{"id":"https://openalex.org/W4415536809","doi":"https://doi.org/10.1145/3746027.3755423","title":"Cued-Agent: A Collaborative Multi-Agent System for Automatic Cued Speech Recognition","display_name":"Cued-Agent: A Collaborative Multi-Agent System for Automatic Cued Speech Recognition","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536809","doi":"https://doi.org/10.1145/3746027.3755423"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051727700","display_name":"Guanjie Huang","orcid":"https://orcid.org/0000-0003-1977-3647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanjie Huang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1977-3647","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040138091","display_name":"Danny H. K. Tsang","orcid":"https://orcid.org/0000-0003-0135-7098"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danny H.K. Tsang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0135-7098","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"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":"Shan Yang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4464-146X","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120131343","display_name":"Guangzhi Lei","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":"Guangzhi Lei","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-6136-7619","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418818","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-4497-0135"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4497-0135","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8313","last_page":"8321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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":0.9916999936103821,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9760000109672546,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5335999727249146},{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.5282999873161316},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47760000824928284},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4408999979496002},{"id":"https://openalex.org/keywords/asynchrony","display_name":"Asynchrony (computer programming)","score":0.40610000491142273},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.384799987077713},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3589000105857849},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.3564000129699707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101999759674072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6349999904632568},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.5282999873161316},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C2779019669","wikidata":"https://www.wikidata.org/wiki/Q25203946","display_name":"Asynchrony (computer programming)","level":3,"score":0.40610000491142273},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1972680065","https://openalex.org/W2008757213","https://openalex.org/W2109455879","https://openalex.org/W2744640636","https://openalex.org/W2766219058","https://openalex.org/W2888888638","https://openalex.org/W2970641574","https://openalex.org/W2998687373","https://openalex.org/W3008402854","https://openalex.org/W3109496323","https://openalex.org/W3113399631","https://openalex.org/W3163112956","https://openalex.org/W4225685860","https://openalex.org/W4375868832","https://openalex.org/W4385823053","https://openalex.org/W4390788068","https://openalex.org/W4391759831","https://openalex.org/W4392207805","https://openalex.org/W4393178509","https://openalex.org/W4403203873","https://openalex.org/W4411635528"],"related_works":[],"abstract_inverted_index":{"Cued":[0],"Speech":[1],"(CS)":[2],"is":[3,239],"a":[4,115,136,150,166,170,213],"visual":[5],"communication":[6,16],"system":[7,105],"that":[8,123,142,155,174,222],"combines":[9],"lip-reading":[10],"with":[11,19,92,160,234],"hand":[12,30,45,134,158],"coding":[13],"to":[14,27,55,132,183],"facilitate":[15,56],"for":[17,71,106,187],"individuals":[18],"hearing":[20],"impairments.":[21],"Automatic":[22],"CS":[23,29,128,203],"Recognition":[24,121,140],"(ACSR)":[25],"aims":[26],"convert":[28],"gestures":[31],"and":[32,46,127,169,177,230],"lip":[33,47,144,161],"movements":[34,48],"into":[35],"text":[36],"via":[37],"AI-driven":[38],"methods.":[39,236],"Traditionally,":[40],"the":[41,50,101,147,188,200],"temporal":[42],"asynchrony":[43],"between":[44],"requires":[49],"design":[51],"of":[52,216],"complex":[53,90],"modules":[54],"effective":[57],"multimodal":[58],"fusion.":[59],"However,":[60],"constrained":[61],"by":[62,205],"limited":[63,93],"data":[64,94,207],"availability,":[65],"current":[66],"methods":[67],"demonstrate":[68,221],"insufficient":[69],"capacity":[70],"adequately":[72],"training":[73],"these":[74],"fusion":[75],"mechanisms,":[76],"resulting":[77],"in":[78,88,165,227],"suboptimal":[79],"performance.":[80],"Recently,":[81],"multi-agent":[82,104],"systems":[83],"have":[84],"shown":[85],"promising":[86],"capabilities":[87],"handling":[89],"tasks":[91],"availability.":[95],"To":[96,194],"this":[97,196],"end,":[98],"we":[99,198],"propose":[100],"first":[102,189],"collaborative":[103],"ACSR,":[107],"named":[108],"Cued-Agent.":[109],"It":[110],"integrates":[111,157],"four":[112],"specialized":[113],"sub-agents:":[114],"Multimodal":[116],"Large":[117],"Language":[118],"Model-based":[119],"Hand":[120,151],"agent":[122,141,154,173],"employs":[124],"keyframe":[125],"screening":[126],"expert":[129],"prompt":[130],"strategies":[131],"decode":[133],"movements,":[135],"pretrained":[137],"Transformer-based":[138],"Lip":[139],"extracts":[143],"features":[145,162],"from":[146,180,208],"input":[148],"video,":[149],"Prompt":[152],"Decoding":[153],"dynamically":[156],"prompts":[159],"during":[163],"inference":[164],"training-free":[167],"manner,":[168],"Self-Correction":[171],"Phoneme-to-Word":[172],"enables":[175],"post-processing":[176],"end-to-end":[178],"conversion":[179],"phoneme":[181],"sequences":[182],"natural":[184],"language":[185],"sentences":[186],"time":[190],"through":[191],"semantic":[192],"refinement.":[193],"support":[195],"study,":[197],"expand":[199],"existing":[201],"Mandarin":[202],"dataset":[204,215],"collecting":[206],"eight":[209],"hearing-impaired":[210,231],"cuers,":[211],"establishing":[212],"mixed":[214],"fourteen":[217],"subjects.":[218],"Extensive":[219],"experiments":[220],"our":[223],"Cued-Agent":[224],"performs":[225],"superbly":[226],"both":[228],"normal":[229],"scenarios":[232],"compared":[233],"state-of-the-art":[235],"The":[237],"implementation":[238],"available":[240],"at":[241],"https://github.com/DennisHgj/Cued-Agent.":[242]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}