{"id":"https://openalex.org/W4408355214","doi":"https://doi.org/10.1109/icassp49660.2025.10888246","title":"Inter- and Intra-Sentence Cuer-Invariant Representation Learning for Generalizable Cued Speech Recognition","display_name":"Inter- and Intra-Sentence Cuer-Invariant Representation Learning for Generalizable Cued Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355214","doi":"https://doi.org/10.1109/icassp49660.2025.10888246"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888246","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":"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/A5109662421","display_name":"Tianxin Xie","orcid":"https://orcid.org/0009-0002-1949-0516"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tianxin Xie","raw_affiliation_strings":["HKUST(GZ),Artificial Intelligence Thrust,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST(GZ),Artificial Intelligence Thrust,Guangzhou,China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418783","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-2011-2873"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["HKUST(GZ),Artificial Intelligence Thrust,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST(GZ),Artificial Intelligence Thrust,Guangzhou,China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02746587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9891999959945679,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9891999959945679,"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/T10860","display_name":"Speech and Audio Processing","score":0.9714000225067139,"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/T12031","display_name":"Speech and dialogue systems","score":0.9096999764442444,"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/speech-recognition","display_name":"Speech recognition","score":0.7131564021110535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6453862190246582},{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.5997191071510315},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.47573399543762207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46650853753089905},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4102003574371338},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1801910102367401},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.1067608892917633}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7131564021110535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6453862190246582},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.5997191071510315},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.47573399543762207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46650853753089905},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4102003574371338},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1801910102367401},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.1067608892917633}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888246","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":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"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":38,"referenced_works":["https://openalex.org/W1972680065","https://openalex.org/W2011674701","https://openalex.org/W2079623482","https://openalex.org/W2105594594","https://openalex.org/W2109455879","https://openalex.org/W2194775991","https://openalex.org/W2507009361","https://openalex.org/W2526425061","https://openalex.org/W2678916739","https://openalex.org/W2769205094","https://openalex.org/W2778635523","https://openalex.org/W2788787949","https://openalex.org/W2799813293","https://openalex.org/W2888888638","https://openalex.org/W2890197052","https://openalex.org/W2892209435","https://openalex.org/W2972620384","https://openalex.org/W2985525390","https://openalex.org/W2998687373","https://openalex.org/W3008402854","https://openalex.org/W3113399631","https://openalex.org/W3162249256","https://openalex.org/W3168640669","https://openalex.org/W3196404295","https://openalex.org/W3196826198","https://openalex.org/W4225685860","https://openalex.org/W4285606530","https://openalex.org/W4319586818","https://openalex.org/W4321780088","https://openalex.org/W4375868832","https://openalex.org/W4385245566","https://openalex.org/W4385823053","https://openalex.org/W4387969186","https://openalex.org/W4391759831","https://openalex.org/W4392903558","https://openalex.org/W6631190155","https://openalex.org/W6777179611","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2791807133","https://openalex.org/W4220960781","https://openalex.org/W2010535944","https://openalex.org/W2082933777","https://openalex.org/W2082371543","https://openalex.org/W3157864487","https://openalex.org/W3095039513","https://openalex.org/W3176549632","https://openalex.org/W62877638","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Cued":[0,23],"Speech":[1,24],"(CS)":[2],"is":[3,27],"a":[4,66,119,173],"visual":[5],"coding":[6],"system":[7],"that":[8,73,100,124,166],"combines":[9],"lip":[10,50,105,127],"movements":[11,128],"and":[12,51,106,117,129,151,181],"hand":[13,52,107,130],"gestures":[14,131],"to":[15,83,109,132,146,183],"represent":[16],"spoken":[17],"languages":[18],"for":[19,104],"hearing-impaired":[20],"people.":[21],"Automatic":[22],"Recognition":[25],"(ACSR)":[26],"an":[28,95,141],"emerging":[29],"research":[30],"topic,":[31],"but":[32],"the":[33,47,56,60,111,126,134,148,185,188],"cuer":[34,112],"(i.e.,":[35],"people":[36],"who":[37],"perform":[38],"CS)":[39],"generalization":[40,61,113],"problem":[41,114],"of":[42,187],"ACSR":[43,76],"remains":[44],"unexplored.":[45],"Moreover,":[46],"asynchrony":[48,136],"between":[49],"modalities":[53,108],"further":[54],"aggravates":[55],"challenges":[57],"associated":[58],"with":[59],"problem.":[62],"Therefore,":[63],"we":[64],"propose":[65],"novel":[67],"multi-modal,":[68],"cuer-invariant":[69,102],"representation":[70],"learning":[71,98,144,149],"framework":[72],"facilitates":[74],"generalizable":[75],"through":[77],"contrastive":[78,97],"learning,":[79],"enabling":[80],"our":[81,167],"model":[82],"recognize":[84],"unseen":[85],"cuers.":[86],"The":[87],"proposed":[88,189],"approach":[89],"comprises":[90],"three":[91],"key":[92],"components:":[93],"1)":[94],"inter-sentence":[96],"module":[99,123],"learns":[101],"representations":[103],"solve":[110],"in":[115,138],"ACSR;":[116,139],"2)":[118],"multi-level":[120],"intra-sentence":[121],"cross-attention":[122],"synchronizes":[125],"address":[133],"modality":[135],"issue":[137],"3)":[140],"easy-to-hard":[142],"progressive":[143],"strategy":[145],"stabilize":[147],"process":[150],"prevent":[152],"performance":[153],"degradation":[154],"on":[155,160],"hard":[156],"examples.":[157],"Extensive":[158],"experiments":[159],"two":[161],"available":[162],"CS":[163],"datasets":[164],"show":[165],"method":[168],"outperforms":[169],"previous":[170],"works":[171],"by":[172],"large":[174],"margin.":[175],"We":[176],"also":[177],"conduct":[178],"ablation":[179],"studies":[180],"visualization":[182],"demonstrate":[184],"effectiveness":[186],"method.":[190]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}