{"id":"https://openalex.org/W4392904484","doi":"https://doi.org/10.1109/icassp48485.2024.10445891","title":"Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer","display_name":"Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904484","doi":"https://doi.org/10.1109/icassp48485.2024.10445891"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445891","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":"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/A5057004182","display_name":"Maxime Burchi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maxime Burchi","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069691915","display_name":"Krishna C. Puvvada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna C. Puvvada","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052236177","display_name":"Radu Timofte","orcid":"https://orcid.org/0000-0002-1478-0402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radu Timofte","raw_affiliation_strings":["CAIDAS & IFI, University of Würzburg,Computer Vision Lab,Germany"],"affiliations":[{"raw_affiliation_string":"CAIDAS & IFI, University of Würzburg,Computer Vision Lab,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057004182"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":4.5215,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.95240135,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10211","last_page":"10215"},"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":0.9969000220298767,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9932000041007996,"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/computer-science","display_name":"Computer science","score":0.8321335315704346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8227732181549072},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6413152813911438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48510754108428955},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.47342589497566223},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4577878713607788},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.42638924717903137},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4207850694656372},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33587461709976196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321335315704346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8227732181549072},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6413152813911438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48510754108428955},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.47342589497566223},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4577878713607788},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.42638924717903137},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4207850694656372},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33587461709976196},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445891","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":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2194775991","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2808631503","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2908510526","https://openalex.org/W2949662773","https://openalex.org/W2963250244","https://openalex.org/W2963785710","https://openalex.org/W2974231335","https://openalex.org/W3015995734","https://openalex.org/W3034552680","https://openalex.org/W3035042697","https://openalex.org/W3097777922","https://openalex.org/W3102469722","https://openalex.org/W3104792420","https://openalex.org/W3162249256","https://openalex.org/W3162293946","https://openalex.org/W3197140813","https://openalex.org/W4221153068","https://openalex.org/W4285595742","https://openalex.org/W4289665794","https://openalex.org/W4297841641","https://openalex.org/W4297841719","https://openalex.org/W4307286264","https://openalex.org/W4311553423","https://openalex.org/W4319300051","https://openalex.org/W4321648689","https://openalex.org/W4372346152","https://openalex.org/W4376481237","https://openalex.org/W4385822729","https://openalex.org/W4390040710","https://openalex.org/W4391021542","https://openalex.org/W4391021811","https://openalex.org/W6754420807","https://openalex.org/W6757817989","https://openalex.org/W6767671539","https://openalex.org/W6810168380","https://openalex.org/W6839936984","https://openalex.org/W6847363464","https://openalex.org/W6847652939","https://openalex.org/W6850461100"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218"],"abstract_inverted_index":{"Humans":[0],"are":[1],"adept":[2],"at":[3,149],"leveraging":[4],"visual":[5,66],"cues":[6],"from":[7],"lip":[8],"movements":[9],"for":[10,82],"recognizing":[11],"speech":[12,28,147],"in":[13,30,126],"adverse":[14],"listening":[15],"conditions.":[16,32],"Audio-Visual":[17],"Speech":[18],"Recognition":[19],"(AVSR)":[20],"models":[21],"follow":[22],"similar":[23],"approach":[24],"to":[25,45,61,128,141],"achieve":[26],"robust":[27],"recognition":[29,148],"noisy":[31],"In":[33],"this":[34],"work,":[35],"we":[36,53,133],"present":[37],"a":[38,69],"multilingual":[39,91],"AVSR":[40],"model":[41,60,98,118,140],"incorporating":[42],"several":[43],"enhancements":[44],"improve":[46],"performance":[47,102],"and":[48,65,94,145],"audio":[49,64],"noise":[50],"robustness.":[51],"Notably,":[52],"adapt":[54],"the":[55,76,104,112,129,135,138],"recently":[56,113],"proposed":[57,97,139],"Fast":[58],"Conformer":[59],"process":[62],"both":[63],"modalities":[67],"using":[68],"novel":[70],"hybrid":[71],"CTC/RNN-T":[72],"architecture.":[73],"We":[74],"increase":[75],"amount":[77],"of":[78,89,109,124,137],"audio-visual":[79,146],"training":[80],"data":[81],"six":[83],"distinct":[84],"languages,":[85],"generating":[86],"automatic":[87],"transcriptions":[88],"unlabelled":[90],"datasets":[92],"(VoxCeleb2":[93],"AVSpeech).":[95],"Our":[96],"achieves":[99],"new":[100],"state-of-the-art":[101],"on":[103],"LRS3":[105],"dataset,":[106],"reaching":[107],"WER":[108],"0.8%.":[110],"On":[111],"introduced":[114],"MuAViC":[115],"benchmark,":[116],"our":[117],"yields":[119],"an":[120],"absolute":[121],"average-WER":[122],"reduction":[123],"11.9%":[125],"comparison":[127],"original":[130],"baseline.":[131],"Finally,":[132],"demonstrate":[134],"ability":[136],"perform":[142],"audio-only,":[143],"visual-only,":[144],"test":[150],"time.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}