{"id":"https://openalex.org/W3199490845","doi":"https://doi.org/10.1109/mmsp53017.2021.9733452","title":"Large-vocabulary Audio-visual Speech Recognition in Noisy Environments","display_name":"Large-vocabulary Audio-visual Speech Recognition in Noisy Environments","publication_year":2021,"publication_date":"2021-10-06","ids":{"openalex":"https://openalex.org/W3199490845","doi":"https://doi.org/10.1109/mmsp53017.2021.9733452","mag":"3199490845"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp53017.2021.9733452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp53017.2021.9733452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)","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/A5019861809","display_name":"Wentao Yu","orcid":"https://orcid.org/0000-0002-0026-6955"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wentao Yu","raw_affiliation_strings":["Ruhr University,Institute of Communication Acoustics,Bochum,Germany","Institute of Communication Acoustics, Ruhr University, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ruhr University,Institute of Communication Acoustics,Bochum,Germany","institution_ids":[]},{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046724251","display_name":"Steffen Zeiler","orcid":"https://orcid.org/0009-0002-9594-2633"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Zeiler","raw_affiliation_strings":["Ruhr University,Institute of Communication Acoustics,Bochum,Germany","Institute of Communication Acoustics, Ruhr University, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ruhr University,Institute of Communication Acoustics,Bochum,Germany","institution_ids":[]},{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007017640","display_name":"Dorothea Kolossa","orcid":"https://orcid.org/0000-0003-0678-3053"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorothea Kolossa","raw_affiliation_strings":["Ruhr University,Institute of Communication Acoustics,Bochum,Germany","Institute of Communication Acoustics, Ruhr University, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ruhr University,Institute of Communication Acoustics,Bochum,Germany","institution_ids":[]},{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I904495901"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8303186893463135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7546700239181519},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6168623566627502},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5428696870803833},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5424150228500366},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5069854259490967},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5008630752563477},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5007579326629639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44622722268104553},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.41128265857696533},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3557816743850708},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3524640202522278},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33881914615631104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8303186893463135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7546700239181519},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6168623566627502},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5428696870803833},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5424150228500366},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5069854259490967},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5008630752563477},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5007579326629639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44622722268104553},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.41128265857696533},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3557816743850708},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3524640202522278},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33881914615631104},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp53017.2021.9733452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp53017.2021.9733452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W182561118","https://openalex.org/W1524333225","https://openalex.org/W1576996184","https://openalex.org/W1895481600","https://openalex.org/W1978380426","https://openalex.org/W2015394094","https://openalex.org/W2023334087","https://openalex.org/W2024490110","https://openalex.org/W2026369565","https://openalex.org/W2035777533","https://openalex.org/W2047619634","https://openalex.org/W2085628288","https://openalex.org/W2096391593","https://openalex.org/W2098562545","https://openalex.org/W2101200205","https://openalex.org/W2133115605","https://openalex.org/W2144121180","https://openalex.org/W2151802380","https://openalex.org/W2219249508","https://openalex.org/W2303024254","https://openalex.org/W2513140567","https://openalex.org/W2521686623","https://openalex.org/W2551572271","https://openalex.org/W2596627958","https://openalex.org/W2696731410","https://openalex.org/W2889448058","https://openalex.org/W2890952074","https://openalex.org/W2901907199","https://openalex.org/W2952746495","https://openalex.org/W2952979007","https://openalex.org/W2963356069","https://openalex.org/W2963528589","https://openalex.org/W2970971581","https://openalex.org/W3000086239","https://openalex.org/W3011234510","https://openalex.org/W3015383493","https://openalex.org/W3045872183","https://openalex.org/W3106423890","https://openalex.org/W3115365386","https://openalex.org/W4295312788","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6725923168","https://openalex.org/W6766978945","https://openalex.org/W7074232798"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2620660273","https://openalex.org/W3081187864","https://openalex.org/W2964829415","https://openalex.org/W4385611764","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1],"recognition":[2,10,33],"(AVSR)":[3],"can":[4,131],"effectively":[5],"and":[6,74,111,138,205],"significantly":[7],"improve":[8,40],"the":[9,54,58,81,98,135,147,163,192,209,223,232],"rates":[11],"of":[12,57,101,109,141,219,231],"small-vocabulary":[13],"systems,":[14,22],"compared":[15,221],"to":[16,39,67,96,222],"their":[17],"audio-only":[18,42,62,224],"counterparts.":[19],"For":[20],"large-vocabulary":[21,55],"however,":[23],"there":[24],"are":[25],"still":[26],"many":[27],"difficulties,":[28,83],"such":[29,50],"as":[30,153,155],"unsatisfactory":[31],"video":[32],"accuracies,":[34,69],"that":[35,162],"make":[36],"it":[37,130],"hard":[38],"over":[41],"baselines.":[43],"In":[44],"this":[45,71,118],"paper,":[46],"we":[47,84],"specifically":[48],"consider":[49],"scenarios,":[51],"focusing":[52],"on":[53,170],"task":[56],"LRS2":[59],"database,":[60],"where":[61,129],"performance":[63,195],"is":[64,94,120,196,200],"far":[65,181],"superior":[66,168],"video-only":[68],"making":[70],"an":[72],"interesting":[73],"challenging":[75],"setup":[76],"for":[77,122,186],"multi-modal":[78],"integration.To":[79],"address":[80],"inherent":[82],"propose":[85],"a":[86,90,107,126,213,228],"new":[87,164,210],"fusion":[88,165],"strategy:":[89],"recurrent":[91],"integration":[92,124,199,234],"network":[93,119],"trained":[95],"fuse":[97],"state":[99],"posteriors":[100],"multiple":[102,143],"single-modality":[103],"models,":[104,160],"guided":[105],"by":[106],"set":[108],"model-based":[110],"signal-based":[112],"stream":[113,123,176,188],"reliability":[114,137],"measures.":[115],"During":[116],"decoding,":[117],"used":[121],"within":[125],"hybrid":[127,158],"recognizer,":[128],"thus":[132],"cope":[133],"with":[134,149,156],"time-variant":[136],"information":[139],"content":[140],"its":[142],"feature":[144],"inputs.We":[145],"compare":[146],"results":[148],"end-to-end":[150],"AVSR":[151],"systems":[152],"well":[154],"competitive":[157],"baseline":[159],"finding":[161],"strategy":[166],"shows":[167],"results,":[169],"average":[171],"even":[172],"outperforming":[173],"oracle":[174],"dynamic":[175],"weighting,":[177],"which":[178],"has":[179],"so":[180],"marked":[182],"the\u2014realistically":[183],"unachievable\u2014upper":[184],"bound":[185],"standard":[187],"weighting.":[189],"Even":[190],"though":[191],"pure":[193],"lipreading":[194],"low,":[197],"audio-visual":[198],"helpful":[201],"under":[202],"all\u2014clean,":[203],"noisy,":[204],"reverberant\u2014conditions.":[206],"On":[207],"average,":[208],"system":[211],"achieves":[212],"relative":[214],"word":[215],"error":[216],"rate":[217],"reduction":[218],"42.18%":[220],"model,":[225],"pointing":[226],"at":[227],"high":[229],"effectiveness":[230],"proposed":[233],"approach.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}