{"id":"https://openalex.org/W3083173864","doi":"https://doi.org/10.1145/3414685.3417838","title":"Speech gesture generation from the trimodal context of text, audio, and speaker identity","display_name":"Speech gesture generation from the trimodal context of text, audio, and speaker identity","publication_year":2020,"publication_date":"2020-11-27","ids":{"openalex":"https://openalex.org/W3083173864","doi":"https://doi.org/10.1145/3414685.3417838","mag":"3083173864"},"language":"en","primary_location":{"id":"doi:10.1145/3414685.3417838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3414685.3417838","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.02119","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045112037","display_name":"Youngwoo Yoon","orcid":"https://orcid.org/0000-0003-4286-3421"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Youngwoo Yoon","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059564500","display_name":"Bok Cha","orcid":null},"institutions":[{"id":"https://openalex.org/I118692353","display_name":"University of Science and Technology","ror":"https://ror.org/05bj7sh33","country_code":"YE","type":"education","lineage":["https://openalex.org/I118692353"]}],"countries":["YE"],"is_corresponding":false,"raw_author_name":"Bok Cha","raw_affiliation_strings":["University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology","institution_ids":["https://openalex.org/I118692353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034140846","display_name":"Joo-Haeng Lee","orcid":"https://orcid.org/0000-0002-5788-712X"},"institutions":[{"id":"https://openalex.org/I118692353","display_name":"University of Science and Technology","ror":"https://ror.org/05bj7sh33","country_code":"YE","type":"education","lineage":["https://openalex.org/I118692353"]}],"countries":["YE"],"is_corresponding":false,"raw_author_name":"Joo-Haeng Lee","raw_affiliation_strings":["ETRI","University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI","institution_ids":[]},{"raw_affiliation_string":"University of Science and Technology","institution_ids":["https://openalex.org/I118692353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069073713","display_name":"Minsu Jang","orcid":"https://orcid.org/0000-0002-7166-0300"},"institutions":[{"id":"https://openalex.org/I118692353","display_name":"University of Science and Technology","ror":"https://ror.org/05bj7sh33","country_code":"YE","type":"education","lineage":["https://openalex.org/I118692353"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR","YE"],"is_corresponding":false,"raw_author_name":"Minsu Jang","raw_affiliation_strings":["ETRI","KAIST","ETRI, University of Science and Technology MINSU JANG, ETRI","KAIST BOK CHA, University of Science and Technology, ETRI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI","institution_ids":[]},{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]},{"raw_affiliation_string":"ETRI, University of Science and Technology MINSU JANG, ETRI","institution_ids":["https://openalex.org/I118692353"]},{"raw_affiliation_string":"KAIST BOK CHA, University of Science and Technology, ETRI","institution_ids":["https://openalex.org/I118692353","https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676670","display_name":"Jaeyeon Lee","orcid":"https://orcid.org/0000-0003-4633-1641"},"institutions":[{"id":"https://openalex.org/I118692353","display_name":"University of Science and Technology","ror":"https://ror.org/05bj7sh33","country_code":"YE","type":"education","lineage":["https://openalex.org/I118692353"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR","YE"],"is_corresponding":false,"raw_author_name":"Jaeyeon Lee","raw_affiliation_strings":["ETRI","University of Science and Technology","ETRI, University of Science and Technology MINSU JANG, ETRI","KAIST BOK CHA, University of Science and Technology, ETRI","KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI","institution_ids":[]},{"raw_affiliation_string":"University of Science and Technology","institution_ids":["https://openalex.org/I118692353"]},{"raw_affiliation_string":"ETRI, University of Science and Technology MINSU JANG, ETRI","institution_ids":["https://openalex.org/I118692353"]},{"raw_affiliation_string":"KAIST BOK CHA, University of Science and Technology, ETRI","institution_ids":["https://openalex.org/I118692353","https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101480473","display_name":"Jaehong Kim","orcid":"https://orcid.org/0000-0002-9111-9976"},"institutions":[{"id":"https://openalex.org/I118692353","display_name":"University of Science and Technology","ror":"https://ror.org/05bj7sh33","country_code":"YE","type":"education","lineage":["https://openalex.org/I118692353"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR","YE"],"is_corresponding":false,"raw_author_name":"Jaehong Kim","raw_affiliation_strings":["ETRI","KAIST BOK CHA, University of Science and Technology, ETRI","KAIST","ETRI, University of Science and Technology MINSU JANG, ETRI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI","institution_ids":[]},{"raw_affiliation_string":"KAIST BOK CHA, University of Science and Technology, ETRI","institution_ids":["https://openalex.org/I118692353","https://openalex.org/I157485424"]},{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]},{"raw_affiliation_string":"ETRI, University of Science and Technology MINSU JANG, ETRI","institution_ids":["https://openalex.org/I118692353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009537165","display_name":"Geehyuk Lee","orcid":"https://orcid.org/0000-0001-9674-6496"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Geehyuk Lee","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.3664,"has_fulltext":false,"cited_by_count":306,"citation_normalized_percentile":{"value":0.99364519,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"39","issue":"6","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9986000061035156,"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/T12290","display_name":"Human Motion and Animation","score":0.9965999722480774,"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/gesture","display_name":"Gesture","score":0.9326657056808472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.772296667098999},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5888819694519043},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4965830445289612},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.47614407539367676},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4368252158164978},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4324558973312378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4008178412914276},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36617663502693176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3626757562160492}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9326657056808472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772296667098999},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5888819694519043},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4965830445289612},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.47614407539367676},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4368252158164978},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4324558973312378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4008178412914276},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36617663502693176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3626757562160492},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3414685.3417838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3414685.3417838","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2009.02119","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02119","pdf_url":"https://arxiv.org/pdf/2009.02119","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.02119","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02119","pdf_url":"https://arxiv.org/pdf/2009.02119","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W42414577","https://openalex.org/W175626799","https://openalex.org/W1208039178","https://openalex.org/W1493478487","https://openalex.org/W1496828312","https://openalex.org/W1959608418","https://openalex.org/W1969681536","https://openalex.org/W1973282202","https://openalex.org/W2007337857","https://openalex.org/W2012844124","https://openalex.org/W2023890289","https://openalex.org/W2024536104","https://openalex.org/W2046033161","https://openalex.org/W2061009502","https://openalex.org/W2081580037","https://openalex.org/W2099471712","https://openalex.org/W2101032778","https://openalex.org/W2118163921","https://openalex.org/W2135431835","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2201822004","https://openalex.org/W2212290492","https://openalex.org/W2250539671","https://openalex.org/W2296371640","https://openalex.org/W2493916176","https://openalex.org/W2495266147","https://openalex.org/W2525579820","https://openalex.org/W2619383789","https://openalex.org/W2727071501","https://openalex.org/W2766171407","https://openalex.org/W2766736793","https://openalex.org/W2782290562","https://openalex.org/W2792764867","https://openalex.org/W2889326414","https://openalex.org/W2905488776","https://openalex.org/W2914848199","https://openalex.org/W2922298118","https://openalex.org/W2950133940","https://openalex.org/W2962785568","https://openalex.org/W2962795401","https://openalex.org/W2962896489","https://openalex.org/W2962897886","https://openalex.org/W2963185411","https://openalex.org/W2963373786","https://openalex.org/W2963544341","https://openalex.org/W2963981733","https://openalex.org/W2964308564","https://openalex.org/W2965813579","https://openalex.org/W2967443589","https://openalex.org/W2981802563","https://openalex.org/W2982625143","https://openalex.org/W2986302981","https://openalex.org/W2995801453","https://openalex.org/W3009042479","https://openalex.org/W3048625561","https://openalex.org/W3093647117","https://openalex.org/W3105974384","https://openalex.org/W4231374965"],"related_works":["https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735","https://openalex.org/W4322710567"],"abstract_inverted_index":{"For":[0],"human-like":[1,36,111],"agents,":[2],"including":[3],"virtual":[4],"avatars":[5],"and":[6,24,61,87,99,112,118,137,175,209],"social":[7],"robots,":[8],"making":[9],"proper":[10],"gestures":[11,20,37,65,108],"while":[12],"speaking":[13],"is":[14,32,148,161,199,211],"crucial":[15],"in":[16,168,193],"human-agent":[17],"interaction.":[18],"Co-speech":[19],"enhance":[21],"interaction":[22],"experiences":[23],"make":[25],"the":[26,40,59,80,104,134,143,185,194,207],"agents":[27],"look":[28],"alive.":[29],"However,":[30],"it":[31],"difficult":[33],"to":[34,39,51,90,163],"generate":[35,92],"due":[38],"lack":[41],"of":[42,44,64,83,203],"understanding":[43],"how":[45],"people":[46],"gesture.":[47],"Data-driven":[48],"approaches":[49],"attempt":[50],"learn":[52],"gesticulation":[53],"skills":[54],"from":[55,201],"human":[56,139],"demonstrations,":[57],"but":[58],"ambiguous":[60],"individual":[62],"nature":[63],"hinders":[66],"learning.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"present":[72],"an":[73,100],"automatic":[74],"gesture":[75,129,145,179],"generation":[76,130,146,153],"model":[77,106,147,160],"that":[78,109,113,142,158,177,198],"uses":[79],"multimodal":[81,97],"context":[82,98],"speech":[84,116,187],"text,":[85],"audio,":[86],"speaker":[88,191],"identity":[89],"reliably":[91],"gestures.":[93],"By":[94],"incorporating":[95],"a":[96,123,169],"adversarial":[101],"training":[102],"scheme,":[103],"proposed":[105,144],"outputs":[107],"are":[110,173],"match":[114],"with":[115,133,165],"content":[117],"rhythm.":[119],"We":[120,155],"also":[121],"introduce":[122],"new":[124],"quantitative":[125],"evaluation":[126,140],"metric":[127,136],"for":[128,184],"models.":[131,154],"Experiments":[132],"introduced":[135],"subjective":[138],"showed":[141],"better":[149],"than":[150],"existing":[151],"end-to-end":[152],"further":[156],"confirm":[157],"our":[159],"able":[162],"work":[164],"synthesized":[166],"audio":[167],"scenario":[170],"where":[171],"contexts":[172],"constrained,":[174],"show":[176],"different":[178,190],"styles":[180],"can":[181],"be":[182],"generated":[183],"same":[186],"by":[188],"specifying":[189],"identities":[192],"style":[195],"embedding":[196],"space":[197],"learned":[200],"videos":[202],"various":[204],"speakers.":[205],"All":[206],"code":[208],"data":[210],"available":[212],"at":[213],"https://github.com/ai4r/Gesture-Generation-from-Trimodal-Context.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":63},{"year":2024,"cited_by_count":81},{"year":2023,"cited_by_count":70},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2020-09-11T00:00:00"}
