{"id":"https://openalex.org/W4406611576","doi":"https://doi.org/10.1109/smc54092.2024.10832087","title":"SAM-Wav2lip++: Enhancing Behavioral Realism in Synthetic Agents Through Audio-Driven Speech and Action Refinement","display_name":"SAM-Wav2lip++: Enhancing Behavioral Realism in Synthetic Agents Through Audio-Driven Speech and Action Refinement","publication_year":2024,"publication_date":"2024-10-06","ids":{"openalex":"https://openalex.org/W4406611576","doi":"https://doi.org/10.1109/smc54092.2024.10832087"},"language":"en","primary_location":{"id":"doi:10.1109/smc54092.2024.10832087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10832087","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 Systems, Man, and Cybernetics (SMC)","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/A5043026583","display_name":"Bihui Yu","orcid":"https://orcid.org/0000-0001-8614-7350"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bihui Yu","raw_affiliation_strings":["Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168"],"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037147534","display_name":"Dawei Liu","orcid":"https://orcid.org/0000-0003-1911-9207"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Liu","raw_affiliation_strings":["Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168"],"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052595442","display_name":"Huiyang Shi","orcid":null},"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":"Huiyang Shi","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China,100049"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"GuiYong Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"GuiYong Chang","raw_affiliation_strings":["Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168"],"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043101779","display_name":"Jingxuan Wei","orcid":"https://orcid.org/0000-0002-8757-5602"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxuan Wei","raw_affiliation_strings":["Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168"],"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076535884","display_name":"Linzhuang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linzhuang Sun","raw_affiliation_strings":["Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168"],"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078047250","display_name":"Songtao Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songtao Tian","raw_affiliation_strings":["Tsinghua University,Department of Mathematical Sciences,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Mathematical Sciences,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071996873","display_name":"Liping Bu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210120842","display_name":"Shenyang Institute of Computing Technology (China)","ror":"https://ror.org/02xqp7x96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210120842"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Bu","raw_affiliation_strings":["Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168"],"affiliations":[{"raw_affiliation_string":"Shenyang Institute of Computing Technology, Chinese Academy of Sciences,Shenyang,China,110168","institution_ids":["https://openalex.org/I4210120842","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5043026583"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210120842"],"apc_list":null,"apc_paid":null,"fwci":0.3345,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69875806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2999","last_page":"3006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9739999771118164,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9739999771118164,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.972000002861023,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9661999940872192,"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":0.6824976801872253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5654142498970032},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5529749393463135},{"id":"https://openalex.org/keywords/realism","display_name":"Realism","score":0.5121817588806152},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.04921680688858032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6824976801872253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5654142498970032},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5529749393463135},{"id":"https://openalex.org/C543847140","wikidata":"https://www.wikidata.org/wiki/Q2642826","display_name":"Realism","level":2,"score":0.5121817588806152},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.04921680688858032},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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":1,"locations":[{"id":"doi:10.1109/smc54092.2024.10832087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc54092.2024.10832087","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 Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2342475039","https://openalex.org/W2497597915","https://openalex.org/W2594690981","https://openalex.org/W2726515241","https://openalex.org/W2738406145","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2897492880","https://openalex.org/W2914217321","https://openalex.org/W2944294033","https://openalex.org/W2964076328","https://openalex.org/W2981767644","https://openalex.org/W2982625143","https://openalex.org/W2983796203","https://openalex.org/W3019952993","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3144253442","https://openalex.org/W3153832461","https://openalex.org/W3186090335","https://openalex.org/W3187364420","https://openalex.org/W3197199219","https://openalex.org/W3211147706","https://openalex.org/W4200150166","https://openalex.org/W4200631136","https://openalex.org/W4285603330","https://openalex.org/W4288079574","https://openalex.org/W4289665794","https://openalex.org/W4310379947","https://openalex.org/W4386072021","https://openalex.org/W4390873117","https://openalex.org/W4390874575","https://openalex.org/W4391305822","https://openalex.org/W6748181857","https://openalex.org/W6754420807","https://openalex.org/W6756726438","https://openalex.org/W6767264202","https://openalex.org/W6779661269","https://openalex.org/W6781523853","https://openalex.org/W6781874425","https://openalex.org/W6844223692","https://openalex.org/W6849049266","https://openalex.org/W6851732043","https://openalex.org/W6858529799","https://openalex.org/W6858865347"],"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":{"Digital":[0],"human":[1,146],"generation":[2,14],"is":[3],"a":[4,70,75,90,105,114],"forward-looking":[5],"field":[6],"in":[7,12,32],"technology.":[8],"Despite":[9],"significant":[10],"progress":[11],"the":[13,58,117,124,162,167],"of":[15,62,80,94,119,148],"speaking":[16],"facial":[17,128],"videos,":[18,34],"many":[19],"challenges":[20],"remain":[21],"unaddressed.":[22],"Issues":[23],"such":[24],"as":[25],"unnatural":[26],"head":[27,53],"movements,":[28],"distorted":[29],"expressions,":[30],"artifacts":[31],"generated":[33],"and":[35,74,85,122,134,158],"uncoordinated":[36],"limb":[37],"movements":[38,54,157],"persist.":[39],"Most":[40],"current":[41],"efforts":[42],"are":[43],"focused":[44],"on":[45],"specific":[46],"individuals,":[47],"with":[48,161],"enhancements":[49],"often":[50],"limited":[51],"to":[52],"without":[55],"further":[56],"advancing":[57],"overall":[59],"behavioral":[60,159],"actions":[61,160],"digital":[63,145],"humans.":[64],"In":[65],"this":[66],"context,":[67],"we":[68],"introduce":[69],"new":[71],"dataset,":[72],"CFMD,":[73],"novel":[76],"model,":[77],"SAM-Wav2lip++,":[78],"capable":[79],"generating":[81],"consistent,":[82],"audio-synchronized":[83],"lip":[84,111,156],"behavior":[86],"action":[87],"videos":[88,147],"from":[89],"single":[91],"reference":[92],"image":[93],"any":[95],"identity.":[96],"This":[97],"work":[98],"features":[99],"three":[100],"main":[101],"innovative":[102],"components:":[103],"(1)":[104],"contrastive":[106],"lip-sync":[107],"discriminator":[108],"for":[109,116,127],"precise":[110],"synchronization,":[112],"(2)":[113],"generator":[115],"synthesis":[118],"sound-action":[120],"consistency,":[121],"(3)":[123],"SAM":[125],"module":[126],"refinement":[129],"operations.":[130],"Through":[131],"extensive":[132],"experiments":[133],"user":[135],"studies,":[136],"our":[137,141],"results":[138],"demonstrate":[139],"that":[140,153],"model":[142],"can":[143],"synthesize":[144],"impressively":[149],"high":[150],"perceptual":[151],"quality":[152],"accurately":[154],"sync":[155],"input":[163],"audio,":[164],"substantially":[165],"outperforming":[166],"state-of-the-art":[168],"baselines":[169],"evaluations.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}