{"id":"https://openalex.org/W3002310794","doi":"https://doi.org/10.1145/3382507.3418815","title":"Gesticulator: A framework for semantically-aware speech-driven gesture generation","display_name":"Gesticulator: A framework for semantically-aware speech-driven gesture generation","publication_year":2020,"publication_date":"2020-10-21","ids":{"openalex":"https://openalex.org/W3002310794","doi":"https://doi.org/10.1145/3382507.3418815","mag":"3002310794"},"language":"en","primary_location":{"id":"doi:10.1145/3382507.3418815","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3382507.3418815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.09326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Taras Kucherenko","orcid":null},"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":"Taras Kucherenko","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Patrik Jonell","orcid":null},"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":"Patrik Jonell","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sanne van Waveren","orcid":null},"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":"Sanne van Waveren","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gustav Eje Henter","orcid":null},"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":"Gustav Eje Henter","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Simon Alexandersson","orcid":null},"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":"Simon Alexandersson","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Iolanda Leite","orcid":null},"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":"Iolanda Leite","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hedvig Kjellstr\u00f6m","orcid":null},"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":"Hedvig Kjellstr\u00f6m","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":41.1816,"has_fulltext":false,"cited_by_count":158,"citation_normalized_percentile":{"value":0.99943232,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"242","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.9514999985694885},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.46369999647140503},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4449999928474426},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3573000133037567},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.3357999920845032}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9514999985694885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6880000233650208},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.46369999647140503},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43209999799728394},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36899998784065247},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3382507.3418815","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3382507.3418815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.09326","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09326","pdf_url":"https://arxiv.org/pdf/2001.09326","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.09326","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09326","pdf_url":"https://arxiv.org/pdf/2001.09326","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W290231511","https://openalex.org/W1208039178","https://openalex.org/W1969784320","https://openalex.org/W1977259876","https://openalex.org/W1988932066","https://openalex.org/W2002616384","https://openalex.org/W2122376170","https://openalex.org/W2135996168","https://openalex.org/W2235920218","https://openalex.org/W2563154651","https://openalex.org/W2598638573","https://openalex.org/W2760103357","https://openalex.org/W2809225253","https://openalex.org/W2895551801","https://openalex.org/W2896593898","https://openalex.org/W2901285216","https://openalex.org/W2901872500","https://openalex.org/W2922298118","https://openalex.org/W2962795401","https://openalex.org/W2967443589","https://openalex.org/W2969845259","https://openalex.org/W2981133004","https://openalex.org/W3009042479","https://openalex.org/W4205471895","https://openalex.org/W4231947169"],"related_works":[],"abstract_inverted_index":{"During":[0],"speech,":[1],"people":[2],"spontaneously":[3],"gesticulate,":[4],"which":[5],"plays":[6],"a":[7,35,61,77,106],"key":[8],"role":[9],"in":[10],"conveying":[11],"information.":[12],"Similarly,":[13],"realistic":[14],"co-speech":[15,30],"gestures":[16,55,86,104,116],"are":[17,47,141],"crucial":[18],"to":[19,50,70,80,120],"enable":[20],"natural":[21],"and":[22,84,95,102,124,128,139],"smooth":[23],"interactions":[24],"with":[25],"social":[26],"agents.":[27],"Current":[28],"end-to-end":[29],"gesture":[31,73],"generation":[32],"systems":[33,46],"use":[34],"single":[36],"modality":[37],"for":[38],"representing":[39],"speech:":[40],"either":[41,52],"audio":[42],"or":[43,56],"text.":[44],"These":[45],"therefore":[48],"confined":[49],"producing":[51],"acoustically-linked":[53],"beat":[54,83],"semantically-linked":[57],"gesticulation":[58],"(e.g.,":[59],"raising":[60],"hand":[62],"when":[63],"saying":[64],"\"high''):":[65],"they":[66],"cannot":[67],"appropriately":[68],"learn":[69],"generate":[71],"both":[72,93,121],"types.":[74],"We":[75],"present":[76],"model":[78,91],"designed":[79],"produce":[81],"arbitrary":[82],"semantic":[85,96],"together.":[87],"Our":[88],"deep-learning":[89],"based":[90],"takes":[92],"acoustic":[94],"representations":[97],"of":[98,108,134],"speech":[99],"as":[100,105,112],"input,":[101],"generates":[103],"sequence":[107],"joint":[109],"angle":[110],"rotations":[111],"output.":[113],"The":[114,137],"resulting":[115],"can":[117],"be":[118],"applied":[119],"virtual":[122],"agents":[123],"humanoid":[125],"robots.":[126],"Subjective":[127],"objective":[129],"evaluations":[130],"confirm":[131],"the":[132,144],"success":[133],"our":[135],"approach.":[136],"code":[138],"video":[140],"available":[142],"at":[143],"project":[145],"page":[146],"svito-zar.github.io/gesticulator":[147],".":[148]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":33},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2020-01-30T00:00:00"}