{"id":"https://openalex.org/W4387446239","doi":"https://doi.org/10.1145/3610661.3616551","title":"The KU-ISPL entry to the GENEA Challenge 2023-A Diffusion Model for Co-speech Gesture generation","display_name":"The KU-ISPL entry to the GENEA Challenge 2023-A Diffusion Model for Co-speech Gesture generation","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4387446239","doi":"https://doi.org/10.1145/3610661.3616551"},"language":"en","primary_location":{"id":"doi:10.1145/3610661.3616551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610661.3616551","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/A5002789888","display_name":"Gwantae Kim","orcid":"https://orcid.org/0000-0002-3239-1865"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Gwantae Kim","raw_affiliation_strings":["Korea University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028033244","display_name":"Yuanming Li","orcid":"https://orcid.org/0000-0003-2560-9261"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yuanming Li","raw_affiliation_strings":["Korea University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026204977","display_name":"Hanseok Ko","orcid":"https://orcid.org/0000-0002-8744-4514"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanseok Ko","raw_affiliation_strings":["Korea University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002789888"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65948848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"220","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.90693199634552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7036799192428589},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6473990678787231},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.44841068983078003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4251723289489746},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3802008032798767}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.90693199634552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7036799192428589},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6473990678787231},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.44841068983078003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4251723289489746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3802008032798767}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610661.3616551","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3610661.3616551","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":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1977259876","https://openalex.org/W2157331557","https://openalex.org/W2191779130","https://openalex.org/W2884225676","https://openalex.org/W2922298118","https://openalex.org/W3002310794","https://openalex.org/W3083173864","https://openalex.org/W3096831136","https://openalex.org/W3099073275","https://openalex.org/W3125775899","https://openalex.org/W4230429791","https://openalex.org/W4292945985","https://openalex.org/W4308222716","https://openalex.org/W4308222758","https://openalex.org/W4312674262","https://openalex.org/W4312719027","https://openalex.org/W4312933868","https://openalex.org/W4372349426","https://openalex.org/W4386065848","https://openalex.org/W4387421378"],"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/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,26,32,66,72,76,106,112],"diffusion":[4,49],"model":[5,51,98],"for":[6,117,156],"co-speech":[7,27,43,101,153],"gesture":[8,22,28,34,44,73,81,154],"generation":[9,23,29,35,45,155],"presented":[10],"by":[11,47,91],"KU-ISPL":[12],"entry":[13],"of":[14,110,115,122,130,142],"the":[15,21,42,60,80,84,118,140,143,146,152],"GENEA":[16,92],"Challenge":[17,93],"2023.":[18],"We":[19,58,132],"formulate":[20],"problem":[24,30,46],"as":[25,65,75],"and":[31,37,55,69,124],"semantic":[33],"problem,":[36],"we":[38,70],"focus":[39],"on":[40],"solving":[41],"denoising":[48,67],"probabilistic":[50],"with":[52,62],"text,":[53],"audio,":[54],"pre-pose":[56],"conditions.":[57],"use":[59],"U-Net":[61],"cross-attention":[63],"architecture":[64],"model,":[68],"propose":[71],"autoencoder":[74],"mapping":[77],"function":[78],"from":[79],"domain":[82],"to":[83,138,151],"latent":[85],"domain.":[86],"The":[87],"collective":[88],"evaluation":[89],"released":[90],"2023":[94],"shows":[95],"that":[96],"our":[97,148],"successfully":[99],"generates":[100],"gestures.":[102],"Our":[103],"system":[104,149],"receives":[105],"mean":[107],"human-likeness":[108],"score":[109,114,129],"32.0,":[111],"preference-matched":[113],"appropriateness":[116,128],"main":[119],"agent":[120],"speech":[121,127],"53.6%,":[123],"an":[125,135],"interlocutor":[126],"53.5%.":[131],"also":[133],"conduct":[134],"ablation":[136],"study":[137],"measure":[139],"effects":[141],"pre-pose.":[144],"By":[145],"results,":[147],"contributes":[150],"natural":[157],"interaction.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
