{"id":"https://openalex.org/W3188493377","doi":"https://doi.org/10.1145/3474085.3475223","title":"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning","display_name":"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3188493377","doi":"https://doi.org/10.1145/3474085.3475223","mag":"3188493377"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","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/2108.00262","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042584669","display_name":"Uttaran Bhattacharya","orcid":"https://orcid.org/0000-0003-2141-9276"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Uttaran Bhattacharya","raw_affiliation_strings":["University of Maryland, College Park, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114626423","display_name":"Elizabeth Childs","orcid":"https://orcid.org/0000-0002-5768-6029"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Childs","raw_affiliation_strings":["University of Maryland, College Park, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011535172","display_name":"Nicholas Rewkowski","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas Rewkowski","raw_affiliation_strings":["University of Maryland, College Park, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland, College Park, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2027","last_page":"2036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9972000122070312,"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":0.9972000122070312,"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/T12031","display_name":"Speech and dialogue systems","score":0.9952999949455261,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9922999739646912,"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/gesture","display_name":"Gesture","score":0.8384968042373657},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7729755640029907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.704839289188385},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.6291346549987793},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.610284686088562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5247081518173218},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39650943875312805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39289039373397827},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34813570976257324},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08517712354660034}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8384968042373657},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7729755640029907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704839289188385},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.6291346549987793},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.610284686088562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5247081518173218},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39650943875312805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39289039373397827},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34813570976257324},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08517712354660034}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3474085.3475223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.00262","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.00262","pdf_url":"https://arxiv.org/pdf/2108.00262","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:2108.00262","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.00262","pdf_url":"https://arxiv.org/pdf/2108.00262","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G3867936446","display_name":null,"funder_award_id":"W911NF1910069, W911NF1910315","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W579975518","https://openalex.org/W1208039178","https://openalex.org/W1490440056","https://openalex.org/W1522301498","https://openalex.org/W1544484417","https://openalex.org/W1777859530","https://openalex.org/W1844030040","https://openalex.org/W2007041320","https://openalex.org/W2007337857","https://openalex.org/W2014002306","https://openalex.org/W2024221294","https://openalex.org/W2072956256","https://openalex.org/W2101032778","https://openalex.org/W2103075368","https://openalex.org/W2109636054","https://openalex.org/W2118163921","https://openalex.org/W2141493634","https://openalex.org/W2151215842","https://openalex.org/W2169025255","https://openalex.org/W2296371640","https://openalex.org/W2462512047","https://openalex.org/W2469134594","https://openalex.org/W2493916176","https://openalex.org/W2495266147","https://openalex.org/W2611706523","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2747308422","https://openalex.org/W2786842250","https://openalex.org/W2802076562","https://openalex.org/W2808005485","https://openalex.org/W2883409523","https://openalex.org/W2896593898","https://openalex.org/W2901285216","https://openalex.org/W2901466962","https://openalex.org/W2901872500","https://openalex.org/W2916507371","https://openalex.org/W2922298118","https://openalex.org/W2945556097","https://openalex.org/W2953623390","https://openalex.org/W2962713165","https://openalex.org/W2962795401","https://openalex.org/W2963076818","https://openalex.org/W2963351004","https://openalex.org/W2963544341","https://openalex.org/W2967443589","https://openalex.org/W2968990787","https://openalex.org/W2974177253","https://openalex.org/W2981271350","https://openalex.org/W2981802563","https://openalex.org/W2982294548","https://openalex.org/W2982625143","https://openalex.org/W2986708244","https://openalex.org/W2991276178","https://openalex.org/W3002310794","https://openalex.org/W3009042479","https://openalex.org/W3083173864","https://openalex.org/W3087580124","https://openalex.org/W3090160436","https://openalex.org/W3093647117","https://openalex.org/W3098699623","https://openalex.org/W3099073275","https://openalex.org/W3103543904","https://openalex.org/W3109709077","https://openalex.org/W3124346429","https://openalex.org/W3125775899","https://openalex.org/W3133090439","https://openalex.org/W3153551559","https://openalex.org/W3181695292","https://openalex.org/W4206566734","https://openalex.org/W4225837128","https://openalex.org/W4230312136","https://openalex.org/W4310301283"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W2537963312","https://openalex.org/W2066003895","https://openalex.org/W2537762514","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492"],"abstract_inverted_index":{"We":[0,61,92,112,150,201],"present":[1],"a":[2,25,31,47,204],"generative":[3],"adversarial":[4],"network":[5,20],"to":[6,27,49,82,102,130,144,175,211],"synthesize":[7,28],"3D":[8,58,104],"pose":[9,54,59,105],"sequences":[10,55,106],"of":[11,22,35,218,230],"co-speech":[12],"upper-body":[13],"gestures":[14,29,143,223,234],"with":[15,241],"appropriate":[16,147,237],"affective":[17,90,95,110,115,124,148,238],"expressions.":[18,149],"Our":[19],"consists":[21],"two":[23,155],"components:":[24],"generator":[26,81],"from":[30,38,72,126,161],"joint":[32,184],"embedding":[33],"space":[34],"features":[36,125],"encoded":[37],"the":[39,43,52,63,68,73,84,88,127,132,141,146,162,164,169,176,181,188,195,212,233,242],"input":[40,74],"speech":[41,75],"and":[42,46,56,67,87,135,168,194,207,227],"seed":[44,128],"poses,":[45],"discriminator":[48],"distinguish":[50],"between":[51],"synthesized":[53,142,222],"real":[57],"sequences.":[60],"leverage":[62],"Mel-frequency":[64],"cepstral":[65],"coefficients":[66],"text":[69],"transcript":[70],"computed":[71],"in":[76,79,117],"separate":[77],"encoders":[78],"our":[80,114,119,136,221],"learn":[83],"desired":[85],"sentiments":[86],"associated":[89],"cues.":[91],"design":[93],"an":[94],"encoder":[96,116],"using":[97],"multi-scale":[98],"spatial-temporal":[99],"graph":[100],"convolutions":[101],"transform":[103],"into":[107],"latent,":[108],"pose-based":[109],"features.":[111],"use":[113],"both":[118],"generator,":[120],"where":[121,138],"it":[122,139],"learns":[123],"poses":[129],"guide":[131],"gesture":[133,159],"synthesis,":[134],"discriminator,":[137],"enforces":[140],"contain":[145],"perform":[151],"extensive":[152],"evaluations":[153],"on":[154],"benchmark":[156],"datasets":[157],"for":[158],"synthesis":[160],"speech,":[163],"TED":[165],"Gesture":[166,197],"Dataset":[167],"GENEA":[170],"Challenge":[171],"2020":[172],"Dataset.":[173],"Compared":[174],"best":[177,213],"baselines,":[178,215],"we":[179],"improve":[180],"mean":[182,189],"absolute":[183],"error":[185],"by":[186,192,199],"10-33%,":[187],"acceleration":[190],"difference":[191],"8-58%,":[193],"Fr\u00e9chet":[196],"Distance":[198],"21-34%.":[200],"also":[202],"conduct":[203],"user":[205],"study":[206],"observe":[208],"that":[209],"compared":[210],"current":[214],"around":[216,228],"15.28%":[217],"participants":[219,231],"indicated":[220],"appear":[224],"more":[225,236],"plausible,":[226],"16.32%":[229],"felt":[232],"had":[235],"expressions":[239],"aligned":[240],"speech.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":12}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}