{"id":"https://openalex.org/W7163512145","doi":"https://doi.org/10.1109/lra.2026.3700424","title":"Speech-Driven Gesture Generation via Conditional Flow Matching With Masked Training and Clamped Sampling","display_name":"Speech-Driven Gesture Generation via Conditional Flow Matching With Masked Training and Clamped Sampling","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163512145","doi":"https://doi.org/10.1109/lra.2026.3700424"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3700424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3700424","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5137878970","display_name":"Bowen Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Wu","raw_affiliation_strings":["RIKEN, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8518-2939","affiliations":[{"raw_affiliation_string":"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":["RIKEN, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8130-1048","affiliations":[{"raw_affiliation_string":"RIKEN, Kyoto, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057967837","display_name":"Takashi Minato","orcid":"https://orcid.org/0000-0003-4071-1352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Minato","raw_affiliation_strings":["RIKEN, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4071-1352","affiliations":[{"raw_affiliation_string":"RIKEN, Kyoto, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137877379","display_name":"Hiroshi Ishiguro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroshi Ishiguro","raw_affiliation_strings":["ATR, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0805-7648","affiliations":[{"raw_affiliation_string":"ATR, Kyoto, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70155572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"7","first_page":"8720","last_page":"8727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.3553999960422516,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.3553999960422516,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.10369999706745148,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.08240000158548355,"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/sampling","display_name":"Sampling (signal processing)","score":0.5098000168800354},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5072000026702881},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5024999976158142},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.37860000133514404},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.3698999881744385},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6434000134468079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5978999733924866},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5098000168800354},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4542999863624573},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3659999966621399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.33559998869895935},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3700424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3700424","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,25,42,89,123],"perform":[3],"co-speech":[4,27],"gestures":[5,28],"is":[6],"essential":[7],"for":[8],"robots":[9],"with":[10],"human-like":[11],"appearances.":[12],"In":[13,87],"this":[14],"paper,":[15],"we":[16,33,96],"present":[17],"a":[18,120],"novel":[19],"conditional":[20],"flow":[21],"matching-based":[22],"generative":[23],"model":[24],"generate":[26],"from":[29],"speech":[30,54,85],"input.":[31],"Moreover,":[32],"propose":[34],"masked":[35,40,57],"training":[36],"and":[37,69],"the":[38,115,125],"corresponding":[39],"generation":[41,58],"ensure":[43],"smooth":[44],"transitions":[45],"in":[46,79],"sequential":[47],"gesture":[48,64,80],"movements":[49],"when":[50],"processing":[51],"segmented,":[52],"long":[53],"inputs.":[55],"Furthermore,":[56],"inherently":[59],"supports":[60],"general":[61],"purpose":[62],"partial":[63],"completion.":[65],"While":[66],"objective":[67],"evaluation":[68],"user":[70],"study":[71],"confirm":[72],"that":[73,112],"our":[74],"method":[75],"outperforms":[76],"existing":[77],"baselines":[78],"naturalness,":[81],"it":[82],"shows":[83],"weak":[84],"appropriateness.":[86],"addition,":[88],"enable":[90],"direct":[91],"deployment":[92],"on":[93],"humanoid":[94],"robots,":[95],"introduce":[97],"clamped":[98,128],"sampling":[99],"which":[100],"enforces":[101],"physical":[102],"limits":[103],"during":[104],"generation,":[105],"thereby":[106],"avoiding":[107],"hard":[108],"post-processing":[109],"(e.g.,":[110],"clamping)":[111],"may":[113],"distort":[114],"intended":[116],"gestures.":[117],"We":[118],"conducted":[119],"proof-of-concept":[121],"experiment":[122],"demonstrate":[124],"efficacy":[126],"of":[127],"sampling.":[129]},"counts_by_year":[],"updated_date":"2026-06-12T06:20:11.936012","created_date":"2026-06-05T00:00:00"}