{"id":"https://openalex.org/W4387446360","doi":"https://doi.org/10.1145/3610661.3616554","title":"Gesture Generation with Diffusion Models Aided by Speech Activity Information","display_name":"Gesture Generation with Diffusion Models Aided by Speech Activity Information","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4387446360","doi":"https://doi.org/10.1145/3610661.3616554"},"language":"en","primary_location":{"id":"doi:10.1145/3610661.3616554","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610661.3616554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","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/A5043095306","display_name":"Rodolfo Luis Tonoli","orcid":"https://orcid.org/0000-0002-5800-654X"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rodolfo L. Tonoli","raw_affiliation_strings":["Dept. of Computer Engineering and Automation, School of Electrical and Computer Engineering, University of Campinas (UNICAMP), Brazil and Artificial Intelligence Lab., Recod.ai, University of Campinas (UNICAMP), Brazil"],"raw_orcid":"https://orcid.org/0000-0002-5800-654X","affiliations":[{"raw_affiliation_string":"Dept. of Computer Engineering and Automation, School of Electrical and Computer Engineering, University of Campinas (UNICAMP), Brazil and Artificial Intelligence Lab., Recod.ai, University of Campinas (UNICAMP), Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073917855","display_name":"Leonardo B. de M. M. Marques","orcid":"https://orcid.org/0000-0002-8821-4972"},"institutions":[{"id":"https://openalex.org/I4210090141","display_name":"Centre for Research and Development in Telecommunications (Brazil)","ror":"https://ror.org/00ej99c12","country_code":"BR","type":"company","lineage":["https://openalex.org/I4210090141"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo B. de M. M. Marques","raw_affiliation_strings":["CPQD, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-8821-4972","affiliations":[{"raw_affiliation_string":"CPQD, Brazil","institution_ids":["https://openalex.org/I4210090141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077390919","display_name":"Lucas H. Ueda","orcid":"https://orcid.org/0000-0002-1029-3420"},"institutions":[{"id":"https://openalex.org/I4210090141","display_name":"Centre for Research and Development in Telecommunications (Brazil)","ror":"https://ror.org/00ej99c12","country_code":"BR","type":"company","lineage":["https://openalex.org/I4210090141"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas H. Ueda","raw_affiliation_strings":["CPQD, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-1029-3420","affiliations":[{"raw_affiliation_string":"CPQD, Brazil","institution_ids":["https://openalex.org/I4210090141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047253278","display_name":"Paula Dornhofer Paro Costa","orcid":"https://orcid.org/0000-0002-1534-5744"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Paula Dornhofer Paro Costa","raw_affiliation_strings":["Dept. of Computer Engineering and Automation, School of Electrical and Computer Engineering, University of Campinas (UNICAMP), Brazil and Artificial Intelligence Lab., Recod.ai, University of Campinas (UNICAMP), Brazil"],"raw_orcid":"https://orcid.org/0000-0002-1534-5744","affiliations":[{"raw_affiliation_string":"Dept. of Computer Engineering and Automation, School of Electrical and Computer Engineering, University of Campinas (UNICAMP), Brazil and Artificial Intelligence Lab., Recod.ai, University of Campinas (UNICAMP), Brazil","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5495,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64326834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9980999827384949,"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/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7767815589904785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7509934902191162},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.596065104007721},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5391749143600464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33973008394241333}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7767815589904785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509934902191162},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.596065104007721},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5391749143600464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33973008394241333},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610661.3616554","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610661.3616554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3794326933","display_name":null,"funder_award_id":"Code 001","funder_id":"https://openalex.org/F4320321091","funder_display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior"}],"funders":[{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2007337857","https://openalex.org/W2145891654","https://openalex.org/W2603777577","https://openalex.org/W2619383789","https://openalex.org/W2727071501","https://openalex.org/W2945629925","https://openalex.org/W2949924544","https://openalex.org/W2981802563","https://openalex.org/W3107914916","https://openalex.org/W3133090439","https://openalex.org/W3135367836","https://openalex.org/W3153551559","https://openalex.org/W3209984917","https://openalex.org/W4292945985","https://openalex.org/W4299390018","https://openalex.org/W4308222758","https://openalex.org/W4312933868","https://openalex.org/W4361755841","https://openalex.org/W4386065807","https://openalex.org/W4387421378"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,40],"gesture":[4,32],"generation":[5],"model":[6,54,80],"based":[7],"on":[8],"state-of-the-art":[9],"diffusion":[10],"models.":[11],"Novel":[12],"adaptations":[13],"were":[14,99],"introduced":[15],"to":[16,21,30,34,46,57,72,88],"improve":[17],"motion":[18],"appropriateness":[19,87],"relative":[20],"speech":[22,35,91],"and":[23],"human-likeness.":[24,85],"Specifically,":[25],"the":[26,58,73,89,108],"main":[27],"focus":[28],"was":[29,55,93],"enhance":[31],"responsiveness":[33],"audio.":[36],"We":[37],"explored":[38],"using":[39],"pre-trained":[41],"Voice":[42],"Activity":[43],"Detector":[44],"(VAD)":[45],"obtain":[47],"more":[48],"meaningful":[49],"audio":[50],"representations.":[51],"The":[52,75],"proposed":[53],"submitted":[56],"GENEA":[59],"Challenge":[60],"2023.":[61],"Perceptual":[62],"experiments":[63],"compared":[64],"our":[65,79],"model,":[66],"labeled":[67],"SH,":[68],"with":[69],"other":[70],"submissions":[71],"challenge.":[74],"results":[76],"indicated":[77],"that":[78],"achieved":[81],"competitive":[82],"levels":[83],"of":[84],"While":[86],"agent\u2019s":[90],"score":[92],"lower":[94],"than":[95],"most":[96,105],"entries,":[97],"there":[98],"no":[100],"statistically":[101],"significant":[102],"differences":[103],"from":[104],"models":[106],"at":[107],"confidence":[109],"level.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-21T07:57:09.225873","created_date":"2025-10-10T00:00:00"}
