{"id":"https://openalex.org/W4392910552","doi":"https://doi.org/10.1109/icassp48485.2024.10448208","title":"Conversational Co-Speech Gesture Generation via Modeling Dialog Intention, Emotion, and Context with Diffusion Models","display_name":"Conversational Co-Speech Gesture Generation via Modeling Dialog Intention, Emotion, and Context with Diffusion Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910552","doi":"https://doi.org/10.1109/icassp48485.2024.10448208"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102788950","display_name":"Haiwei Xue","orcid":"https://orcid.org/0000-0001-7318-9682"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haiwei Xue","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101473093","display_name":"Sicheng Yang","orcid":"https://orcid.org/0009-0008-5201-4494"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sicheng Yang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043901952","display_name":"Zhensong Zhang","orcid":"https://orcid.org/0009-0001-7911-7564"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhensong Zhang","raw_affiliation_strings":["Huawei Noah’s Ark Lab,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","The Chinese University of Hong Kong, Hong Kong SAR, China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780135","display_name":"Minglei Li","orcid":"https://orcid.org/0000-0002-1427-3507"},"institutions":[{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglei Li","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd,Shenzhen,China","Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210144487"]},{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103105111","display_name":"Zonghong Dai","orcid":"https://orcid.org/0009-0006-7723-4130"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zonghong Dai","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd,Shenzhen,China","Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327","https://openalex.org/I4210144487"]},{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102225156","display_name":"Helen Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102788950"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.3379,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82577834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8296","last_page":"8300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9602000117301941,"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":0.9602000117301941,"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/dialog-box","display_name":"Dialog box","score":0.8823398351669312},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7278033494949341},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259687781333923},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6683147549629211},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.6532208919525146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5626299381256104},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.49833035469055176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4748687446117401},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4601832330226898},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4568957984447479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34901881217956543},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14360061287879944},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.05421966314315796}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8823398351669312},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7278033494949341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259687781333923},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6683147549629211},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.6532208919525146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5626299381256104},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.49833035469055176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4748687446117401},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4601832330226898},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4568957984447479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34901881217956543},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14360061287879944},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.05421966314315796},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1888327543","display_name":null,"funder_award_id":"15001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2123497280","display_name":null,"funder_award_id":"202106","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757194791","display_name":null,"funder_award_id":"JCYJ20","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1971199318","https://openalex.org/W2103153725","https://openalex.org/W2168236107","https://openalex.org/W2493916176","https://openalex.org/W2745809839","https://openalex.org/W2746807059","https://openalex.org/W2896457183","https://openalex.org/W2910112284","https://openalex.org/W2911763550","https://openalex.org/W2965373594","https://openalex.org/W2978017171","https://openalex.org/W3009385801","https://openalex.org/W3083173864","https://openalex.org/W3125775899","https://openalex.org/W3194872882","https://openalex.org/W4292945985","https://openalex.org/W4298186886","https://openalex.org/W4312309978","https://openalex.org/W4323076533","https://openalex.org/W4385764101","https://openalex.org/W4386066602","https://openalex.org/W4386270206","https://openalex.org/W4387421378","https://openalex.org/W4394597452","https://openalex.org/W4399206662","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6768851824","https://openalex.org/W6844223692","https://openalex.org/W6846666370","https://openalex.org/W6849489509","https://openalex.org/W6850082022","https://openalex.org/W6852737781"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W1963944933","https://openalex.org/W2563921006","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047","https://openalex.org/W1977846844"],"abstract_inverted_index":{"Audio-driven":[0],"co-speech":[1,30],"human":[2],"gesture":[3,20,31,81],"generation":[4,32,82],"has":[5],"made":[6],"remarkable":[7],"advancements":[8],"recently.":[9],"However,":[10],"most":[11],"previous":[12],"works":[13],"only":[14],"focus":[15],"on":[16],"single":[17],"person":[18],"audio-driven":[19],"generation.":[21],"We":[22],"aim":[23],"at":[24,112],"solving":[25],"the":[26,49,62,66,104,113,124,128],"problem":[27],"of":[28,51,127],"conversational":[29,86,101],"that":[33],"considers":[34],"multiple":[35],"participants":[36],"in":[37],"a":[38,42,74,117],"conversation,":[39],"which":[40],"is":[41],"novel":[43],"and":[44,56,65,89,108],"challenging":[45],"task":[46],"due":[47],"to":[48],"difficulty":[50],"simultaneously":[52],"incorporating":[53],"semantic":[54,90],"information":[55],"other":[57],"relevant":[58],"features":[59],"from":[60],"both":[61],"primary":[63],"speaker":[64],"interlocutor.":[67],"To":[68],"this":[69],"end,":[70],"we":[71],"propose":[72],"CoDiffuseGesture,":[73],"diffusion":[75],"model-based":[76],"approach":[77],"for":[78,100],"speech-driven":[79],"interaction":[80],"via":[83],"modeling":[84],"bilateral":[85],"intention,":[87],"emotion,":[88],"context.":[91],"Our":[92],"method":[93],"synthesizes":[94],"appropriate":[95],"interactive,":[96],"speech-matched,":[97],"high-quality":[98],"gestures":[99],"motions":[102],"through":[103],"intention":[105],"perception":[106],"module":[107,111],"emotion":[109],"reasoning":[110],"sentence":[114],"level":[115],"by":[116],"pretrained":[118],"language":[119],"model.":[120],"Experimental":[121],"results":[122],"demonstrate":[123],"promising":[125],"performance":[126],"proposed":[129],"method.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}