{"id":"https://openalex.org/W3207529040","doi":"https://doi.org/10.1145/3461615.3485407","title":"Probabilistic Human-like Gesture Synthesis from Speech using GRU-based WGAN","display_name":"Probabilistic Human-like Gesture Synthesis from Speech using GRU-based WGAN","publication_year":2021,"publication_date":"2021-10-18","ids":{"openalex":"https://openalex.org/W3207529040","doi":"https://doi.org/10.1145/3461615.3485407","mag":"3207529040"},"language":"en","primary_location":{"id":"doi:10.1145/3461615.3485407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3485407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101512079","display_name":"Bowen Wu","orcid":"https://orcid.org/0000-0001-6631-8722"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Bowen Wu","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Japan and Interactive Robot Research Team, RIKEN Guardian Robot Project, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan and Interactive Robot Research Team, RIKEN Guardian Robot Project, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905297","display_name":"Chaoran Liu","orcid":"https://orcid.org/0000-0003-3789-2981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaoran Liu","raw_affiliation_strings":["ATR, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000037110","display_name":"Carlos Toshinori Ishi","orcid":"https://orcid.org/0000-0001-8130-1048"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos T. Ishi","raw_affiliation_strings":["Interactive Robot Research Team, RIKEN Guardian Robot Project, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Robot Research Team, RIKEN Guardian Robot Project, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101425832","display_name":"Hiroshi Ishiguro","orcid":"https://orcid.org/0000-0002-0805-7648"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Ishiguro","raw_affiliation_strings":["Graduate School of Engineering Science, Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T12290","display_name":"Human Motion and Animation","score":0.9976999759674072,"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/discriminator","display_name":"Discriminator","score":0.8376440405845642},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.8314274549484253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7954604625701904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5690141916275024},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5359808802604675},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5082659125328064},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.4687034785747528},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4572025239467621},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.41262978315353394},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3281231224536896},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.09309539198875427},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07237833738327026}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8376440405845642},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8314274549484253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954604625701904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690141916275024},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5359808802604675},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5082659125328064},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.4687034785747528},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4572025239467621},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.41262978315353394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3281231224536896},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.09309539198875427},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07237833738327026},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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:10.1145/3461615.3485407","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3485407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6899999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2021174319","https://openalex.org/W2612744935","https://openalex.org/W2802076562","https://openalex.org/W2884374054","https://openalex.org/W2887511658","https://openalex.org/W2901468574","https://openalex.org/W2901872500","https://openalex.org/W2922298118","https://openalex.org/W2981802563","https://openalex.org/W3002310794","https://openalex.org/W3042815677","https://openalex.org/W3083173864","https://openalex.org/W3098994456","https://openalex.org/W3099073275","https://openalex.org/W3113116087","https://openalex.org/W3115266783","https://openalex.org/W3125277150","https://openalex.org/W3125775899","https://openalex.org/W3132298525"],"related_works":["https://openalex.org/W4293202849","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"],"abstract_inverted_index":{"Gestures":[0],"are":[1,28,101],"crucial":[2],"for":[3,52,147],"increasing":[4],"the":[5,31,77,81,84,98,113,129],"human-likeness":[6],"of":[7,19,80],"agents":[8],"and":[9,87,107,143],"robots":[10],"to":[11,23,36,75,89,139],"achieve":[12],"smoother":[13],"interactions":[14],"with":[15,30,58],"humans.":[16],"The":[17,71,94],"realization":[18],"an":[20,63,104],"effective":[21],"system":[22,100],"model":[24,51,72,115,119],"human":[25],"gestures,":[26],"which":[27,55,120],"matched":[29],"speech":[32],"utterances,":[33],"is":[34,56,73,121,137],"necessary":[35],"be":[37,155],"embedded":[38],"in":[39,62,83,157],"these":[40],"agents.":[41],"In":[42],"this":[43],"work,":[44],"we":[45],"propose":[46],"a":[47,59,67,91,108,117,124,141],"GRU-based":[48],"autoregressive":[49],"generation":[50,150],"gesture":[53,149],"generation,":[54],"trained":[57,74,122],"CNN-based":[60],"discriminator":[61],"adversarial":[64],"manner":[65],"using":[66,128],"WGAN-based":[68],"learning":[69,145],"algorithm.":[70],"output":[76],"rotation":[78],"angles":[79],"joints":[82],"upper":[85],"body,":[86],"implemented":[88],"animate":[90],"CG":[92],"avatar.":[93],"motions":[95],"synthesized":[96],"by":[97,123],"proposed":[99,114],"evaluated":[102],"via":[103],"objective":[105],"measure":[106],"subjective":[109],"experiment,":[110],"showing":[111],"that":[112,135],"outperforms":[116],"baseline":[118],"state-of-the-art":[125],"GAN-based":[126],"algorithm,":[127],"same":[130],"dataset.":[131],"This":[132],"result":[133],"reveals":[134],"it":[136],"essential":[138],"develop":[140],"stable":[142],"robust":[144],"algorithm":[146],"training":[148],"models.":[151],"Our":[152],"code":[153],"can":[154],"found":[156],"https://github.com/wubowen416/gesture-generation.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}