{"id":"https://openalex.org/W4287219610","doi":"https://doi.org/10.3390/s22155501","title":"Reliability-Based Large-Vocabulary Audio-Visual Speech Recognition","display_name":"Reliability-Based Large-Vocabulary Audio-Visual Speech Recognition","publication_year":2022,"publication_date":"2022-07-23","ids":{"openalex":"https://openalex.org/W4287219610","doi":"https://doi.org/10.3390/s22155501","pmid":"https://pubmed.ncbi.nlm.nih.gov/35898005"},"language":"en","primary_location":{"id":"doi:10.3390/s22155501","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22155501","pdf_url":"https://www.mdpi.com/1424-8220/22/15/5501/pdf?version=1659597321","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/22/15/5501/pdf?version=1659597321","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Wentao Yu","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr University Bochum, 44801 Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University Bochum, 44801 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, 44801 Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University Bochum, 44801 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, 44801 Bochum, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0678-3053","affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University Bochum, 44801 Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5019861809"],"corresponding_institution_ids":["https://openalex.org/I904495901"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":0.707,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66619694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"22","issue":"15","first_page":"5501","last_page":"5501"},"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":0.9991000294685364,"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":0.9990000128746033,"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":0.7833483815193176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7401455640792847},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6651176810264587},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6404017806053162},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5972397327423096},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5027799606323242},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.498460054397583},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47626206278800964},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.460082083940506},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4398244321346283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3896624445915222},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07861453294754028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833483815193176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7401455640792847},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6651176810264587},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6404017806053162},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5972397327423096},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5027799606323242},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.498460054397583},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47626206278800964},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.460082083940506},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4398244321346283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3896624445915222},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07861453294754028},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014825","descriptor_name":"Vocabulary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014825","descriptor_name":"Vocabulary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014825","descriptor_name":"Vocabulary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s22155501","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22155501","pdf_url":"https://www.mdpi.com/1424-8220/22/15/5501/pdf?version=1659597321","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:35898005","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35898005","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:f6d9771b093b467a8280a333d3188c45","is_oa":true,"landing_page_url":"https://doaj.org/article/f6d9771b093b467a8280a333d3188c45","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 22, Iss 15, p 5501 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/15/5501/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22155501","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 22; Issue 15; Pages: 5501","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9370936","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9370936","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s22155501","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22155501","pdf_url":"https://www.mdpi.com/1424-8220/22/15/5501/pdf?version=1659597321","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G917135823","display_name":null,"funder_award_id":"KO3434/4-2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4287219610.pdf","grobid_xml":"https://content.openalex.org/works/W4287219610.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W89614834","https://openalex.org/W142803501","https://openalex.org/W182561118","https://openalex.org/W1494198834","https://openalex.org/W1576996184","https://openalex.org/W1610379133","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/W2096391593","https://openalex.org/W2098562545","https://openalex.org/W2101200205","https://openalex.org/W2132991150","https://openalex.org/W2133115605","https://openalex.org/W2144121180","https://openalex.org/W2144499799","https://openalex.org/W2151802380","https://openalex.org/W2303024254","https://openalex.org/W2327501763","https://openalex.org/W2395639500","https://openalex.org/W2405806852","https://openalex.org/W2521686623","https://openalex.org/W2551572271","https://openalex.org/W2696731410","https://openalex.org/W2889448058","https://openalex.org/W2890952074","https://openalex.org/W2901907199","https://openalex.org/W2935794029","https://openalex.org/W2944255943","https://openalex.org/W2952979007","https://openalex.org/W2963356069","https://openalex.org/W2963370694","https://openalex.org/W2963528589","https://openalex.org/W2972389417","https://openalex.org/W3000086239","https://openalex.org/W3011234510","https://openalex.org/W3015371109","https://openalex.org/W3015383493","https://openalex.org/W3036601975","https://openalex.org/W3097139988","https://openalex.org/W3097882114","https://openalex.org/W3103005696","https://openalex.org/W3106423890","https://openalex.org/W3115365386","https://openalex.org/W3155419065","https://openalex.org/W3199490845","https://openalex.org/W4295312788","https://openalex.org/W6631362777","https://openalex.org/W6656689313","https://openalex.org/W6739901393","https://openalex.org/W6754392867","https://openalex.org/W6766978945","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1],"recognition":[2,10],"(AVSR)":[3],"can":[4],"significantly":[5],"improve":[6,75],"performance":[7,39,109],"over":[8,110],"audio-only":[9,149,171],"for":[11,47,114,140],"small":[12],"or":[13,21],"medium":[14],"vocabularies.":[15],"However,":[16],"current":[17],"AVSR,":[18],"whether":[19],"hybrid":[20,83,118,148],"end-to-end":[22],"(E2E),":[23],"still":[24,41],"does":[25],"not":[26],"appear":[27],"to":[28,74,134,146],"make":[29],"optimal":[30],"use":[31],"of":[32,64,159,181,187],"this":[33],"secondary":[34],"information":[35],"stream":[36],"as":[37,70],"the":[38,93,121,136,147,151,164,185],"is":[40,79,132],"clearly":[42],"diminished":[43],"in":[44,81,108],"noisy":[45],"conditions":[46],"large-vocabulary":[48,91,115],"systems.":[49],"We,":[50],"therefore,":[51],"propose":[52],"a":[53,155,175],"new":[54],"fusion":[55,58,190],"architecture\u2014the":[56],"decision":[57],"net":[59],"(DFN).":[60],"A":[61],"broad":[62],"range":[63],"time-variant":[65],"reliability":[66],"measures":[67],"are":[68],"used":[69,80],"an":[71],"auxiliary":[72],"input":[73],"performance.":[76],"The":[77,117],"DFN":[78,123,153],"both":[82,183],"and":[84,98,101],"E2E":[85],"models.":[86],"Our":[87],"experiments":[88],"on":[89,161],"two":[90],"datasets,":[92],"Lip":[94],"Reading":[95],"Sentences":[96],"2":[97],"3":[99],"(LRS2":[100],"LRS3)":[102],"corpora,":[103],"show":[104],"highly":[105],"significant":[106],"improvements":[107],"previous":[111],"AVSR":[112],"systems":[113],"datasets.":[116],"model":[119],"with":[120,167],"proposed":[122,152,189],"integration":[124],"component":[125],"even":[126],"outperforms":[127],"oracle":[128],"dynamic":[129,142],"stream-weighting,":[130],"which":[131],"considered":[133],"be":[135],"theoretical":[137],"upper":[138],"bound":[139],"conventional":[141],"stream-weighting":[143],"approaches.":[144],"Compared":[145],"model,":[150,166],"achieves":[154,174],"relative":[156,176],"word-error-rate":[157],"reduction":[158,180],"51%":[160],"average,":[162],"while":[163],"E2E-DFN":[165],"its":[168],"more":[169],"competitive":[170],"baseline":[172],"system,":[173],"word":[177],"error":[178],"rate":[179],"43%,":[182],"showing":[184],"efficacy":[186],"our":[188],"architecture.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
