{"id":"https://openalex.org/W2901872500","doi":"https://doi.org/10.1145/3267851.3267878","title":"Evaluation of Speech-to-Gesture Generation Using Bi-Directional LSTM Network","display_name":"Evaluation of Speech-to-Gesture Generation Using Bi-Directional LSTM Network","publication_year":2018,"publication_date":"2018-11-05","ids":{"openalex":"https://openalex.org/W2901872500","doi":"https://doi.org/10.1145/3267851.3267878","mag":"2901872500"},"language":"en","primary_location":{"id":"doi:10.1145/3267851.3267878","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3267851.3267878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111467265","display_name":"Dai Hasegawa","orcid":null},"institutions":[{"id":"https://openalex.org/I91764395","display_name":"Hokkai Gakuen University","ror":"https://ror.org/05h9h0e34","country_code":"JP","type":"education","lineage":["https://openalex.org/I91764395"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Dai Hasegawa","raw_affiliation_strings":["Hokkai Gakuen University Sapporo, Japan"],"affiliations":[{"raw_affiliation_string":"Hokkai Gakuen University Sapporo, Japan","institution_ids":["https://openalex.org/I91764395"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011769227","display_name":"Naoshi Kaneko","orcid":"https://orcid.org/0000-0002-5638-2509"},"institutions":[{"id":"https://openalex.org/I131231118","display_name":"Aoyama Gakuin University","ror":"https://ror.org/002rw7y37","country_code":"JP","type":"education","lineage":["https://openalex.org/I131231118"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoshi Kaneko","raw_affiliation_strings":["Aoyama Gakuin University, Japan Sagamihara, Japan"],"affiliations":[{"raw_affiliation_string":"Aoyama Gakuin University, Japan Sagamihara, Japan","institution_ids":["https://openalex.org/I131231118"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005268349","display_name":"Shinichi Shirakawa","orcid":"https://orcid.org/0000-0002-4659-6108"},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinichi Shirakawa","raw_affiliation_strings":["Yokohama National University, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Yokohama National University, Yokohama, Japan","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020190687","display_name":"Hiroshi Sakuta","orcid":null},"institutions":[{"id":"https://openalex.org/I131231118","display_name":"Aoyama Gakuin University","ror":"https://ror.org/002rw7y37","country_code":"JP","type":"education","lineage":["https://openalex.org/I131231118"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sakuta","raw_affiliation_strings":["Aoyama Gakuin University, Japan Sagamihara, Japan"],"affiliations":[{"raw_affiliation_string":"Aoyama Gakuin University, Japan Sagamihara, Japan","institution_ids":["https://openalex.org/I131231118"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620014","display_name":"Kazuhiko Sumi","orcid":"https://orcid.org/0000-0002-9165-5912"},"institutions":[{"id":"https://openalex.org/I131231118","display_name":"Aoyama Gakuin University","ror":"https://ror.org/002rw7y37","country_code":"JP","type":"education","lineage":["https://openalex.org/I131231118"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiko Sumi","raw_affiliation_strings":["Aoyama Gakuin University, Japan Sagamihara, Japan"],"affiliations":[{"raw_affiliation_string":"Aoyama Gakuin University, Japan Sagamihara, Japan","institution_ids":["https://openalex.org/I131231118"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111467265"],"corresponding_institution_ids":["https://openalex.org/I91764395"],"apc_list":null,"apc_paid":null,"fwci":8.1496,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":{"value":0.97966436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998000264167786,"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":0.9994000196456909,"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":0.9988999962806702,"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":0.9209814071655273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7829676270484924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6928232312202454},{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.6734259724617004},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6119315028190613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5014755725860596},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.45948824286460876},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.45700016617774963},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32589462399482727}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.9209814071655273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829676270484924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6928232312202454},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.6734259724617004},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6119315028190613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5014755725860596},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.45948824286460876},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.45700016617774963},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32589462399482727},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3267851.3267878","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3267851.3267878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W114912394","https://openalex.org/W164929510","https://openalex.org/W216945601","https://openalex.org/W1208039178","https://openalex.org/W1504784536","https://openalex.org/W1549941057","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1936750108","https://openalex.org/W2024590593","https://openalex.org/W2027222744","https://openalex.org/W2037859676","https://openalex.org/W2074788634","https://openalex.org/W2079735306","https://openalex.org/W2095705004","https://openalex.org/W2118163921","https://openalex.org/W2128123720","https://openalex.org/W2131774270","https://openalex.org/W2135533529","https://openalex.org/W2148154194","https://openalex.org/W2150692719","https://openalex.org/W2155643851","https://openalex.org/W2235920218","https://openalex.org/W2612744935","https://openalex.org/W2964121744","https://openalex.org/W3013901159"],"related_works":["https://openalex.org/W2549567669","https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W3147379364","https://openalex.org/W2010878661","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735"],"abstract_inverted_index":{"We":[0,76,93],"present":[1],"a":[2,18,35,43,49,78,83,98,114],"novel":[3],"framework":[4],"to":[5,69,89,134,152],"automatically":[6],"generate":[7],"natural":[8],"gesture":[9,139],"motions":[10],"accompanying":[11],"speech":[12],"from":[13,51,55,113],"audio":[14,58],"utterances.":[15],"Based":[16],"on":[17],"Bi-Directional":[19],"LSTM":[20],"Network,":[21],"our":[22,91,95,122],"deep":[23],"network":[24,41],"learns":[25],"speech-gesture":[26,79],"relationships":[27],"with":[28,82,97,132],"both":[29],"backward":[30],"and":[31,85,101,108],"forward":[32],"consistencies":[33],"over":[34],"long":[36],"period":[37],"of":[38,48,147],"time.":[39],"Our":[40],"regresses":[42],"full":[44],"3D":[45],"skeletal":[46],"pose":[47,74],"human":[50,106,110],"perceptual":[52],"features":[53],"extracted":[54],"the":[56,72,129],"input":[57],"in":[59,145],"each":[60],"time":[61,135],"step.":[62],"Then,":[63],"we":[64],"apply":[65],"combined":[66],"temporal":[67],"filters":[68],"smooth":[70],"out":[71],"generated":[73,123,138],"sequences.":[75],"utilize":[77],"dataset":[80],"recorded":[81],"headset":[84],"marker-based":[86],"motion":[87],"capture":[88],"train":[90],"network.":[92],"validated":[94],"approach":[96],"subjective":[99],"evaluation":[100,118],"compared":[102,151],"it":[103],"against":[104],"\"original\"":[105],"gestures":[107,111,124,131],"\"mismatched\"":[109,130,153],"taken":[112],"different":[115],"utterance.":[116],"The":[117,137],"result":[119],"shows":[120,141],"that":[121],"are":[125],"significantly":[126],"better":[127],"than":[128],"respect":[133],"consistency.":[136],"also":[140],"marginally":[142],"significant":[143],"improvement":[144],"terms":[146],"semantic":[148],"consistency":[149],"when":[150],"gestures.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":12}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}