{"id":"https://openalex.org/W7166857912","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1718","title":"ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing","display_name":"ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166857912","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1718"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1718","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1718","pdf_url":"https://aclanthology.org/2026.findings-acl.1718.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1718.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139778115","display_name":"Xi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139722125","display_name":"Wei Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139806936","display_name":"Yike Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yike Guo","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84647303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"34399","last_page":"34413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7459999918937683,"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/T12031","display_name":"Speech and dialogue systems","score":0.7459999918937683,"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":0.021299999207258224,"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":0.01940000057220459,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2921999990940094},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2653000056743622},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2533000111579895},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2506999969482422}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6093999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4422000050544739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23980000615119934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1718","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1718","pdf_url":"https://aclanthology.org/2026.findings-acl.1718.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1718","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1718","pdf_url":"https://aclanthology.org/2026.findings-acl.1718.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5541484355926514,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166857912.pdf","grobid_xml":"https://content.openalex.org/works/W7166857912.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Role-playing":[0],"has":[1],"garnered":[2],"rising":[3],"attention":[4],"as":[5],"it":[6],"provides":[7],"a":[8,29,53,83,144],"strong":[9],"foundation":[10],"for":[11],"humanmachine":[12],"interaction":[13],"and":[14,44,50,78,97,148],"facilitates":[15],"sociological":[16],"research.However,":[17],"current":[18],"work":[19],"is":[20,82,104,172],"confined":[21],"to":[22,64],"textual":[23],"modalities,":[24],"neglecting":[25],"speech,":[26],"which":[27],"plays":[28],"predominant":[30],"role":[31,125],"in":[32,118,166],"daily":[33],"life,":[34],"thus":[35],"limiting":[36],"genuine":[37],"role-playing.To":[38],"bridge":[39],"this":[40],"gap,":[41],"we":[42,51],"conceptualize":[43],"benchmark":[45,85],"speech":[46,168],"roleplaying":[47],"through":[48,138],"ActorMindBench,":[49],"present":[52],"corresponding":[54,157],"reasoning":[55,110],"framework,":[56],"called":[57],"ActorMind.Specifically,":[58],"(1)":[59],"Speech":[60],"Role-Playing":[61],"enables":[62],"models":[63],"deliver":[65],"spontaneous":[66],"responses":[67],"with":[68,89,94,100,156],"personalized":[69],"verbal":[70],"traits":[71],"based":[72],"on":[73],"their":[74],"role,":[75],"the":[76,153,162],"scene,":[77],"spoken":[79,136],"dialogue.(2)":[80],"ActorMindBench":[81],"hierarchical":[84],"comprises":[86],"Utterance-Level":[87],"content":[88,93,99],"7,653":[90],"utterances,":[91],"Scene-Level":[92],"313":[95],"scenes,":[96],"Role-Level":[98],"6":[101],"roles.(3)":[102],"ActorMind":[103],"an":[105],"off-theshelf,":[106],"multi-agent":[107],"chain-of-though":[108],"style":[109],"framework":[111],"that":[112],"emulates":[113],"how":[114],"human":[115],"actors":[116],"perform":[117],"theaters.Concretely,":[119],"Actor-Mind":[120,165],"first":[121],"reads":[122],"its":[123],"assigned":[124],"description":[126],"via":[127],"Eye":[128],"Agent,":[129],"then":[130],"comprehends":[131],"emotional":[132,146],"cues":[133],"within":[134],"contextual":[135],"dialogues":[137],"Ear":[139],"Agent.Subsequently,":[140],"Brain":[141],"Agent":[142,151],"generates":[143],"descriptive":[145],"state,":[147],"finally,":[149],"Mouth":[150],"delivers":[152],"scripts":[154],"infused":[155],"emotion":[158],"state.Experimental":[159],"results":[160],"demonstrate":[161],"effectiveness":[163],"of":[164],"enhancing":[167],"role-playing.The":[169],"project":[170],"page":[171],"available":[173],"at":[174],"https://github.":[175],"com/OzymandiasChen/ActorMind.":[176]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
