{"id":"https://openalex.org/W7148436364","doi":"https://doi.org/10.1109/asru65441.2025.11434748","title":"Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion","display_name":"Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148436364","doi":"https://doi.org/10.1109/asru65441.2025.11434748"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132775246","display_name":"DongHoon Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"DongHoon Lim","raw_affiliation_strings":["Hanyang University,Dept. Artificial Intelligence,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Dept. Artificial Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038488963","display_name":"Youngchae Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"YoungChae Kim","raw_affiliation_strings":["Hanyang University,Dept. Artificial Intelligence,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Dept. Artificial Intelligence,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132796506","display_name":"Dong-Hyun Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-Hyun Kim","raw_affiliation_strings":["Hanyang University,Dept. Electronic and Electrical Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Dept. Electronic and Electrical Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132799529","display_name":"Da-Hee Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Da-Hee Yang","raw_affiliation_strings":["Hanyang University,Dept. Electronic and Electrical Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Dept. Electronic and Electrical Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132816791","display_name":"Joon-Hyuk Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":["Hanyang University,Dept. Electronic and Electrical Engineering,Seoul,Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Hanyang University,Dept. Electronic and Electrical Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5132775246"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":null,"apc_paid":null,"fwci":1.4129,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87232294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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":0.9509000182151794,"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":0.9509000182151794,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.016300000250339508,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.006399999838322401,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.504800021648407},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4839000105857849},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.36890000104904175},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.3637000024318695},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31679999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.635200023651123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6068999767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5878000259399414},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.504800021648407},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321142","display_name":"Hanyang University","ror":"https://ror.org/046865y68"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1869491686","https://openalex.org/W2015394094","https://openalex.org/W2052666245","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2897067191","https://openalex.org/W2936774411","https://openalex.org/W3006974783","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3162293946","https://openalex.org/W3199527474","https://openalex.org/W4297841641","https://openalex.org/W4386071467","https://openalex.org/W4386076638","https://openalex.org/W4391021811","https://openalex.org/W4400645639","https://openalex.org/W4401112665","https://openalex.org/W4402112360","https://openalex.org/W4402774452","https://openalex.org/W4408351984","https://openalex.org/W4408355725","https://openalex.org/W4408355902","https://openalex.org/W7133185223","https://openalex.org/W7133196460"],"related_works":[],"abstract_inverted_index":{"Robust":[0],"audio-visual":[1,48],"speech":[2],"recognition":[3],"(AVSR)":[4],"in":[5,65,95],"noisy":[6],"environments":[7],"remains":[8],"challenging,":[9],"as":[10],"existing":[11],"systems":[12],"struggle":[13],"to":[14,73,100,113],"estimate":[15],"audio":[16,36,56,80],"reliability":[17],"and":[18,37,58,109],"dynamically":[19],"adjust":[20],"modality":[21,78],"reliance.":[22],"We":[23],"propose":[24],"router-gated":[25],"cross-modal":[26],"feature":[27,49],"fusion,":[28],"a":[29],"novel":[30],"AVSR":[31],"framework":[32],"that":[33,87,105],"adaptively":[34],"reweights":[35],"visual":[38,60,77],"features":[39],"based":[40],"on":[41,84],"token-level":[42],"acoustic":[43,118],"corruption":[44],"scores.":[45],"Using":[46],"an":[47,91],"fusion-based":[50],"router,":[51],"our":[52,88],"method":[53],"down-weights":[54],"unreliable":[55],"tokens":[57],"reinforces":[59],"cues":[61],"through":[62],"gated":[63],"cross-attention":[64],"each":[66],"decoder":[67],"layer.":[68],"This":[69],"enables":[70],"the":[71,76,107],"model":[72],"pivot":[74],"toward":[75],"when":[79],"quality":[81],"deteriorates.":[82],"Experiments":[83],"LRS3":[85],"demonstrate":[86],"approach":[89],"achieves":[90],"16.51-42.67%":[92],"relative":[93],"reduction":[94],"word":[96],"error":[97],"rate":[98],"compared":[99],"AV-HuBERT.":[101],"Ablation":[102],"studies":[103],"confirm":[104],"both":[106],"router":[108],"gating":[110],"mechanism":[111],"contribute":[112],"improved":[114],"robustness":[115],"under":[116],"real-world":[117],"noise.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-04-03T00:00:00"}