{"id":"https://openalex.org/W3115365386","doi":"https://doi.org/10.23919/eusipco47968.2020.9287841","title":"Multimodal Integration for Large-Vocabulary Audio-Visual Speech Recognition","display_name":"Multimodal Integration for Large-Vocabulary Audio-Visual Speech Recognition","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3115365386","doi":"https://doi.org/10.23919/eusipco47968.2020.9287841","mag":"3115365386"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287841","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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":0.8233615159988403},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7600827217102051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7190119028091431},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6460586190223694},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4799221456050873},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.477627694606781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4359533488750458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38633108139038086},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26983731985092163},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.25054389238357544},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0738910436630249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8233615159988403},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7600827217102051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7190119028091431},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6460586190223694},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4799221456050873},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.477627694606781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4359533488750458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38633108139038086},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26983731985092163},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25054389238357544},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0738910436630249},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287841","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W2023334087","https://openalex.org/W2024490110","https://openalex.org/W2098562545","https://openalex.org/W2103621378","https://openalex.org/W2104263160","https://openalex.org/W2113642685","https://openalex.org/W2131342762","https://openalex.org/W2133564696","https://openalex.org/W2144121180","https://openalex.org/W2155998647","https://openalex.org/W2219249508","https://openalex.org/W2406799669","https://openalex.org/W2513140567","https://openalex.org/W2521686623","https://openalex.org/W2551572271","https://openalex.org/W2586219009","https://openalex.org/W2696731410","https://openalex.org/W2889448058","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2944255943","https://openalex.org/W2952746495","https://openalex.org/W2963528589","https://openalex.org/W2964308564","https://openalex.org/W3011234510","https://openalex.org/W3102469722","https://openalex.org/W3103005696","https://openalex.org/W3106423890","https://openalex.org/W6631362777","https://openalex.org/W6679434410","https://openalex.org/W6688816777","https://openalex.org/W6725923168","https://openalex.org/W6754392867"],"related_works":["https://openalex.org/W2539919382","https://openalex.org/W22517275","https://openalex.org/W2042419400","https://openalex.org/W2122924390","https://openalex.org/W2064347532","https://openalex.org/W2131711534","https://openalex.org/W2589081144","https://openalex.org/W2171620991","https://openalex.org/W189256204","https://openalex.org/W90026711"],"abstract_inverted_index":{"For":[0],"many":[1,106],"small-":[2],"and":[3,90,102,111],"medium-vocabulary":[4],"tasks,":[5],"audio-visual":[6],"speech":[7,68],"recognition":[8,13,71,110],"can":[9],"significantly":[10],"improve":[11],"the":[12,27,38,50,70,78,83,87,126,142,148],"rates":[14],"compared":[15],"to":[16,43,75,120,138],"audio-only":[17],"systems.":[18],"However,":[19],"there":[20],"is":[21,59,118,125,151],"still":[22],"an":[23,47],"ongoing":[24],"debate":[25],"regarding":[26],"best":[28],"combination":[29],"strategy":[30],"for":[31,37,63,135],"multi-modal":[32],"information,":[33],"which":[34,117,133],"should":[35],"allow":[36,134],"translation":[39],"of":[40,52,86,96,108,128,144],"these":[41],"gains":[42],"large-vocabulary":[44,67,84],"recognition.":[45],"While":[46],"integration":[48,97,101],"at":[49],"level":[51],"state-posterior":[53],"probabilities,":[54],"using":[55],"dynamic":[56,112,129],"stream":[57,113,130],"weighting,":[58],"almost":[60],"universally":[61],"helpful":[62],"small-vocabulary":[64],"systems,":[65],"in":[66],"recognition,":[69],"accuracy":[72],"remains":[73],"difficult":[74],"improve.":[76],"In":[77],"following,":[79],"we":[80,91],"specifically":[81],"consider":[82],"task":[85],"LRS2":[88],"database,":[89],"investigate":[92],"a":[93],"broad":[94],"range":[95],"strategies,":[98],"comparing":[99],"early":[100],"end-to-end":[103],"learning":[104],"with":[105],"versions":[107],"hybrid":[109,136],"weighting.":[114],"One":[115],"aspect,":[116],"shown":[119],"provide":[121],"much":[122],"benefit":[123],"here,":[124],"use":[127],"reliability":[131],"indicators,":[132],"architectures":[137],"strongly":[139],"profit":[140],"from":[141],"inclusion":[143],"visual":[145],"information":[146],"whenever":[147],"audio":[149],"channel":[150],"distorted":[152],"even":[153],"slightly.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}