{"id":"https://openalex.org/W4411635654","doi":"https://doi.org/10.1145/3731715.3733366","title":"Inter - Diffusion Generation Model of Speakers and Listeners for Effective Communication","display_name":"Inter - Diffusion Generation Model of Speakers and Listeners for Effective Communication","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635654","doi":"https://doi.org/10.1145/3731715.3733366"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5014390378","display_name":"Jinhe Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhe Huang","raw_affiliation_strings":["Nanjing Agriculture University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0000-9349-3948","affiliations":[{"raw_affiliation_string":"Nanjing Agriculture University, Nanjing, China","institution_ids":["https://openalex.org/I119454577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110296331","display_name":"Y.M. Cheng","orcid":"https://orcid.org/0000-0003-3392-2012"},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkang Cheng","raw_affiliation_strings":["Nanjing Agriculture University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3392-2012","affiliations":[{"raw_affiliation_string":"Nanjing Agriculture University, Nanjing, China","institution_ids":["https://openalex.org/I119454577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101263138","display_name":"Minghang Yu","orcid":"https://orcid.org/0009-0001-3756-1528"},"institutions":[{"id":"https://openalex.org/I89652312","display_name":"Northwest A&F University","ror":"https://ror.org/0051rme32","country_code":"CN","type":"education","lineage":["https://openalex.org/I89652312"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghang Yu","raw_affiliation_strings":["Northwest A&amp;F University, Yangling, China"],"raw_orcid":"https://orcid.org/0009-0001-3756-1528","affiliations":[{"raw_affiliation_string":"Northwest A&amp;F University, Yangling, China","institution_ids":["https://openalex.org/I89652312"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100682156","display_name":"Gaoge Han","orcid":"https://orcid.org/0009-0001-6731-8203"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Gaoge Han","raw_affiliation_strings":["City University of Hong Kong, Hong Kong SAR, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0001-6731-8203","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong SAR, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinwei Li","orcid":"https://orcid.org/0009-0005-6606-3359"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwei Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-6606-3359","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Hangzhou, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0002-0953-3669"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-0953-3669","affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Ningbo, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039152048","display_name":"Shilei Wang","orcid":"https://orcid.org/0000-0002-0507-7256"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Wang","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0507-7256","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xingjian Gu","orcid":"https://orcid.org/0009-0003-9027-4987"},"institutions":[{"id":"https://openalex.org/I119454577","display_name":"Nanjing Agricultural University","ror":"https://ror.org/05td3s095","country_code":"CN","type":"education","lineage":["https://openalex.org/I119454577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjian Gu","raw_affiliation_strings":["Nanjing Agriculture University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-9027-4987","affiliations":[{"raw_affiliation_string":"Nanjing Agriculture University, Nanjing, China","institution_ids":["https://openalex.org/I119454577"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7711,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85180844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"497","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9948999881744385,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9948999881744385,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9905999898910522,"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":0.9886000156402588,"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/computer-science","display_name":"Computer science","score":0.661470890045166},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5806384086608887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4175414443016052},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08268702030181885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661470890045166},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5806384086608887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4175414443016052},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08268702030181885},{"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:10.1145/3731715.3733366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W3083173864","https://openalex.org/W3125775899","https://openalex.org/W3198131199","https://openalex.org/W3204221554","https://openalex.org/W4221142137","https://openalex.org/W4281661987","https://openalex.org/W4285981714","https://openalex.org/W4292945985","https://openalex.org/W4308222716","https://openalex.org/W4310831393","https://openalex.org/W4385284180","https://openalex.org/W4385764101","https://openalex.org/W4386075984","https://openalex.org/W4386076103","https://openalex.org/W4386755513","https://openalex.org/W4392904562","https://openalex.org/W4402979917","https://openalex.org/W4409262261","https://openalex.org/W4409262798","https://openalex.org/W4409263146","https://openalex.org/W4409346346","https://openalex.org/W6602344735","https://openalex.org/W6847123917"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Full-body":[0],"gestures":[1,71],"play":[2],"a":[3,80,127],"pivotal":[4],"role":[5,31],"in":[6,34,149,182,228],"natural":[7],"interactions":[8],"and":[9,38,58,95,116,186],"are":[10,208],"crucial":[11],"for":[12,60,236],"achieving":[13],"effective":[14,237],"communication.":[15,98,238],"Nevertheless,":[16],"most":[17],"existing":[18],"studies":[19],"primarily":[20],"focus":[21],"on":[22,105,141],"the":[23,29,35,43,64,69,75,89,100,106,117,122,133,142,152,159,168,174,183,190,194,201,225],"gesture":[24,131,171],"generation":[25,76,172],"of":[26,32,56,72,189],"speakers,":[27],"overlooking":[28],"vital":[30],"listeners":[33,73,96],"interaction":[36,45,91,114,157,203],"process":[37],"failing":[39],"to":[40,120,151,210],"fully":[41],"explore":[42],"dynamic":[44],"between":[46,93,158],"them.":[47],"This":[48],"paper":[49],"innovatively":[50,112],"proposes":[51],"an":[52],"Inter-Diffusion":[53],"Generation":[54],"Model":[55],"Speakers":[57],"Listeners":[59],"Effective":[61],"Communication.":[62],"For":[63],"first":[65],"time,":[66],"we":[67,111,176],"integrate":[68],"full-body":[70],"into":[74],"framework.":[77],"By":[78],"devising":[79],"novel":[81],"inter-diffusion":[82],"mechanism,":[83],"this":[84],"model":[85,101,109,119,134,175,223],"can":[86,135],"accurately":[87],"capture":[88],"complex":[90],"patterns":[92],"speakers":[94],"during":[97],"In":[99,193],"construction":[102],"process,":[103],"based":[104,140],"advanced":[107],"diffusion":[108],"architecture,":[110],"introduce":[113],"conditions":[115],"GAN":[118],"increase":[121],"denoising":[123],"step":[124],"size.":[125],"As":[126],"result,":[128],"when":[129],"generating":[130],"sequences,":[132],"not":[136],"only":[137],"dynamically":[138],"generate":[139],"speaker's":[143],"speech":[144],"information":[145],"but":[146],"also":[147,219],"respond":[148],"realtime":[150],"listener's":[153],"feedback,":[154],"enabling":[155],"synergistic":[156],"two.":[160],"Abundant":[161],"experimental":[162],"results":[163],"demonstrate":[164],"that":[165,206,221],"compared":[166],"with":[167],"current":[169],"state-of-the-art":[170],"methods,":[173],"proposed":[177],"has":[178],"achieved":[179],"remarkable":[180],"improvements":[181],"naturalness,":[184],"coherence,":[185],"speech-gesture":[187],"synchronization":[188],"generated":[191,202],"gestures.":[192],"subjective":[195],"evaluation":[196],"experiments,":[197],"users":[198],"highly":[199],"praised":[200],"scenarios,":[204],"believing":[205],"they":[207],"closer":[209],"real":[211],"life":[212],"human":[213],"communication":[214],"situations.":[215],"Objective":[216],"index":[217],"evaluations":[218],"show":[220],"our":[222],"outperforms":[224],"baseline":[226],"methods":[227],"multiple":[229],"key":[230],"indicators,":[231],"providing":[232],"more":[233],"powerful":[234],"support":[235]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}
