{"id":"https://openalex.org/W7138293645","doi":"https://doi.org/10.1609/aaai.v40i38.40516","title":"Cueing Without Gapping: Cuer-Independent Cued Speech Recognition Powered by Cross-Cuer Invariant Modeling","display_name":"Cueing Without Gapping: Cuer-Independent Cued Speech Recognition Powered by Cross-Cuer Invariant Modeling","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138293645","doi":"https://doi.org/10.1609/aaai.v40i38.40516"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i38.40516","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40516","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i38.40516","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067178735","display_name":"Fengji Ma","orcid":"https://orcid.org/0000-0002-0896-5347"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fengji Ma","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669435","display_name":"Chenxing Li","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":"Chenxing Li","raw_affiliation_strings":["Tencent"],"affiliations":[{"raw_affiliation_string":"Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129711582","display_name":"Li Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067178735"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65168539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"38","first_page":"32410","last_page":"32418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5087000131607056,"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":0.5087000131607056,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.32260000705718994,"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/T11448","display_name":"Face recognition and analysis","score":0.033900000154972076,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6535999774932861},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.566100001335144},{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.5375999808311462},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.45100000500679016},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.44029998779296875},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4034999907016754},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.39890000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547000050544739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6553999781608582},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6535999774932861},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.44029998779296875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43389999866485596},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.38580000400543213},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C2779338814","wikidata":"https://www.wikidata.org/wiki/Q5179285","display_name":"Covert","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i38.40516","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40516","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i38.40516","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i38.40516","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5978108644485474,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Cued":[1,126],"Speech":[2],"Recognition":[3],"(ACSR)":[4],"is":[5],"a":[6,93,124],"vital":[7],"communication":[8],"system":[9],"designed":[10],"to":[11,26,41,45,60,77,109,151,170],"enhance":[12],"spoken":[13],"language":[14,134,143],"accessibility":[15],"for":[16],"the":[17,46,54,153,158,165,171,182],"hearing-impaired":[18],"by":[19,132,141],"combining":[20],"lip":[21],"movements":[22],"and":[23,106,114,176,184],"hand":[24],"gestures":[25],"encode":[27],"phonemes.":[28],"Despite":[29],"its":[30],"effectiveness,":[31],"current":[32],"ACSR":[33,187],"methods":[34],"face":[35],"significant":[36],"challenges,":[37],"including":[38,149],"poor":[39],"generalization":[40],"unseen":[42],"cuers":[43],"due":[44],"limited":[47],"scale":[48],"of":[49,56,167,186],"CS":[50,63,178],"datasets,":[51,179],"which":[52],"restricts":[53],"ability":[55],"existing":[57],"visual":[58,64],"encoder":[59],"capture":[61],"cuer-invariant":[62,112],"features.":[65],"Additionally,":[66],"previous":[67],"approaches":[68],"relying":[69],"on":[70,174],"Connectionist":[71],"Temporal":[72],"Classification":[73],"(CTC)":[74],"decoding":[75,140,160],"fail":[76],"incorporate":[78],"prior":[79],"linguistic":[80,147],"sequence":[81],"knowledge,":[82,148],"further":[83],"limiting":[84],"their":[85],"performance.":[86],"To":[87],"address":[88,152],"these":[89],"issues,":[90],"we":[91,122],"propose":[92],"novel":[94],"Two":[95],"Auxiliary":[96],"Modalities":[97],"guided":[98],"Cross-cuer":[99],"Invariant":[100],"Adaptation":[101],"method":[102,137],"(TACIA),":[103],"introducing":[104],"pose":[105],"text":[107],"modalities":[108],"help":[110],"extract":[111],"motion":[113],"semantic":[115],"features,":[116],"thereby":[117],"improving":[118],"generalization.":[119],"In":[120],"addition,":[121],"introduce":[123],"Visual-guided":[125],"Token":[127],"Prediction":[128],"(VG-NTP)":[129],"method,":[130],"inspired":[131],"large":[133],"models.":[135],"This":[136],"replaces":[138],"CTC":[139,159],"incorporating":[142],"modeling,":[144],"leveraging":[145],"rich":[146],"semantics,":[150],"suboptimal":[154],"issues":[155],"present":[156],"in":[157],"process.":[161],"Extensive":[162],"experiments":[163],"demonstrate":[164],"superiority":[166],"our":[168],"approach":[169],"state-of-the-art":[172],"(SOTA)":[173],"Chinese":[175],"British":[177],"significantly":[180],"advancing":[181],"accuracy":[183],"quality":[185],"systems.":[188]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}