{"id":"https://openalex.org/W2922298118","doi":"https://doi.org/10.1145/3308532.3329472","title":"Analyzing Input and Output Representations for Speech-Driven Gesture Generation","display_name":"Analyzing Input and Output Representations for Speech-Driven Gesture Generation","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2922298118","doi":"https://doi.org/10.1145/3308532.3329472","mag":"2922298118"},"language":"en","primary_location":{"id":"doi:10.1145/3308532.3329472","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3308532.3329472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents","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/1903.03369","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034104476","display_name":"Taras Kucherenko","orcid":"https://orcid.org/0000-0001-9838-8848"},"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 in Stockholm, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology in Stockholm, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","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":false,"raw_author_name":"Dai Hasegawa","raw_affiliation_strings":["Hokkai Gakuen University, Sapporo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkai Gakuen University, Sapporo, Japan","institution_ids":["https://openalex.org/I91764395"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"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 in Stockholm, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology in Stockholm, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"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, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aoyama Gakuin University, Tokyo, Japan","institution_ids":["https://openalex.org/I131231118"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021003965","display_name":"Hedvig Kjellstr\u00f6m","orcid":"https://orcid.org/0000-0002-5750-9655"},"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 in Stockholm, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology in Stockholm, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":32.93,"has_fulltext":false,"cited_by_count":154,"citation_normalized_percentile":{"value":0.99922431,"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":"97","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9998000264167786,"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":0.9998000264167786,"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/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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7810511589050293},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7337442636489868},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6918573379516602},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6214745044708252},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5813692212104797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.560977578163147},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.48827362060546875},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.48330259323120117},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4829532504081726},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4179891347885132},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3444376289844513},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3363131880760193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810511589050293},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7337442636489868},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6918573379516602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6214745044708252},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5813692212104797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.560977578163147},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.48827362060546875},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.48330259323120117},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4829532504081726},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4179891347885132},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3444376289844513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3363131880760193},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3308532.3329472","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3308532.3329472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.03369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.03369","pdf_url":"https://arxiv.org/pdf/1903.03369","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.03369","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.03369","pdf_url":"https://arxiv.org/pdf/1903.03369","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W114912394","https://openalex.org/W579975518","https://openalex.org/W1208039178","https://openalex.org/W1522301498","https://openalex.org/W1534876773","https://openalex.org/W1544484417","https://openalex.org/W1875231349","https://openalex.org/W1969784320","https://openalex.org/W2007337857","https://openalex.org/W2024649868","https://openalex.org/W2039376592","https://openalex.org/W2058079053","https://openalex.org/W2078082557","https://openalex.org/W2118163921","https://openalex.org/W2145094598","https://openalex.org/W2148154194","https://openalex.org/W2163334800","https://openalex.org/W2172140247","https://openalex.org/W2235920218","https://openalex.org/W2296371640","https://openalex.org/W2296629652","https://openalex.org/W2469134594","https://openalex.org/W2502094132","https://openalex.org/W2560662850","https://openalex.org/W2593390416","https://openalex.org/W2594167370","https://openalex.org/W2612744935","https://openalex.org/W2738406145","https://openalex.org/W2745980686","https://openalex.org/W2747308422","https://openalex.org/W2766709201","https://openalex.org/W2784473436","https://openalex.org/W2801567109","https://openalex.org/W2802076562","https://openalex.org/W2802441648","https://openalex.org/W2803747201","https://openalex.org/W2895551801","https://openalex.org/W2901468574","https://openalex.org/W2901872500","https://openalex.org/W2945664519","https://openalex.org/W2963389355","https://openalex.org/W2963544341","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964203186","https://openalex.org/W2967443589","https://openalex.org/W2986302981","https://openalex.org/W2997574889","https://openalex.org/W3152485530","https://openalex.org/W3177525997","https://openalex.org/W4235821942","https://openalex.org/W4252434905","https://openalex.org/W4299390018","https://openalex.org/W4385490321"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,51],"novel":[4],"framework":[5],"for":[6,28],"automatic":[7],"speech-driven":[8,29],"gesture":[9,30],"generation,":[10],"applicable":[11],"to":[12],"human-agent":[13],"interaction":[14],"including":[15],"both":[16],"virtual":[17],"agents":[18],"and":[19,42],"robots.":[20],"Specifically,":[21],"we":[22],"extend":[23],"recent":[24],"deep-learning-based,":[25],"data-driven":[26],"methods":[27],"generation":[31],"by":[32],"incorporating":[33],"representation":[34],"learning.":[35],"Our":[36],"model":[37],"takes":[38],"speech":[39],"as":[40,45],"input":[41],"produces":[43],"gestures":[44],"output,":[46],"in":[47],"the":[48],"form":[49],"of":[50,53],"sequence":[52],"3D":[54],"coordinates.":[55]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}