastian Schnell","orcid":"https://orcid.org/0000-0002-3540-0149"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Bastian Schnell","raw_affiliation_strings":["IDIAP RESEARCH INSTITUTE"],"affiliations":[{"raw_affiliation_string":"IDIAP RESEARCH INSTITUTE","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058343897","display_name":"Goeric Huybrechts","orcid":"https://orcid.org/0000-0003-0222-3008"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Goeric Huybrechts","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033936072","display_name":"Bartek Perz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bartek Perz","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050653844"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":0.1398,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51284075,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9991000294685364,"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/T10863","display_name":"Voice and Speech Disorders","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367393970489502},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6578445434570312},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6025657653808594},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.525116503238678},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.522416353225708},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4401313066482544},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41764605045318604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3693917393684387},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35912662744522095},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15715312957763672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367393970489502},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6578445434570312},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6025657653808594},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.525116503238678},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.522416353225708},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4401313066482544},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41764605045318604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3693917393684387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35912662744522095},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15715312957763672},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/ssw.2021-13","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.05695","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.05695","pdf_url":"https://arxiv.org/pdf/2101.05695","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3118242141","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2101.05695.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2101.05695","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.05695","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.05695","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.05695","pdf_url":"https://arxiv.org/pdf/2101.05695","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3118242141.pdf","grobid_xml":"https://content.openalex.org/works/W3118242141.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2471520273","https://openalex.org/W2608338293","https://openalex.org/W2899361462","https://openalex.org/W2932022923","https://openalex.org/W2949281321","https://openalex.org/W2950007391","https://openalex.org/W2954386831","https://openalex.org/W2963539064","https://openalex.org/W2963826681","https://openalex.org/W2964243274","https://openalex.org/W2973158936","https://openalex.org/W2990883660","https://openalex.org/W3015241559","https://openalex.org/W3015336668","https://openalex.org/W3015796413","https://openalex.org/W3022876224","https://openalex.org/W3025044797","https://openalex.org/W3025680351"],"related_works":["https://openalex.org/W3194143312","https://openalex.org/W3163573274","https://openalex.org/W3136699727","https://openalex.org/W87461617","https://openalex.org/W2995021324","https://openalex.org/W3179060760","https://openalex.org/W3185276528","https://openalex.org/W1993267429","https://openalex.org/W3205065526","https://openalex.org/W3100430603","https://openalex.org/W3197034238","https://openalex.org/W3196543367","https://openalex.org/W2998980418","https://openalex.org/W3101054222","https://openalex.org/W3201011692","https://openalex.org/W2345371550","https://openalex.org/W2602037756","https://openalex.org/W3015241559","https://openalex.org/W3213873715","https://openalex.org/W3015841875"],"abstract_inverted_index":{"Emotional":[0],"voice":[1,46,84],"conversion":[2,47,53,85,136],"models":[3,24],"adapt":[4],"the":[5,11,99,102,125,154,171],"emotion":[6,52,96,150,179],"in":[7,54,72],"speech":[8],"without":[9],"changing":[10],"speaker":[12],"identity":[13],"or":[14],"linguistic":[15],"content.":[16],"They":[17],"are":[18],"less":[19,57],"data":[20,33,71],"hungry":[21],"than":[22,58],"text-to-speech":[23],"and":[25,128],"allow":[26],"to":[27,94,101,113,116,122,129,131,144,153,164],"generate":[28],"large":[29,67],"amounts":[30,68],"of":[31,61,69,176],"emotional":[32,45,63,70],"for":[34,157,173],"downstream":[35],"tasks.":[36],"In":[37],"this":[38],"work":[39],"we":[40],"propose":[41],"EmoCat,":[42],"a":[43,83,110],"language-agnostic":[44],"model.":[48],"It":[49],"achieves":[50],"high-quality":[51],"German":[55,62],"with":[56,134,170],"45":[59],"minutes":[60],"recordings":[64,172],"by":[65,109],"exploiting":[66],"US":[73],"English.":[74],"EmoCat":[75,161],"is":[76,107,162],"an":[77],"encoder-decoder":[78],"model":[79],"based":[80],"on":[81,149,168],"CopyCat,":[82],"system":[86],"which":[87],"transfers":[88],"prosody.":[89],"We":[90],"use":[91],"adversarial":[92,105],"training":[93,106],"remove":[95,123],"leakage":[97],"from":[98],"encoder":[100],"decoder.":[103],"The":[104],"improved":[108],"novel":[111],"contribution":[112],"gradient":[114],"reversal":[115],"truly":[117],"reverse":[118],"gradients.":[119],"This":[120],"allows":[121],"only":[124],"leaking":[126],"information":[127],"converge":[130],"better":[132],"optima":[133],"higher":[135],"performance.":[137],"Evaluations":[138],"show":[139],"that":[140],"Emocat":[141],"can":[142],"convert":[143],"different":[145],"emotions":[146],"but":[147],"misses":[148],"intensity":[151],"compared":[152],"recordings,":[155],"especially":[156],"very":[158],"expressive":[159],"emotions.":[160],"able":[163],"achieve":[165],"audio":[166],"quality":[167],"par":[169],"five":[174],"out":[175],"six":[177],"tested":[178],"intensities.":[180]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
