{"id":"https://openalex.org/W4390825590","doi":"https://doi.org/10.3233/faia231260","title":"Dynamic Talking-Head Generation with Speech Emotion Recognition and Intensity Detection","display_name":"Dynamic Talking-Head Generation with Speech Emotion Recognition and Intensity Detection","publication_year":2024,"publication_date":"2024-01-12","ids":{"openalex":"https://openalex.org/W4390825590","doi":"https://doi.org/10.3233/faia231260"},"language":"en","primary_location":{"id":"doi:10.3233/faia231260","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia231260","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA231260","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA231260","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039118363","display_name":"Chen Fu","orcid":"https://orcid.org/0000-0001-6554-1770"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chen Fu","raw_affiliation_strings":["Graduate School of Science and Engineering, Hosei University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Hosei University, Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067762815","display_name":"Yang Yu","orcid":"https://orcid.org/0009-0007-7047-1501"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["Graduate School of Science and Engineering, Hosei University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Hosei University, Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019348755","display_name":"Zhiqiang Zhang","orcid":"https://orcid.org/0000-0002-2408-366X"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Southwest University of Science And Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Southwest University of Science And Technology, China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025961783","display_name":"Wei Weng","orcid":"https://orcid.org/0000-0003-0354-8795"},"institutions":[{"id":"https://openalex.org/I10091056","display_name":"Kanazawa University","ror":"https://ror.org/02hwp6a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I10091056"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wei Weng","raw_affiliation_strings":["Institute of Liberal Arts and Science, Kanazawa University, Japan"],"affiliations":[{"raw_affiliation_string":"Institute of Liberal Arts and Science, Kanazawa University, Japan","institution_ids":["https://openalex.org/I10091056"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021863826","display_name":"Jinjia Zhou","orcid":"https://orcid.org/0000-0002-5078-0522"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jinjia Zhou","raw_affiliation_strings":["Graduate School of Science and Engineering, Hosei University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Hosei University, Japan","institution_ids":["https://openalex.org/I204291657"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021863826"],"corresponding_institution_ids":["https://openalex.org/I204291657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02321188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11448","display_name":"Face recognition and analysis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/emotive","display_name":"Emotive","score":0.9287693500518799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6526615619659424},{"id":"https://openalex.org/keywords/emotion-detection","display_name":"Emotion detection","score":0.48726072907447815},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.45709720253944397},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45694053173065186},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.452324241399765},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.4145083427429199},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4141598343849182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3272738754749298}],"concepts":[{"id":"https://openalex.org/C2776215170","wikidata":"https://www.wikidata.org/wiki/Q5373820","display_name":"Emotive","level":2,"score":0.9287693500518799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6526615619659424},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.48726072907447815},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.45709720253944397},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45694053173065186},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.452324241399765},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.4145083427429199},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4141598343849182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3272738754749298},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia231260","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia231260","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA231260","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia231260","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia231260","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA231260","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6237854213","display_name":null,"funder_award_id":"JPJSBP1","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7146533649","display_name":null,"funder_award_id":"JPJSBP120","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390825590.pdf","grobid_xml":"https://content.openalex.org/works/W4390825590.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W2924744988","https://openalex.org/W2962770129","https://openalex.org/W2964449965","https://openalex.org/W2973181312","https://openalex.org/W3015267357","https://openalex.org/W3015884429","https://openalex.org/W3018302085","https://openalex.org/W3022013598","https://openalex.org/W3099284785","https://openalex.org/W4200631136","https://openalex.org/W4205131079","https://openalex.org/W4221162871","https://openalex.org/W4225635674","https://openalex.org/W4235832433","https://openalex.org/W4308537255","https://openalex.org/W4309873549","https://openalex.org/W4310379947","https://openalex.org/W4382469130","https://openalex.org/W4386072021","https://openalex.org/W6605980550"],"related_works":["https://openalex.org/W1973672316","https://openalex.org/W139179520","https://openalex.org/W2800896616","https://openalex.org/W2557395687","https://openalex.org/W4379117383","https://openalex.org/W2584926856","https://openalex.org/W3090814224","https://openalex.org/W2336827033","https://openalex.org/W4312615275","https://openalex.org/W4206796671"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"speech":[3,87],"emotion":[4,23],"recognition":[5,24],"(SER)":[6],"and":[7,101,130,148,163,185,196],"emotive":[8],"talking":[9,33,115,123,177,197],"head":[10,116,198],"generation":[11,57],"have":[12],"drawn":[13],"significant":[14],"attention.":[15],"However,":[16],"existing":[17,161,191],"methods":[18,162],"either":[19],"focus":[20],"predominantly":[21],"on":[22],"without":[25],"considering":[26],"its":[27],"intensity":[28,174],"or":[29],"produce":[30],"emotionally":[31,121],"consistent":[32],"heads,":[34],"neglecting":[35],"the":[36,62,65,69,81,99,114,134,158,169,183],"rich":[37],"expressiveness":[38],"of":[39,64,83,103,111,151,160,172,187],"human":[40,138,152],"interactions.":[41],"Addressing":[42],"these":[43,50],"limitations,":[44],"our":[45,188],"study":[46],"aims":[47],"to":[48],"bridge":[49],"two":[51],"areas,":[52],"proposing":[53],"an":[54,107],"innovative":[55],"talking-head":[56],"approach":[58,189],"that":[59,77,125],"further":[60],"enhances":[61,98],"realism":[63],"generated":[66],"video.":[67],"Within":[68],"SER":[70,195],"domain,":[71],"we":[72],"develop":[73],"a":[74,145,165],"dual-level":[75],"model":[76,96,135],"not":[78],"only":[79],"improves":[80],"accuracy":[82,109],"identifying":[84],"emotions":[85],"in":[86,175,193],"data":[88],"but":[89],"also":[90,136],"assesses":[91],"their":[92],"intensity.":[93,131],"This":[94],"dual-capacity":[95],"significantly":[97],"depth":[100],"subtlety":[102],"emotional":[104,128,173],"recognition,":[105],"achieving":[106],"industry-leading":[108],"rate":[110],"73.5%.":[112],"On":[113],"front,":[117],"this":[118],"work":[119],"generates":[120],"expressive":[122],"heads":[124],"reflect":[126],"both":[127,194],"state":[129],"Beyond":[132],"this,":[133],"simulates":[137],"facial":[139],"dynamics":[140],"like":[141],"blinking,":[142],"thus":[143],"offering":[144],"more":[146],"comprehensive":[147],"realistic":[149],"representation":[150],"speech.":[153],"These":[154],"advances":[155],"effectively":[156],"address":[157],"shortcomings":[159],"provide":[164],"new":[166],"avenue":[167],"for":[168],"accurate":[170],"portrayal":[171],"synthesized":[176],"heads.":[178],"Extensive":[179],"experimental":[180],"results":[181],"demonstrate":[182],"effectiveness":[184],"superiority":[186],"over":[190],"methodologies":[192],"generation.":[199]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}