{"id":"https://openalex.org/W4408354517","doi":"https://doi.org/10.1109/icassp49660.2025.10887862","title":"SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation","display_name":"SPEAK: Speech-Driven Pose and Emotion-Adjustable Talking Head Generation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354517","doi":"https://doi.org/10.1109/icassp49660.2025.10887862"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5021763401","display_name":"Changpeng Cai","orcid":"https://orcid.org/0000-0002-2538-8908"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changpeng Cai","raw_affiliation_strings":["Southeast University,Ping An Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Southeast University,Ping An Technology,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101353835","display_name":"Guinan Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guinan Guo","raw_affiliation_strings":["Sun Yat-Sen University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101882556","display_name":"Jiao Li","orcid":"https://orcid.org/0009-0004-8331-6920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao Li","raw_affiliation_strings":["Ping An Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Nanjing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043198787","display_name":"Junhao Su","orcid":"https://orcid.org/0000-0002-8560-3999"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhao Su","raw_affiliation_strings":["Southeast University,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Southeast University,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075489680","display_name":"Fei Shen","orcid":"https://orcid.org/0000-0001-9749-0234"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Shen","raw_affiliation_strings":["Nanjing University of Science and Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111253965","display_name":"Chenghao He","orcid":null},"institutions":[{"id":"https://openalex.org/I143593769","display_name":"East China University of Science and Technology","ror":"https://ror.org/01vyrm377","country_code":"CN","type":"education","lineage":["https://openalex.org/I143593769"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenghao He","raw_affiliation_strings":["East China University of Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"East China University of Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I143593769"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006774543","display_name":"Yuanxu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanxu Chen","raw_affiliation_strings":["Ping An Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051071915","display_name":"Lei Dai","orcid":"https://orcid.org/0000-0002-5662-0765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Dai","raw_affiliation_strings":["Ping An Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Ping An Technology,Nanjing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005251827","display_name":"Feiyu Zhu","orcid":"https://orcid.org/0000-0001-6863-7137"},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyu Zhu","raw_affiliation_strings":["University of Shanghai for Science and Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"University of Shanghai for Science and Technology,Shanghai,China","institution_ids":["https://openalex.org/I148128674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5021763401"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":5.1419,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93512638,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9455000162124634,"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/computer-science","display_name":"Computer science","score":0.7227164506912231},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6729453206062317},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.55116206407547},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4409344494342804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.356886088848114},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3261410593986511},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.060853809118270874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7227164506912231},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6729453206062317},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.55116206407547},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4409344494342804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.356886088848114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3261410593986511},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.060853809118270874},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2113396990","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2468212864","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2738406145","https://openalex.org/W2798536775","https://openalex.org/W2944294033","https://openalex.org/W2963073614","https://openalex.org/W2963290645","https://openalex.org/W3015814181","https://openalex.org/W3035574324","https://openalex.org/W3081492798","https://openalex.org/W3099284785","https://openalex.org/W3186090335","https://openalex.org/W3197199219","https://openalex.org/W3199003182","https://openalex.org/W4210657261","https://openalex.org/W4281730245","https://openalex.org/W4375868848","https://openalex.org/W4382469130","https://openalex.org/W4390874567","https://openalex.org/W4404586213","https://openalex.org/W6859110512"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Most":[0],"earlier":[1],"researches":[2],"on":[3,9],"talking":[4,33,175],"face":[5,34,107],"generation":[6,35],"have":[7],"focused":[8],"the":[10,76,136,162],"synchronization":[11,160],"of":[12,28,168],"lip":[13,159,179],"motion":[14],"and":[15,21,52,84,114,145,184],"speech":[16,112,146],"content.":[17],"However,":[18],"head":[19,143,176,186],"pose":[20],"facial":[22,44,97,115,150,169,182],"emotions":[23,45],"are":[24,47],"equally":[25],"important":[26],"characteristics":[27],"natural":[29],"faces.":[30],"While":[31],"audio-driven":[32],"has":[36],"seen":[37],"notable":[38],"advancements,":[39],"existing":[40],"methods":[41],"either":[42],"overlook":[43],"or":[46],"limited":[48],"to":[49,56,95,139],"specific":[50],"individuals":[51],"cannot":[53],"be":[54],"applied":[55],"arbitrary":[57],"subjects.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62,88,104,124],"propose":[63],"a":[64,106,119,126],"novel":[65,127],"one-shot":[66],"Talking":[67,78],"Head":[68],"Generation":[69,80],"framework":[70],"(SPEAK)":[71],"that":[72,110,129,155],"distinguishes":[73],"itself":[74],"from":[75,135],"general":[77],"Face":[79],"by":[81],"enabling":[82,165],"emotional":[83,141],"postural":[85],"control.":[86],"Specifically,":[87],"introduce":[89],"Inter-Reconstructed":[90],"Feature":[91],"Disentanglement":[92],"(IRFD)":[93],"module":[94,109,138],"decouple":[96],"features":[98],"into":[99,118],"three":[100],"latent":[101,116,121,132],"spaces.":[102],"Then":[103],"design":[105],"editing":[108,137],"modifies":[111],"content":[113,147],"codes":[117,133],"single":[120],"space.":[122],"Subsequently,":[123],"present":[125],"generator":[128],"employs":[130],"modified":[131],"derived":[134],"regulate":[140],"expression,":[142],"poses,":[144],"in":[148],"synthesizing":[149],"animations.":[151],"Extensive":[152],"trials":[153],"demonstrate":[154],"our":[156],"method":[157],"ensures":[158],"with":[161,177],"audio":[163],"while":[164],"decoupled":[166],"control":[167],"features,":[170],"it":[171],"can":[172],"generate":[173],"realistic":[174],"coordinated":[178],"motions,":[180],"authentic":[181],"emotions,":[183],"smooth":[185],"movements.":[187],"The":[188],"demo":[189],"video":[190],"is":[191],"available:":[192],"https://anonymous.4open.science/r/SPEAK-8A22.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
