{"id":"https://openalex.org/W4390094955","doi":"https://doi.org/10.1145/3570945.3607289","title":"Generation of speech and facial animation with controllable articulatory effort for amusing conversational characters","display_name":"Generation of speech and facial animation with controllable articulatory effort for amusing conversational characters","publication_year":2023,"publication_date":"2023-09-19","ids":{"openalex":"https://openalex.org/W4390094955","doi":"https://doi.org/10.1145/3570945.3607289"},"language":"en","primary_location":{"id":"doi:10.1145/3570945.3607289","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570945.3607289","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570945.3607289","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3570945.3607289","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015417808","display_name":"Joakim Gustafson","orcid":"https://orcid.org/0000-0002-0397-6442"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Joakim Gustafson","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"\u00c9va Sz\u00e9kely","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088064508","display_name":"Jonas Beskow","orcid":"https://orcid.org/0000-0003-1399-6604"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jonas Beskow","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015417808"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.3924,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5968091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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/T11448","display_name":"Face recognition and analysis","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7719992399215698},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6996377110481262},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6719664335250854},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6399540901184082},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.588190495967865},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5876588821411133},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5331040620803833},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4845280051231384},{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.47271105647087097},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.45049089193344116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30544236302375793},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12723255157470703},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.08486762642860413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719992399215698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6996377110481262},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6719664335250854},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6399540901184082},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.588190495967865},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5876588821411133},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5331040620803833},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4845280051231384},{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.47271105647087097},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.45049089193344116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30544236302375793},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12723255157470703},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.08486762642860413},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3570945.3607289","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570945.3607289","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570945.3607289","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-333395","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-333395","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"pmh:oai:DiVA.org:kth-341039","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-341039","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3570945.3607289","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570945.3607289","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570945.3607289","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3102226089","display_name":null,"funder_award_id":"P20-0298","funder_id":"https://openalex.org/F4320322659","funder_display_name":"Riksbankens Jubileumsfond"},{"id":"https://openalex.org/G712881263","display_name":null,"funder_award_id":"2018-","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G7322658688","display_name":null,"funder_award_id":"2018-05409","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320322659","display_name":"Riksbankens Jubileumsfond","ror":"https://ror.org/02jkbm893"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390094955.pdf","grobid_xml":"https://content.openalex.org/works/W4390094955.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W91891940","https://openalex.org/W339884141","https://openalex.org/W1483815053","https://openalex.org/W1516931150","https://openalex.org/W1543678897","https://openalex.org/W1980450636","https://openalex.org/W1985370873","https://openalex.org/W2017297220","https://openalex.org/W2042257828","https://openalex.org/W2046077605","https://openalex.org/W2111754733","https://openalex.org/W2115825178","https://openalex.org/W2145421863","https://openalex.org/W2148985157","https://openalex.org/W2159973998","https://openalex.org/W2187089797","https://openalex.org/W2468212864","https://openalex.org/W2550497374","https://openalex.org/W2737658251","https://openalex.org/W2886099142","https://openalex.org/W2921495256","https://openalex.org/W2937881934","https://openalex.org/W2943399188","https://openalex.org/W2964243274","https://openalex.org/W2968193852","https://openalex.org/W3011535310","https://openalex.org/W3015645837","https://openalex.org/W3015841875","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3093732267","https://openalex.org/W3097483812","https://openalex.org/W3097892637","https://openalex.org/W3102356365","https://openalex.org/W3159367349","https://openalex.org/W3182074706","https://openalex.org/W3194605252","https://openalex.org/W3197824033","https://openalex.org/W3202278141","https://openalex.org/W3206228555","https://openalex.org/W3207281888","https://openalex.org/W3211147706","https://openalex.org/W4224233303","https://openalex.org/W4321488265","https://openalex.org/W4372270801"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W615219140","https://openalex.org/W4232411666","https://openalex.org/W2999276620","https://openalex.org/W1564870812","https://openalex.org/W1978243811","https://openalex.org/W2096968018","https://openalex.org/W2906438086","https://openalex.org/W3040900128"],"abstract_inverted_index":{"Engaging":[0],"embodied":[1],"conversational":[2,32,122],"agents":[3],"need":[4],"to":[5,11,88,105,126],"generate":[6,23,106],"expressive":[7],"behavior":[8],"in":[9,14,113],"order":[10],"be":[12,70],"believable":[13],"socializing":[15],"interactions.":[16],"We":[17,60],"present":[18],"a":[19,38,62,130],"system":[20,102,134],"that":[21,42,100,111],"can":[22,69],"spontaneous":[24],"speech":[25,40,63,86,107],"with":[26,129],"supporting":[27],"lip":[28],"movements.":[29],"The":[30,72],"neural":[31],"TTS":[33,123],"voice":[34],"is":[35,75,103],"trained":[36],"on":[37],"multi-style":[39],"corpus":[41],"has":[43],"been":[44],"prosodically":[45],"tagged":[46],"(pitch":[47],"and":[48,51,58,80,108],"speaking":[49],"rate)":[50],"transcribed":[52],"(including":[53],"tokens":[54],"for":[55],"breathing,":[56],"fillers":[57],"laughter).":[59],"introduce":[61],"animation":[64,74,110],"algorithm":[65],"where":[66],"articulatory":[67],"effort":[68],"adjusted.":[71],"facial":[73,109],"driven":[76],"by":[77],"time-stamped":[78],"phonemes":[79],"prominence":[81],"estimates":[82],"from":[83],"the":[84,90,101],"synthesised":[85],"waveform":[87],"modulate":[89],"lip-and":[91],"jaw":[92],"movements":[93],"accordingly.":[94],"In":[95,116],"objective":[96],"evaluations":[97,118],"we":[98,119],"show":[99],"able":[104],"vary":[112],"articulation":[114],"effort.":[115],"subjective":[117],"compare":[120],"our":[121],"system's":[124],"capability":[125],"deliver":[127],"jokes":[128],"commercial":[131],"TTS.":[132],"Both":[133],"succeeded":[135],"equally":[136],"good.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
