{"id":"https://openalex.org/W4296069352","doi":"https://doi.org/10.21437/interspeech.2022-10636","title":"An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion","display_name":"An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069352","doi":"https://doi.org/10.21437/interspeech.2022-10636"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10636","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10636","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/99288/99288 yang22t_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087186760","display_name":"Zijiang Yang","orcid":"https://orcid.org/0000-0001-6469-5217"},"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":true,"raw_author_name":"Zijiang Yang","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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/A5101414146","display_name":"Xin Jing","orcid":"https://orcid.org/0000-0002-3425-3968"},"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":"Xin Jing","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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/A5012240826","display_name":"Andreas Triantafyllopoulos","orcid":"https://orcid.org/0000-0001-8338-617X"},"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":"Andreas Triantafyllopoulos","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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/A5064980455","display_name":"Meishu Song","orcid":"https://orcid.org/0000-0003-0023-415X"},"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/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["DE","JP"],"is_corresponding":false,"raw_author_name":"Meishu Song","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","Educational Physiology Laboratory, University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Educational Physiology Laboratory, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077030428","display_name":"Ilhan Aslan","orcid":"https://orcid.org/0000-0002-4803-1290"},"institutions":[{"id":"https://openalex.org/I4210129353","display_name":"Huawei Technologies (Germany)","ror":"https://ror.org/038cdme44","country_code":"DE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ilhan Aslan","raw_affiliation_strings":["Device Software Lab, Munich Research Center, Huawei Technologies, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Device Software Lab, Munich Research Center, Huawei Technologies, Germany","institution_ids":["https://openalex.org/I4210129353"]}]},{"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":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","GLAM -Group on Language, Audio, & Music, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"GLAM -Group on Language, Audio, & Music, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087186760"],"corresponding_institution_ids":["https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4915","last_page":"4919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9718999862670898,"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":0.9718999862670898,"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":0.9487000107765198,"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/sequence","display_name":"Sequence (biology)","score":0.7371888160705566},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5482207536697388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49457594752311707},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16462594270706177},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11483776569366455}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7371888160705566},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5482207536697388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49457594752311707},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16462594270706177},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11483776569366455}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10636","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10636","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:99288","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-992886","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/99288/99288 yang22t_interspeech.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":null,"raw_type":"conferenceobject"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:99288","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-992886","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/99288/99288 yang22t_interspeech.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":null,"raw_type":"conferenceobject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296069352.pdf","grobid_xml":"https://content.openalex.org/works/W4296069352.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2055332436","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2150791533","https://openalex.org/W2169166781","https://openalex.org/W2239141610","https://openalex.org/W2407110532","https://openalex.org/W2511640485","https://openalex.org/W2526425061","https://openalex.org/W2792059711","https://openalex.org/W2810914326","https://openalex.org/W2901254300","https://openalex.org/W2937870435","https://openalex.org/W2938833595","https://openalex.org/W2946004666","https://openalex.org/W2963609956","https://openalex.org/W2966387353","https://openalex.org/W2968201928","https://openalex.org/W2998572311","https://openalex.org/W3015241559","https://openalex.org/W3015338123","https://openalex.org/W3015699566","https://openalex.org/W3015719316","https://openalex.org/W3015719750","https://openalex.org/W3025680351","https://openalex.org/W3092028330","https://openalex.org/W3096567388","https://openalex.org/W3096939667","https://openalex.org/W3136699727","https://openalex.org/W3174758275","https://openalex.org/W4200225196","https://openalex.org/W4205742757","https://openalex.org/W4221147462","https://openalex.org/W4298580827"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Emotional":[0],"voice":[1],"conversion":[2],"(EVC)":[3],"focuses":[4],"on":[5],"converting":[6],"a":[7,11,14,21,70],"speech":[8,44],"utterance":[9],"from":[10,101],"source":[12],"to":[13,57,83,120],"target":[15],"emotion;":[16],"it":[17],"can":[18,76],"thus":[19],"be":[20],"key":[22,50],"enabling":[23],"technology":[24],"for":[25,73],"human-computer":[26],"interaction":[27],"applications":[28],"and":[29,46,99,113],"beyond.":[30],"However,":[31],"EVC":[32,94],"remains":[33],"an":[34,81,126],"unsolved":[35],"research":[36,86,123],"problem":[37],"with":[38,125],"several":[39],"challenges.":[40,79],"In":[41,80],"particular,":[42],"as":[43,69],"rate":[45],"rhythm":[47],"are":[48],"two":[49],"factors":[51],"of":[52,61,130,139],"emotional":[53],"conversion,":[54],"models":[55,74],"have":[56],"generate":[58],"output":[59],"sequences":[60],"differing":[62],"length.":[63],"Sequence-to-sequence":[64],"modelling":[65],"is":[66,118],"recently":[67],"emerging":[68],"competitive":[71],"paradigm":[72],"that":[75],"overcome":[77],"those":[78],"attempt":[82],"stimulate":[84],"further":[85],"in":[87],"this":[88],"promising":[89],"new":[90],"direction,":[91],"recent":[92],"sequence-to-sequence":[93,140],"papers":[95],"were":[96],"systematically":[97],"investigated":[98],"reviewed":[100],"six":[102],"perspectives:":[103],"their":[104],"motivation,":[105],"training":[106],"strategies,":[107],"model":[108,111],"architectures,":[109],"datasets,":[110],"inputs,":[112],"evaluation":[114],"methods.":[115],"This":[116],"information":[117],"organised":[119],"provide":[121],"the":[122,131],"community":[124],"easily":[127],"digestible":[128],"overview":[129],"current":[132],"state-of-the-art.":[133],"Finally,":[134],"we":[135],"discuss":[136],"existing":[137],"challenges":[138],"EVC.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}