{"id":"https://openalex.org/W4392904039","doi":"https://doi.org/10.1109/icassp48485.2024.10448048","title":"Audio-Visual Speech Recognition In-The-Wild: Multi-Angle Vehicle Cabin Corpus and Attention-Based Method","display_name":"Audio-Visual Speech Recognition In-The-Wild: Multi-Angle Vehicle Cabin Corpus and Attention-Based Method","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904039","doi":"https://doi.org/10.1109/icassp48485.2024.10448048"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5036332146","display_name":"Alexandr Axyonov","orcid":"https://orcid.org/0000-0002-7479-2851"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]},{"id":"https://openalex.org/I4210144352","display_name":"State Research Center of the Russian Federation","ror":"https://ror.org/04qpssw85","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210144352"]},{"id":"https://openalex.org/I4210165514","display_name":"Photochemistry Center","ror":"https://ror.org/05s61gx60","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210145551","https://openalex.org/I4210165514"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexandr Axyonov","raw_affiliation_strings":["St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)","institution_ids":["https://openalex.org/I1313323035","https://openalex.org/I4210144352","https://openalex.org/I4210165514"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008249311","display_name":"Dmitry Ryumin","orcid":"https://orcid.org/0000-0002-7935-0569"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]},{"id":"https://openalex.org/I4210144352","display_name":"State Research Center of the Russian Federation","ror":"https://ror.org/04qpssw85","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210144352"]},{"id":"https://openalex.org/I4210165514","display_name":"Photochemistry Center","ror":"https://ror.org/05s61gx60","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210145551","https://openalex.org/I4210165514"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry Ryumin","raw_affiliation_strings":["St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)","institution_ids":["https://openalex.org/I1313323035","https://openalex.org/I4210144352","https://openalex.org/I4210165514"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013493484","display_name":"Denis Ivanko","orcid":"https://orcid.org/0000-0003-0412-7765"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]},{"id":"https://openalex.org/I4210144352","display_name":"State Research Center of the Russian Federation","ror":"https://ror.org/04qpssw85","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210144352"]},{"id":"https://openalex.org/I4210165514","display_name":"Photochemistry Center","ror":"https://ror.org/05s61gx60","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210145551","https://openalex.org/I4210165514"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Denis Ivanko","raw_affiliation_strings":["St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)","institution_ids":["https://openalex.org/I1313323035","https://openalex.org/I4210144352","https://openalex.org/I4210165514"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016499776","display_name":"Alexey Kashevnik","orcid":"https://orcid.org/0000-0001-6503-1447"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Kashevnik","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia","ITMO University, St. Petersburg, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]},{"raw_affiliation_string":"ITMO University, St. Petersburg, Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032870944","display_name":"Alexey Karpov","orcid":"https://orcid.org/0000-0003-3424-652X"},"institutions":[{"id":"https://openalex.org/I1313323035","display_name":"Russian Academy of Sciences","ror":"https://ror.org/05qrfxd25","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035"]},{"id":"https://openalex.org/I4210144352","display_name":"State Research Center of the Russian Federation","ror":"https://ror.org/04qpssw85","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210144352"]},{"id":"https://openalex.org/I4210165514","display_name":"Photochemistry Center","ror":"https://ror.org/05s61gx60","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210145551","https://openalex.org/I4210165514"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Karpov","raw_affiliation_strings":["St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"St. Petersburg Federal Research Center of the Russian Academy of Sciences (SPC RAS)","institution_ids":["https://openalex.org/I1313323035","https://openalex.org/I4210144352","https://openalex.org/I4210165514"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8195","last_page":"8199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9965000152587891,"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/robustness","display_name":"Robustness (evolution)","score":0.7663455605506897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7342323064804077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7272570133209229},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4877982437610626},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.465433269739151},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43338584899902344},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43154066801071167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4268726110458374},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41560304164886475},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3711391091346741},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30144399404525757},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13115280866622925},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08509021997451782}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7663455605506897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7342323064804077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7272570133209229},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4877982437610626},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.465433269739151},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43338584899902344},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43154066801071167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4268726110458374},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41560304164886475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3711391091346741},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30144399404525757},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13115280866622925},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08509021997451782},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/5"}],"awards":[{"id":"https://openalex.org/G2928192979","display_name":null,"funder_award_id":"000000D730321P5Q0002","funder_id":"https://openalex.org/F4320319755","funder_display_name":"Analytical Center for the Government of the Russian Federation"},{"id":"https://openalex.org/G6047160967","display_name":null,"funder_award_id":"IGK 000000D730321P5Q0002","funder_id":"https://openalex.org/F4320319755","funder_display_name":"Analytical Center for the Government of the Russian Federation"},{"id":"https://openalex.org/G8870280834","display_name":null,"funder_award_id":"70-2021-00141","funder_id":"https://openalex.org/F4320319755","funder_display_name":"Analytical Center for the Government of the Russian Federation"}],"funders":[{"id":"https://openalex.org/F4320319755","display_name":"Analytical Center for the Government of the Russian Federation","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W142945732","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2513259840","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2810311710","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2948210185","https://openalex.org/W2963723765","https://openalex.org/W2963785710","https://openalex.org/W2999528291","https://openalex.org/W3034681889","https://openalex.org/W3134142934","https://openalex.org/W3136499730","https://openalex.org/W3162293946","https://openalex.org/W3203789665","https://openalex.org/W4312920990","https://openalex.org/W4375839990","https://openalex.org/W4380373744","https://openalex.org/W4385245566","https://openalex.org/W4385822258","https://openalex.org/W4385822505","https://openalex.org/W4385822729","https://openalex.org/W4385823040","https://openalex.org/W6754420807","https://openalex.org/W6773827925","https://openalex.org/W6810168380","https://openalex.org/W6811561406"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2072884270","https://openalex.org/W4252682934","https://openalex.org/W2089240210"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1],"recognition":[2],"(AVSR)":[3],"gains":[4],"increasing":[5],"attention":[6,84],"as":[7],"an":[8],"important":[9],"part":[10],"of":[11,45],"human-machine":[12],"interaction.":[13],"However,":[14],"the":[15,42,63],"publicly":[16],"available":[17],"corpora":[18],"are":[19],"limited,":[20],"particularly":[21],"in":[22,35,48,69,110],"driving":[23,71],"conditions":[24],"with":[25,107],"prevalent":[26],"background":[27],"noise.":[28],"Research":[29],"so":[30],"far":[31],"has":[32],"been":[33],"collected":[34,78],"constrained":[36],"environments,":[37],"and":[38,97],"thus":[39],"cannot":[40],"reflect":[41],"true":[43],"performance":[44],"AVSR":[46,68,88],"systems":[47],"real-world":[49],"scenarios.":[50],"Moreover,":[51],"data":[52],"for":[53,65,89],"languages":[54],"other":[55],"than":[56],"English":[57],"is":[58],"often":[59],"unavailable.":[60],"To":[61],"meet":[62],"request":[64],"research":[66],"on":[67],"unconstrained":[70],"conditions,":[72],"this":[73],"paper":[74],"presents":[75],"a":[76,82],"corpus":[77],"\u2018in-the-wild\u2019.":[79],"We":[80],"propose":[81],"cross-modal":[83],"method":[85],"enhancing":[86],"multi-angle":[87],"vehicles,":[90],"leveraging":[91],"visual":[92],"context":[93],"to":[94],"improve":[95],"accuracy":[96,109],"noise":[98],"robustness.":[99],"Our":[100],"proposed":[101],"model":[102],"achieves":[103],"state-of-the-art":[104],"(SOTA)":[105],"results":[106],"98.65%":[108],"recognizing":[111],"driver":[112],"voice":[113],"commands.":[114],"For":[115],"more":[116],"details,":[117],"visit":[118],"our":[119],"project":[120],"page":[121],"<sup":[122],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[123],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[124],".":[125]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
