{"id":"https://openalex.org/W4390094921","doi":"https://doi.org/10.1145/3570945.3607336","title":"How Far ahead Can Model Predict Gesture Pose from Speech and Spoken Text?","display_name":"How Far ahead Can Model Predict Gesture Pose from Speech and Spoken Text?","publication_year":2023,"publication_date":"2023-09-19","ids":{"openalex":"https://openalex.org/W4390094921","doi":"https://doi.org/10.1145/3570945.3607336"},"language":"en","primary_location":{"id":"doi:10.1145/3570945.3607336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570945.3607336","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570945.3607336","source":null,"license":null,"license_id":null,"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/10.1145/3570945.3607336","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101707624","display_name":"Ryo Ishii","orcid":"https://orcid.org/0009-0001-3849-1656"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryo Ishii","raw_affiliation_strings":["NTT Corporation, Minato-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Minato-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090499362","display_name":"Akira Morikawa","orcid":"https://orcid.org/0000-0001-8389-7463"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Morikawa","raw_affiliation_strings":["NTT Corporation, Minato-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Minato-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074511490","display_name":"Shin-ichiro Eitoku","orcid":"https://orcid.org/0000-0002-4351-3530"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinichiro Eitoku","raw_affiliation_strings":["NTT Corporation, Minato-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Minato-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091100876","display_name":"Atsushi Fukayama","orcid":"https://orcid.org/0000-0002-2133-016X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Fukayama","raw_affiliation_strings":["NTT Corporation, Minato-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Minato-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087962351","display_name":"Takao Nakamura","orcid":"https://orcid.org/0000-0001-8267-871X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Nakamura","raw_affiliation_strings":["NTT Corporation, Minato-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Minato-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101707624"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17458678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8268202543258667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7772889733314514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7124236822128296},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.6233047842979431},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45631372928619385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44531187415122986},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36410120129585266},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.15464547276496887},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14847612380981445}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8268202543258667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772889733314514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7124236822128296},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.6233047842979431},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45631372928619385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44531187415122986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36410120129585266},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.15464547276496887},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14847612380981445},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3570945.3607336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570945.3607336","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570945.3607336","source":null,"license":null,"license_id":null,"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"}],"best_oa_location":{"id":"doi:10.1145/3570945.3607336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570945.3607336","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570945.3607336","source":null,"license":null,"license_id":null,"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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390094921.pdf","grobid_xml":"https://content.openalex.org/works/W4390094921.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2080873731","https://openalex.org/W2884374054","https://openalex.org/W2901468574","https://openalex.org/W2901872500","https://openalex.org/W2901908010","https://openalex.org/W2922298118","https://openalex.org/W2962795401","https://openalex.org/W2963544341","https://openalex.org/W2967443589","https://openalex.org/W2981133004","https://openalex.org/W2981298105","https://openalex.org/W3002310794","https://openalex.org/W3008869465","https://openalex.org/W3009042479","https://openalex.org/W3042815677","https://openalex.org/W3083173864","https://openalex.org/W3094632886","https://openalex.org/W3098994456","https://openalex.org/W3115266783","https://openalex.org/W3122221177","https://openalex.org/W3124346429","https://openalex.org/W3132298525","https://openalex.org/W3163389380","https://openalex.org/W3172764674","https://openalex.org/W3181695292","https://openalex.org/W3194872882","https://openalex.org/W3198131199","https://openalex.org/W3207529040","https://openalex.org/W3210580323","https://openalex.org/W4200033096","https://openalex.org/W4230429791","https://openalex.org/W4256361765","https://openalex.org/W4285981714","https://openalex.org/W4292945985","https://openalex.org/W4302915556","https://openalex.org/W4303448003","https://openalex.org/W4308222673","https://openalex.org/W4308222716","https://openalex.org/W4310895557","https://openalex.org/W4312462635","https://openalex.org/W4312655468","https://openalex.org/W4312719027","https://openalex.org/W4316829872","https://openalex.org/W4364377334","https://openalex.org/W4380264398","https://openalex.org/W6840001710","https://openalex.org/W7053040589"],"related_works":["https://openalex.org/W2066003895","https://openalex.org/W2537963312","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2164899521","https://openalex.org/W2782095833"],"abstract_inverted_index":{"We":[0],"investigated":[1],"how":[2,44],"far":[3,45],"into":[4,46],"the":[5,34,37,47,69,72,77,96,123],"future":[6,24,48,102,124],"nonverbal":[7,78],"behavior":[8,49,79],"can":[9,50,87],"be":[10,51,88],"predicted":[11,89],"from":[12,26],"speech":[13,15,27,29,64,66,74,117,119],"and":[14,28,32,65,75,118],"text.":[16],"Specifically,":[17],"we":[18],"build":[19],"a":[20,109],"model":[21],"that":[22,58,94],"generates":[23],"behaviors":[25],"text":[30,120],"information":[31],"evaluate":[33],"quality":[35],"of":[36,71],"generated":[38],"behaviors.":[39],"This":[40,106],"helps":[41],"to":[42,81,121,126],"clarify":[43],"accurately":[52],"predicted.":[53],"Our":[54],"experimental":[55],"results":[56],"show":[57],"in":[59],"Gesture":[60,113],"Pose":[61,114],"Generation":[62,115],"using":[63,116],"text,":[67,76],"on":[68],"basis":[70],"input":[73],"up":[80,125],"at":[82,127],"least":[83,128],"500":[84,129],"ms":[85,130],"ahead":[86,131],"with":[90,132],"objective":[91],"evaluation":[92],"values":[93],"are":[95],"same":[97],"as":[98],"those":[99],"when":[100],"no":[101,133],"prediction":[103],"is":[104],"made.":[105],"result":[107],"shows":[108],"new":[110],"possibility":[111],"for":[112],"predict":[122],"performance":[134],"degradation.":[135]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}