{"id":"https://openalex.org/W3161697668","doi":"https://doi.org/10.1109/icassp39728.2021.9414553","title":"Fusing Information Streams in End-to-End Audio-Visual Speech Recognition","display_name":"Fusing Information Streams in End-to-End Audio-Visual Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161697668","doi":"https://doi.org/10.1109/icassp39728.2021.9414553","mag":"3161697668"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/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":["Institute of Communication Acoustics, Ruhr University, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"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":["Institute of Communication Acoustics, Ruhr University, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"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":["Institute of Communication Acoustics, Ruhr University, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"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":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3430","last_page":"3434"},"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":0.9997000098228455,"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":0.9987999796867371,"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":0.8244717121124268},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7115514874458313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6805890202522278},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5954980850219727},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.560552179813385},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4782665967941284},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.440359503030777},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.42994093894958496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40388116240501404},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.39162155985832214},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2536785900592804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8244717121124268},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7115514874458313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6805890202522278},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5954980850219727},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.560552179813385},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4782665967941284},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.440359503030777},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.42994093894958496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40388116240501404},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.39162155985832214},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2536785900592804},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W1494198834","https://openalex.org/W2015394094","https://openalex.org/W2023334087","https://openalex.org/W2026369565","https://openalex.org/W2085628288","https://openalex.org/W2104263160","https://openalex.org/W2151802380","https://openalex.org/W2219249508","https://openalex.org/W2395639500","https://openalex.org/W2405806852","https://openalex.org/W2406799669","https://openalex.org/W2521686623","https://openalex.org/W2696731410","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2936774411","https://openalex.org/W2944255943","https://openalex.org/W2952979007","https://openalex.org/W2962780374","https://openalex.org/W2963403868","https://openalex.org/W2963528589","https://openalex.org/W2963785710","https://openalex.org/W2972389417","https://openalex.org/W3008191852","https://openalex.org/W3011234510","https://openalex.org/W3036601975","https://openalex.org/W3045872183","https://openalex.org/W3099782249","https://openalex.org/W3103005696","https://openalex.org/W3106423890","https://openalex.org/W3115365386","https://openalex.org/W4385245566","https://openalex.org/W6605737493","https://openalex.org/W6629717138","https://openalex.org/W6688816777","https://openalex.org/W6713409533","https://openalex.org/W6734790163","https://openalex.org/W6739901393","https://openalex.org/W6754392867","https://openalex.org/W6754420807","https://openalex.org/W6780218876","https://openalex.org/W6781299282"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2620660273","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W2916997151","https://openalex.org/W2619911963","https://openalex.org/W3198455051","https://openalex.org/W3133352777","https://openalex.org/W4385611764"],"abstract_inverted_index":{"End-to-end":[0],"acoustic":[1,68,97],"speech":[2,41],"recognition":[3,42,47],"has":[4],"quickly":[5],"gained":[6],"widespread":[7],"popularity":[8],"and":[9,31,69,73,98,142,145,167],"shows":[10],"promising":[11],"results":[12],"in":[13,25,52,75,111],"many":[14,26],"studies.":[15],"Specifically":[16],"the":[17,34,46,81,88,96,118,122,137,150,164,171],"joint":[18],"transformer/CTC":[19,89],"model":[20,90,135],"pro-vides":[21],"very":[22],"good":[23],"performance":[24,35],"tasks.":[27],"However,":[28],"under":[29],"noisy":[30],"distorted":[32],"conditions,":[33,55],"still":[36],"degrades":[37],"notably.":[38],"While":[39],"audio-visual":[40,172],"can":[43],"significantly":[44],"improve":[45],"rate":[48,158],"of":[49,83,91,95,121,160],"end-to-end":[50,173],"models":[51],"such":[53],"poor":[54],"it":[56],"is":[57],"not":[58],"obvious":[59],"how":[60,84],"to":[61,85,131,163,170],"best":[62],"utilize":[63],"any":[64,92],"available":[65],"information":[66,110],"on":[67,136],"visual":[70,99],"signal":[71],"quality":[72],"reliability":[74,94,109],"these":[76],"models.":[77],"We":[78,102],"thus":[79],"consider":[80],"question":[82],"optimally":[86],"inform":[87],"time-variant":[93],"in-formation":[100],"streams.":[101],"propose":[103],"a":[104,112,132,154],"new":[105,151],"fusion":[106,114],"strategy,":[107],"incorporating":[108],"decision":[113],"net":[115],"that":[116],"considers":[117],"temporal":[119],"effects":[120],"attention":[123],"mechanism.":[124],"This":[125],"approach":[126],"yields":[127],"significant":[128],"improvements":[129],"compared":[130,169],"state-of-the-art":[133],"baseline":[134],"Lip":[138],"Reading":[139],"Sentences":[140],"2":[141],"3":[143],"(LRS2":[144],"LRS3)":[146],"corpus.":[147],"On":[148],"average,":[149],"sys-tem":[152],"achieves":[153],"relative":[155],"word":[156],"error":[157],"reduction":[159],"43%":[161],"com-pared":[162],"audio-only":[165],"setup":[166],"31%":[168],"baseline.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}