{"id":"https://openalex.org/W4403276822","doi":"https://doi.org/10.1109/thms.2024.3456085","title":"Speech-Driven Gesture Generation Using Transformer-Based Denoising Diffusion Probabilistic Models","display_name":"Speech-Driven Gesture Generation Using Transformer-Based Denoising Diffusion Probabilistic Models","publication_year":2024,"publication_date":"2024-10-09","ids":{"openalex":"https://openalex.org/W4403276822","doi":"https://doi.org/10.1109/thms.2024.3456085"},"language":"en","primary_location":{"id":"doi:10.1109/thms.2024.3456085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2024.3456085","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Human-Machine Systems","raw_type":"journal-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/A5030184265","display_name":"Bowen Wu","orcid":"https://orcid.org/0000-0001-8518-2939"},"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, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8518-2939","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Osaka, 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":["Guardian Robot Project, RIKEN, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3789-2981","affiliations":[{"raw_affiliation_string":"Guardian Robot Project, RIKEN, Kyoto, 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 Toshinori Ishi","raw_affiliation_strings":["Guardian Robot Project, RIKEN, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8130-1048","affiliations":[{"raw_affiliation_string":"Guardian Robot Project, RIKEN, Kyoto, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012895752","display_name":"Hiroshi Ishiguro","orcid":"https://orcid.org/0000-0002-3603-0987"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroshi Ishiguro","raw_affiliation_strings":["Hiroshi Ishiguro Laboratories, ATR, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hiroshi Ishiguro Laboratories, ATR, Kyoto, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2788,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55231728,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"54","issue":"6","first_page":"733","last_page":"742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9883000254631042,"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":0.9883000254631042,"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/T12031","display_name":"Speech and dialogue systems","score":0.9523000121116638,"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/T10860","display_name":"Speech and Audio Processing","score":0.9056000113487244,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.6831879019737244},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5928134918212891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5532745122909546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5409501791000366},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5047012567520142},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4944593906402588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.329437255859375},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16750013828277588},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12255489826202393},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0483299195766449}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6831879019737244},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5928134918212891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5532745122909546},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5409501791000366},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5047012567520142},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4944593906402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.329437255859375},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16750013828277588},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12255489826202393},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0483299195766449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/thms.2024.3456085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/thms.2024.3456085","pdf_url":null,"source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Human-Machine Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1498883201","https://openalex.org/W1901129140","https://openalex.org/W1969962548","https://openalex.org/W2559085405","https://openalex.org/W2612744935","https://openalex.org/W2896457183","https://openalex.org/W2897056786","https://openalex.org/W2901285216","https://openalex.org/W2901872500","https://openalex.org/W2922298118","https://openalex.org/W2922443216","https://openalex.org/W2962770929","https://openalex.org/W2962795401","https://openalex.org/W2964203186","https://openalex.org/W2967443589","https://openalex.org/W2982625143","https://openalex.org/W3002310794","https://openalex.org/W3006913151","https://openalex.org/W3009042479","https://openalex.org/W3042815677","https://openalex.org/W3083173864","https://openalex.org/W3110095664","https://openalex.org/W3118288752","https://openalex.org/W3124346429","https://openalex.org/W3125277150","https://openalex.org/W3153832461","https://openalex.org/W3177709384","https://openalex.org/W3197859103","https://openalex.org/W3207529040","https://openalex.org/W4221142137","https://openalex.org/W4312674262","https://openalex.org/W4313071962","https://openalex.org/W4364377334","https://openalex.org/W4376226279","https://openalex.org/W4385284180","https://openalex.org/W4385764101","https://openalex.org/W4386076103","https://openalex.org/W4387421716","https://openalex.org/W4387446239","https://openalex.org/W4391305822","https://openalex.org/W6631190155","https://openalex.org/W6679045638","https://openalex.org/W6739901393","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783713337","https://openalex.org/W6788328477","https://openalex.org/W6788990321","https://openalex.org/W6795288823","https://openalex.org/W6802527329","https://openalex.org/W6804146617","https://openalex.org/W6810940779","https://openalex.org/W6840815571","https://openalex.org/W6849941170"],"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/W1982853263","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2796116650"],"abstract_inverted_index":{"While":[0],"it":[1,72],"is":[2,30,114],"crucial":[3],"for":[4,43,68,75,127],"human-like":[5,129],"avatars":[6,130],"to":[7,14,32,46],"perform":[8],"co-speech":[9,34],"gestures,":[10],"existing":[11],"approaches":[12],"struggle":[13],"generate":[15,33],"natural":[16],"and":[17,61,99,131],"realistic":[18],"movements.":[19],"In":[20],"the":[21,48,51,57,117,121],"present":[22],"study,":[23,102],"a":[24,39,76,100,124],"novel":[25],"transformer-based":[26],"denoising":[27],"diffusion":[28,44],"model":[29,64,87,106],"proposed":[31],"gestures.":[35],"Moreover,":[36],"we":[37],"introduce":[38],"practical":[40],"sampling":[41],"trick":[42],"models":[45],"maintain":[47],"continuity":[49],"between":[50],"generated":[52],"motion":[53,59],"segments":[54],"while":[55],"improving":[56],"within-segment":[58],"likelihood":[60],"naturalness.":[62],"Our":[63,111],"can":[65],"be":[66],"used":[67],"online":[69],"generation":[70],"since":[71],"generates":[73],"gestures":[74],"short":[77],"segment":[78],"of":[79],"speech,":[80],"e.g.,":[81],"2":[82],"s.":[83],"We":[84],"evaluate":[85],"our":[86,105],"on":[88,116],"two":[89],"large-scale":[90],"speech-gesture":[91],"datasets":[92],"with":[93],"finger":[94],"movements":[95],"using":[96],"objective":[97],"measurements":[98],"user":[101,112],"showing":[103],"that":[104],"outperforms":[107],"all":[108],"other":[109],"baselines.":[110],"study":[113],"based":[115],"Metahuman":[118],"platform":[119],"in":[120],"Unreal":[122],"Engine,":[123],"popular":[125],"tool":[126],"creating":[128],"motions.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
