{"id":"https://openalex.org/W4205690208","doi":"https://doi.org/10.1109/aciiw52867.2021.9666349","title":"On the Potential of Modular Voice Conversion for Virtual Agents","display_name":"On the Potential of Modular Voice Conversion for Virtual Agents","publication_year":2021,"publication_date":"2021-09-28","ids":{"openalex":"https://openalex.org/W4205690208","doi":"https://doi.org/10.1109/aciiw52867.2021.9666349"},"language":"en","primary_location":{"id":"doi:10.1109/aciiw52867.2021.9666349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aciiw52867.2021.9666349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 9th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)","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/90974/90974.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043580137","display_name":"Silvan Mertes","orcid":"https://orcid.org/0000-0001-5230-5218"},"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":"Silvan Mertes","raw_affiliation_strings":["Augsburg University,Human-Centered Artificial Intelligence,Germany","Human-Centered Artificial Intelligence, Augsburg University, Germany"],"affiliations":[{"raw_affiliation_string":"Augsburg University,Human-Centered Artificial Intelligence,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Human-Centered Artificial Intelligence, Augsburg University, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087592002","display_name":"Thomas Kiderle","orcid":"https://orcid.org/0009-0009-1616-2294"},"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":"Thomas Kiderle","raw_affiliation_strings":["Augsburg University,Human-Centered Artificial Intelligence,Germany","Human-Centered Artificial Intelligence, Augsburg University, Germany"],"affiliations":[{"raw_affiliation_string":"Augsburg University,Human-Centered Artificial Intelligence,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Human-Centered Artificial Intelligence, Augsburg University, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089646210","display_name":"Ruben Schlagowski","orcid":"https://orcid.org/0000-0002-3516-6188"},"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":"Ruben Schlagowski","raw_affiliation_strings":["Augsburg University,Human-Centered Artificial Intelligence,Germany","Human-Centered Artificial Intelligence, Augsburg University, Germany"],"affiliations":[{"raw_affiliation_string":"Augsburg University,Human-Centered Artificial Intelligence,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Human-Centered Artificial Intelligence, Augsburg University, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023000450","display_name":"Florian Lingenfelser","orcid":"https://orcid.org/0000-0003-1582-9850"},"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":"Florian Lingenfelser","raw_affiliation_strings":["Augsburg University,Human-Centered Artificial Intelligence,Germany","Human-Centered Artificial Intelligence, Augsburg University, Germany"],"affiliations":[{"raw_affiliation_string":"Augsburg University,Human-Centered Artificial Intelligence,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Human-Centered Artificial Intelligence, Augsburg University, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056684559","display_name":"Elisabeth Andr\u00e9","orcid":"https://orcid.org/0000-0002-2367-162X"},"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":"Elisabeth Andre","raw_affiliation_strings":["Augsburg University,Human-Centered Artificial Intelligence,Germany","Human-Centered Artificial Intelligence, Augsburg University, Germany"],"affiliations":[{"raw_affiliation_string":"Augsburg University,Human-Centered Artificial Intelligence,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Human-Centered Artificial Intelligence, Augsburg University, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043580137"],"corresponding_institution_ids":["https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":0.4194,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70903901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"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":0.9901999831199646,"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":0.9901999831199646,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9767000079154968,"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/T12290","display_name":"Human Motion and Animation","score":0.9448000192642212,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8335278034210205},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6532834768295288},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5770606398582458},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5630910396575928},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.55820232629776},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5384544730186462},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5312478542327881},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5203656554222107},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.469906747341156},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.41598227620124817},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.30174732208251953},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09919846057891846},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07593825459480286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335278034210205},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6532834768295288},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5770606398582458},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5630910396575928},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.55820232629776},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5384544730186462},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5312478542327881},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5203656554222107},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.469906747341156},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.41598227620124817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30174732208251953},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09919846057891846},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07593825459480286},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/aciiw52867.2021.9666349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aciiw52867.2021.9666349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 9th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:90974","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-909749","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/90974/90974.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":"conferenceobject"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:90974","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-909749","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/90974/90974.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":"conferenceobject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4205690208.pdf"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1272904658","https://openalex.org/W1588037970","https://openalex.org/W1608901476","https://openalex.org/W2001429584","https://openalex.org/W2047028371","https://openalex.org/W2062350891","https://openalex.org/W2071559616","https://openalex.org/W2077801020","https://openalex.org/W2092154366","https://openalex.org/W2105119762","https://openalex.org/W2130050875","https://openalex.org/W2164772857","https://openalex.org/W2292632463","https://openalex.org/W2576309025","https://openalex.org/W2620789817","https://openalex.org/W2740340001","https://openalex.org/W2767118408","https://openalex.org/W2770743791","https://openalex.org/W2774848319","https://openalex.org/W2793479148","https://openalex.org/W2794490148","https://openalex.org/W2902070858","https://openalex.org/W2914814563","https://openalex.org/W2937579788","https://openalex.org/W2945226834","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963539064","https://openalex.org/W2963767194","https://openalex.org/W2964069186","https://openalex.org/W2972667718","https://openalex.org/W2972834593","https://openalex.org/W2995282955","https://openalex.org/W2997400081","https://openalex.org/W3014748700","https://openalex.org/W3015209900","https://openalex.org/W3015241559","https://openalex.org/W3015336668","https://openalex.org/W3015645837","https://openalex.org/W3025528898","https://openalex.org/W3095936335","https://openalex.org/W3096939667","https://openalex.org/W3132565327","https://openalex.org/W3158450963","https://openalex.org/W3159045181","https://openalex.org/W4298289240","https://openalex.org/W6662409566","https://openalex.org/W6697223144","https://openalex.org/W6745537575","https://openalex.org/W6750489868","https://openalex.org/W6759482875","https://openalex.org/W6761382815","https://openalex.org/W6762634096","https://openalex.org/W6794850166"],"related_works":["https://openalex.org/W2378076731","https://openalex.org/W2357256365","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W2348502264","https://openalex.org/W2088988140","https://openalex.org/W2365486383","https://openalex.org/W2362059367","https://openalex.org/W2803103875","https://openalex.org/W2103019253"],"abstract_inverted_index":{"Virtual":[0],"Agents":[1],"are":[2,88,100,130,149],"a":[3,8,38,107],"way":[4,10],"to":[5,11,114,138,151,176],"give":[6],"humans":[7],"familiar":[9],"interact":[12],"with":[13,28],"the":[14,20,26,51,57,66,69,72,104,116,124,152,162,171,174],"computer.":[15],"An":[16],"important":[17,64],"component":[18],"in":[19,56,123],"design":[21],"of":[22,53,59,71,110,118,126,154,164,173],"virtual":[23,60,189],"agents":[24],"is":[25,35,63,83,113,120],"voice":[27,34,70,127,166],"which":[29],"they":[30,135,148],"express":[31],"themselves.":[32],"The":[33],"not":[36],"only":[37,136],"mere":[39],"medium":[40],"for":[41,95,184,188],"information":[42],"transfer,":[43],"but":[44],"also":[45],"contains":[46],"non-verbal":[47,140],"functions":[48],"such":[49,86,165],"as":[50,134],"transmission":[52],"emotions.":[54],"Additionally,":[55],"context":[58],"agents,":[61],"it":[62,76,82],"that":[65,85,106,161],"user":[67],"accepts":[68],"agent":[73],"and":[74,91,169],"considers":[75],"consistent.":[77],"To":[78],"make":[79],"this":[80],"possible,":[81],"necessary":[84],"voices":[87],"highly":[89],"customisable":[90],"adaptable.":[92],"Current":[93],"systems":[94,143,187],"generating":[96],"speech":[97],"from":[98,132],"text":[99],"conceptually":[101],"limited":[102,150],"by":[103],"fact":[105],"large":[108],"part":[109],"their":[111],"task":[112],"model":[115,139],"semantics":[117],"what":[119],"spoken.":[121],"Systems":[122],"field":[125],"conversion,":[128],"however,":[129],"decoupled":[131],"this,":[133],"need":[137],"features.":[141],"Such":[142],"become":[144],"particularly":[145],"efficient":[146],"when":[147],"transformation":[153],"dedicated,":[155],"single":[156],"characteristics.":[157],"This":[158],"paper":[159],"proposes":[160],"use":[163],"conversion":[167],"systems,":[168],"furthermore":[170],"exploitation":[172],"possibility":[175],"cascade":[177],"them,":[178],"can":[179],"be":[180],"an":[181],"immense":[182],"improvement":[183],"conventional":[185],"Text-to-Speech":[186],"agents.":[190]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}
