{"id":"https://openalex.org/W7124866512","doi":"https://doi.org/10.1109/cbmi66578.2025.11339323","title":"Lip Reading Across Languages: A Cross-Modal Framework Leveraging Foundation Models","display_name":"Lip Reading Across Languages: A Cross-Modal Framework Leveraging Foundation Models","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124866512","doi":"https://doi.org/10.1109/cbmi66578.2025.11339323"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5025204322","display_name":"Ruxandra \u021aapu","orcid":"https://orcid.org/0000-0003-3170-4150"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ruxandra TAPU","raw_affiliation_strings":["Institut Polytechnique de Paris,SAMOVAR, Telecom SudParis,Palaiseau,France,91120"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,SAMOVAR, Telecom SudParis,Palaiseau,France,91120","institution_ids":["https://openalex.org/I4210145102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106442601","display_name":"Bogdan Mocanu","orcid":"https://orcid.org/0000-0001-8010-9943"},"institutions":[{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bogdan MOCANU","raw_affiliation_strings":["Institut Polytechnique de Paris,SAMOVAR, Telecom SudParis,Palaiseau,France,91120"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,SAMOVAR, Telecom SudParis,Palaiseau,France,91120","institution_ids":["https://openalex.org/I4210145102"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025204322"],"corresponding_institution_ids":["https://openalex.org/I4210145102"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67243593,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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":0.9916999936103821,"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/T11448","display_name":"Face recognition and analysis","score":0.003599999938160181,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/generalization","display_name":"Generalization","score":0.6360999941825867},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5776000022888184},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4697999954223633},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44830000400543213},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35510000586509705},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3353999853134155},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.30709999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491000294685364},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49320000410079956},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45840001106262207},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43700000643730164},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38690000772476196},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2660999894142151}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8125494122505188}],"awards":[{"id":"https://openalex.org/G5233809703","display_name":null,"funder_award_id":"PN-IV-P6-6.3-SOL-2024-0049","funder_id":"https://openalex.org/F4320336189","funder_display_name":"Colegiul Consultativ pentru Cercetare-Dezvoltare \u015fi Inovare"},{"id":"https://openalex.org/G6405268647","display_name":null,"funder_award_id":"PN-IV-P6-6.3-SOL-2024-2-0238","funder_id":"https://openalex.org/F4320318622","funder_display_name":"Ministerul Cercet\u0103rii, Inov\u0103rii \u015fi Digitaliz\u0103rii"}],"funders":[{"id":"https://openalex.org/F4320318622","display_name":"Ministerul Cercet\u0103rii, Inov\u0103rii \u015fi Digitaliz\u0103rii","ror":null},{"id":"https://openalex.org/F4320323983","display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","ror":"https://ror.org/01q7jq182"},{"id":"https://openalex.org/F4320336189","display_name":"Colegiul Consultativ pentru Cercetare-Dezvoltare \u015fi Inovare","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2113814270","https://openalex.org/W2404704342","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2890952074","https://openalex.org/W2963307811","https://openalex.org/W2963654155","https://openalex.org/W2964283370","https://openalex.org/W2972756321","https://openalex.org/W2995028981","https://openalex.org/W3035042697","https://openalex.org/W3162293946","https://openalex.org/W3197771105","https://openalex.org/W4372346152","https://openalex.org/W4385245566","https://openalex.org/W4385822293","https://openalex.org/W4390872483","https://openalex.org/W4390874021","https://openalex.org/W4392908934","https://openalex.org/W4392932002","https://openalex.org/W4402112360","https://openalex.org/W4402684056","https://openalex.org/W4408345746","https://openalex.org/W4408354236"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Speech":[1],"Recognition":[2],"(VSR),":[3],"or":[4,16],"lip":[5],"reading,":[6],"is":[7,53],"essential":[8],"in":[9,128],"scenarios":[10],"where":[11],"audio":[12,63],"signals":[13],"are":[14],"absent":[15],"degraded.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"introduce":[22],"an":[23],"end-to-end":[24],"framework":[25,96],"that":[26,39,58],"integrates":[27],"visual":[28,65,84],"representations":[29],"into":[30],"a":[31,54,133],"pretrained":[32],"Large":[33],"Language":[34],"Model":[35],"(LLM),":[36],"enabling":[37],"transcription":[38,92],"leverages":[40],"multimodal":[41,75],"context":[42],"for":[43,73],"improved":[44],"accuracy":[45],"and":[46,64,107,141],"robustness.":[47],"The":[48,94],"core":[49],"of":[50,121],"our":[51],"method":[52],"cross-modal":[55],"attention":[56],"module":[57],"establishes":[59],"fine-grained":[60],"alignment":[61],"between":[62],"streams":[66],"during":[67],"training,":[68],"paired":[69],"with":[70],"lightweight":[71],"adapters":[72],"seamless":[74],"integration.":[76],"At":[77],"inference,":[78],"the":[79,118,122],"model":[80],"relies":[81],"solely":[82],"on":[83,131],"data,":[85],"benefiting":[86],"from":[87],"audio-guided":[88],"learning":[89],"to":[90],"enhance":[91],"accuracy.":[93],"proposed":[95],"enables":[97],"robust":[98],"adaptation":[99],"across":[100,111],"varied":[101],"linguistic":[102],"conditions,":[103],"yielding":[104,124],"superior":[105],"generalization":[106,140],"performance.":[108],"Our":[109],"experiments":[110],"Latin-script":[112],"languages":[113],"demonstrate":[114],"consistent":[115],"improvements":[116,143],"over":[117],"current":[119],"state":[120],"art,":[123],"1.53%\u20133.83%":[125],"absolute":[126],"reductions":[127],"WER.":[129],"Experiments":[130],"Romanian,":[132],"previously":[134],"unseen":[135],"language,":[136],"reveal":[137],"strong":[138],"zero-shot":[139],"significant":[142],"after":[144],"fine-tunning.":[145]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-21T00:00:00"}