{"id":"https://openalex.org/W4402979917","doi":"https://doi.org/10.1109/icme57554.2024.10687922","title":"ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidance","display_name":"ExpGest: Expressive Speaker Generation Using Diffusion Model and Hybrid Audio-Text Guidance","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979917","doi":"https://doi.org/10.1109/icme57554.2024.10687922"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.09396","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082921355","display_name":"Yongkang Cheng","orcid":"https://orcid.org/0000-0002-8849-2032"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongkang Cheng","raw_affiliation_strings":["Tencent AILab,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tencent AILab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051734044","display_name":"Mingjiang Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjiang Liang","raw_affiliation_strings":["Tencent AILab,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tencent AILab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017818991","display_name":"Shaoli Huang","orcid":"https://orcid.org/0000-0002-1445-3196"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoli Huang","raw_affiliation_strings":["Tencent AILab,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tencent AILab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037531369","display_name":"Jifeng Ning","orcid":"https://orcid.org/0000-0002-7751-0936"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jifeng Ning","raw_affiliation_strings":["Northwest A&F University,Xianyan,China"],"affiliations":[{"raw_affiliation_string":"Northwest A&F University,Xianyan,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100641142","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-7409-0948"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["University of Technology Sydney,Sydney,Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082921355"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":1.381,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81799873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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/T12290","display_name":"Human Motion and Animation","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7549645900726318},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6116499900817871},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5823681354522705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549645900726318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6116499900817871},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5823681354522705},{"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":3,"locations":[{"id":"doi:10.1109/icme57554.2024.10687922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.09396","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09396","pdf_url":"https://arxiv.org/pdf/2410.09396","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2410.09396","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.09396","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09396","pdf_url":"https://arxiv.org/pdf/2410.09396","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402979917.pdf","grobid_xml":"https://content.openalex.org/works/W4402979917.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1496828312","https://openalex.org/W1959608418","https://openalex.org/W1967554269","https://openalex.org/W2474702929","https://openalex.org/W2606517404","https://openalex.org/W2896457183","https://openalex.org/W2898109996","https://openalex.org/W2971856312","https://openalex.org/W3036167779","https://openalex.org/W3083173864","https://openalex.org/W3125772723","https://openalex.org/W3125775899","https://openalex.org/W4221142137","https://openalex.org/W4285981714","https://openalex.org/W4297981470","https://openalex.org/W4298186886","https://openalex.org/W4303448003","https://openalex.org/W4312635677","https://openalex.org/W4312765683","https://openalex.org/W4385284180","https://openalex.org/W4385764101","https://openalex.org/W4386065848","https://openalex.org/W4386076288","https://openalex.org/W4396696312","https://openalex.org/W6640963894","https://openalex.org/W6755207826","https://openalex.org/W6774314701","https://openalex.org/W6779823529","https://openalex.org/W6844223692","https://openalex.org/W6853035388"],"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":{"Existing":[0],"gesture":[1,97,128],"generation":[2,98,107],"methods":[3],"primarily":[4],"focus":[5],"on":[6,11],"upper":[7],"body":[8],"gestures":[9,26,84,111],"based":[10],"audio":[12,35,47],"features,":[13],"neglecting":[14],"speech":[15],"content,":[16],"emotion,":[17],"and":[18,46,74,83,112,126,130,140],"locomotion.":[19],"These":[20],"limitations":[21],"result":[22],"in":[23,85,144],"stiff,":[24],"mechanical":[25],"that":[27,117,134],"fail":[28],"to":[29,49,104,147],"convey":[30],"the":[31,86,101],"true":[32],"meaning":[33],"of":[34],"content.":[36],"We":[37],"introduce":[38],"ExpGest,":[39,93],"a":[40,62,94],"novel":[41],"framework":[42,119],"leveraging":[43],"synchronized":[44],"text":[45],"information":[48],"generate":[50],"expressive":[51],"full-body":[52],"gestures.":[53],"Unlike":[54],"AdaIN":[55],"or":[56],"one-hot":[57],"encoding":[58],"methods,":[59],"we":[60],"design":[61],"noise":[63],"emotion":[64],"classifier":[65],"for":[66],"optimizing":[67],"adversarial":[68],"direction":[69],"noise,":[70],"avoiding":[71],"melody":[72],"distortion":[73],"guiding":[75],"results":[76,132],"towards":[77],"specified":[78],"emotions.":[79],"Moreover,":[80],"aligning":[81],"semantic":[82],"latent":[87],"space":[88],"provides":[89],"better":[90],"generalization":[91],"capabilities.":[92],"diffusion":[95],"model-based":[96],"framework,":[99],"is":[100],"first":[102],"attempt":[103],"offer":[105],"mixed":[106],"modes,":[108],"including":[109],"audio-driven":[110],"text-shaped":[113],"motion.":[114],"Experiments":[115],"show":[116],"our":[118],"effectively":[120],"learns":[121],"from":[122],"combined":[123],"text-driven":[124],"motion":[125,143],"audio-induced":[127],"datasets,":[129],"preliminary":[131],"demonstrate":[133],"ExpGest":[135],"achieves":[136],"more":[137],"expressive,":[138],"natural,":[139],"controllable":[141],"global":[142],"speakers":[145],"compared":[146],"state-of-the-art":[148],"models.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2024-10-01T00:00:00"}