{"id":"https://openalex.org/W4408355499","doi":"https://doi.org/10.1109/icassp49660.2025.10888331","title":"Injecting Visual Features into Whisper for Parameter-Efficient Noise-Robust Audio-Visual Speech Recognition","display_name":"Injecting Visual Features into Whisper for Parameter-Efficient Noise-Robust Audio-Visual Speech Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355499","doi":"https://doi.org/10.1109/icassp49660.2025.10888331"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888331","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":"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":null,"display_name":"Zhao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112025134","display_name":"Yue Heng Yeo","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yue Heng Yeo","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101966096","display_name":"Rui Jiang","orcid":"https://orcid.org/0000-0001-5007-5746"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Jiang","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103805225","display_name":"Xiao Fu","orcid":"https://orcid.org/0009-0006-6601-5290"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Fu","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101543632","display_name":"Weiguang Chen","orcid":"https://orcid.org/0000-0002-7945-3197"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiguang Chen","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050052141","display_name":"Wei Xi","orcid":"https://orcid.org/0000-0001-9348-2982"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xi","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101471775","display_name":"Jizhong Zhao","orcid":"https://orcid.org/0000-0003-1037-9619"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jizhong Zhao","raw_affiliation_strings":["Xi’an Jiaotong University,School of Computer Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04638647,"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":0.9993000030517578,"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9914000034332275,"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":0.9836000204086304,"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":0.7917377352714539},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.788909912109375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7652510404586792},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5787697434425354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48134884238243103},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15004169940948486},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12812873721122742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917377352714539},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.788909912109375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7652510404586792},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5787697434425354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48134884238243103},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15004169940948486},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12812873721122742}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888331","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2890952074","https://openalex.org/W3006974783","https://openalex.org/W3035042697","https://openalex.org/W3162293946","https://openalex.org/W3204696009","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221153521","https://openalex.org/W4285247752","https://openalex.org/W4385822786","https://openalex.org/W4386076133","https://openalex.org/W4391021811","https://openalex.org/W4392903956","https://openalex.org/W4392904451","https://openalex.org/W4392909314","https://openalex.org/W4402112360","https://openalex.org/W6754420807","https://openalex.org/W6774670964","https://openalex.org/W6780218876","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6810007534","https://openalex.org/W6810168380","https://openalex.org/W6810673746","https://openalex.org/W6839936984","https://openalex.org/W6846807982","https://openalex.org/W6847363464","https://openalex.org/W6847652939","https://openalex.org/W6849177959","https://openalex.org/W6850218400","https://openalex.org/W6852489829","https://openalex.org/W6859549871"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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/W3137890128"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,12,56,179],"recognition":[2,13],"(AVSR)":[3],"aims":[4],"to":[5,68,115,142],"enhance":[6],"the":[7,62,98,102,109,156],"robustness":[8],"of":[9,44],"an":[10],"automatic":[11],"(ASR)":[14],"systems":[15],"by":[16,93],"incorporating":[17],"visual":[18,70,89,95,122,148],"information":[19,73,123,149],"from":[20,35,97],"lip":[21],"movements,":[22],"especially":[23],"in":[24,74,113],"challenging":[25],"noisy":[26],"environments.":[27],"Nevertheless,":[28],"most":[29],"current":[30],"approaches":[31],"either":[32],"involve":[33],"training":[34,138],"scratch":[36],"or":[37],"fully":[38],"finetuning":[39],"a":[40,84,136,171],"pre-trained":[41,103],"model,":[42],"both":[43],"which":[45],"incur":[46],"significant":[47],"computational":[48],"costs":[49],"and":[50,71,90,119,132,147,174],"are":[51],"often":[52],"impractical":[53],"for":[54,64,177],"large-scale":[55],"foundation":[57],"models.":[58],"This":[59],"gap":[60],"highlights":[61],"need":[63],"more":[65,172],"efficient":[66,173],"methods":[67,165],"leverage":[69],"acoustic":[72,91],"AVSR":[75],"tasks.":[76],"To":[77],"address":[78],"this":[79],"challenge,":[80],"we":[81],"propose":[82],"AVWhisper,":[83],"parameter-efficient":[85],"model":[86],"that":[87,160],"integrates":[88,120],"representations":[92],"injecting":[94],"features":[96],"AV-HuBERT":[99],"encoder":[100],"into":[101],"Whisper":[104,114],"model.":[105],"Our":[106],"approach":[107],"leverages":[108],"existing":[110],"attention":[111],"mechanisms":[112],"facilitate":[116],"cross-modal":[117],"interaction":[118],"auxiliary":[121],"through":[124],"lightweight":[125],"adapters":[126],"based":[127],"on":[128,155],"Low-Rank":[129],"Adaptation":[130],"(LoRA)":[131],"prompt-based":[133],"techniques.":[134],"Furthermore,":[135],"two-phase":[137],"strategy":[139],"is":[140],"adopted":[141],"effectively":[143],"handle":[144],"cross-domain":[145],"differences":[146],"injection":[150],"problems":[151],"respectively.":[152],"Extensive":[153],"experiments":[154],"LRS3-TED":[157],"dataset":[158],"demonstrate":[159],"AVWhisper":[161],"consistently":[162],"outperforms":[163],"state-of-the-art":[164],"across":[166],"various":[167],"noise":[168],"conditions,":[169],"offering":[170],"scalable":[175],"solution":[176],"audio-visual":[178],"recognition.":[180]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}