{"id":"https://openalex.org/W4408355485","doi":"https://doi.org/10.1109/icassp49660.2025.10890016","title":"Resource-Efficient and Noise-Robust Modality Fusion for Audio-Visual Speech Recognition","display_name":"Resource-Efficient and Noise-Robust Modality Fusion for Audio-Visual Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355485","doi":"https://doi.org/10.1109/icassp49660.2025.10890016"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890016","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/A5055069331","display_name":"Alexandros Koumparoulis","orcid":null},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Alexandros Koumparoulis","raw_affiliation_strings":["University of Thessaly,Dept. of Electrical and Computer Engineering,Volos,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Thessaly,Dept. of Electrical and Computer Engineering,Volos,Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["University of Thessaly,Dept. of Electrical and Computer Engineering,Volos,Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Thessaly,Dept. of Electrical and Computer Engineering,Volos,Greece","institution_ids":["https://openalex.org/I145722265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145722265"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04502146,"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/T10860","display_name":"Speech and Audio Processing","score":0.9937999844551086,"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":0.9937999844551086,"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":0.9477999806404114,"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/computer-science","display_name":"Computer science","score":0.7576647996902466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7440102696418762},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6296612024307251},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5545135736465454},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5073515772819519},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4593809247016907},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4234924912452698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3739436864852905},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.16958186030387878},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06454846262931824},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06035551428794861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576647996902466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7440102696418762},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6296612024307251},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5545135736465454},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5073515772819519},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4593809247016907},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4234924912452698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3739436864852905},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.16958186030387878},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06454846262931824},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06035551428794861},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890016","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":[{"id":"https://metadata.un.org/sdg/8","score":0.44999998807907104,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1503933356","https://openalex.org/W2033875152","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2790326622","https://openalex.org/W2889624961","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963785710","https://openalex.org/W3006974783","https://openalex.org/W3016011581","https://openalex.org/W3119418740","https://openalex.org/W3120735991","https://openalex.org/W3162707322","https://openalex.org/W4205996202","https://openalex.org/W4225305629","https://openalex.org/W4297841641","https://openalex.org/W4308236834","https://openalex.org/W4372267507","https://openalex.org/W4372346152","https://openalex.org/W4385245566","https://openalex.org/W4385571549","https://openalex.org/W4391021811","https://openalex.org/W4392901809","https://openalex.org/W6638667902","https://openalex.org/W6686207219","https://openalex.org/W6688816777","https://openalex.org/W6731370813","https://openalex.org/W6743446608","https://openalex.org/W6793164127"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2385859805","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":{"Resource-efficient":[0],"audio-visual":[1,28],"fusion":[2,39,156],"techniques":[3],"often":[4],"struggle":[5],"to":[6,34,134],"maintain":[7],"robust":[8],"performance":[9,160],"across":[10,161],"varying":[11],"acoustic":[12,78,163],"noise":[13,79,97],"conditions":[14],"in":[15,65,120,153],"speech":[16],"recognition":[17],"tasks.":[18],"This":[19],"paper":[20],"introduces":[21],"a":[22,127,143],"dynamic":[23],"routing":[24],"approach":[25,47,101],"for":[26,54,69],"noise-robust":[27],"fusion,":[29],"which":[30],"adaptively":[31],"directs":[32],"features":[33],"noise-specific":[35],"subnetworks.":[36],"Unlike":[37],"attention-based":[38],"methods":[40],"that":[41],"incur":[42],"quadratic":[43],"computational":[44,93],"complexity,":[45,50],"our":[46,59,100,150],"maintains":[48],"constant":[49],"making":[51],"it":[52,117],"suitable":[53],"resource-constrained":[55],"applications.":[56],"We":[57],"evaluate":[58],"method":[60,110,141],"on":[61],"the":[62,66,108,135,139],"\"Lip":[63],"Reading":[64],"Wild\"":[67],"dataset":[68],"isolated":[70],"(within":[71],"context)":[72],"word":[73,105],"recognition,":[74],"augmented":[75],"with":[76,125],"diverse":[77,162],"conditions.":[80],"Results":[81],"demonstrate":[82,149],"significant":[83],"improvements":[84],"over":[85],"feature":[86],"concatenation":[87],"and":[88,157],"gating":[89],"baselines":[90],"of":[91],"similar":[92],"complexity.":[94],"In":[95],"extreme":[96],"(-20":[98],"dB),":[99,124],"achieves":[102],"89.51%":[103],"mean":[104],"accuracy,":[106],"outperforming":[107],"next-best":[109],"(bimodal":[111],"gating)":[112],"by":[113],"0.63%":[114],"absolute.":[115],"Notably,":[116],"also":[118],"excels":[119],"low-noise":[121],"scenarios":[122],"(20":[123],"only":[126],"marginal":[128],"0.03%":[129],"absolute":[130,145],"accuracy":[131],"decrease":[132],"compared":[133],"audio-only":[136],"system,":[137],"while":[138,165],"second-best":[140],"shows":[142],"0.54%":[144],"decline.":[146],"These":[147],"results":[148],"method\u2019s":[151],"effectiveness":[152],"mitigating":[154],"catastrophic":[155],"maintaining":[158],"high":[159],"environments,":[164],"remaining":[166],"computationally":[167],"efficient.":[168]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}