{"id":"https://openalex.org/W2890952074","doi":"https://doi.org/10.1109/tpami.2018.2889052","title":"Deep Audio-Visual Speech Recognition","display_name":"Deep Audio-Visual Speech Recognition","publication_year":2018,"publication_date":"2018-12-21","ids":{"openalex":"https://openalex.org/W2890952074","doi":"https://doi.org/10.1109/tpami.2018.2889052","mag":"2890952074","pmid":"https://pubmed.ncbi.nlm.nih.gov/30582526"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2018.2889052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2889052","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.02108","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018690028","display_name":"Triantafyllos Afouras","orcid":"https://orcid.org/0000-0002-3935-9681"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Triantafyllos Afouras","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Senior","raw_affiliation_strings":["Google DeepMind, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003562101","display_name":"Oriol Vinyals","orcid":"https://orcid.org/0000-0001-7848-7283"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oriol Vinyals","raw_affiliation_strings":["Google DeepMind, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-7848-7283","affiliations":[{"raw_affiliation_string":"Google DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom","Google DeepMind, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8945-8573","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Google DeepMind, London, United Kingdom","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018690028"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":41.0645,"has_fulltext":false,"cited_by_count":779,"citation_normalized_percentile":{"value":0.99921743,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"44","issue":"12","first_page":"8717","last_page":"8727"},"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/T11448","display_name":"Face recognition and analysis","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9925000071525574,"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":0.8424882888793945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7537308931350708},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5374342203140259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.495917409658432},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4871060848236084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48091933131217957},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4624692499637604},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.44772863388061523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1451871693134308},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10373014211654663}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424882888793945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7537308931350708},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5374342203140259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.495917409658432},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4871060848236084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48091933131217957},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4624692499637604},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44772863388061523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1451871693134308},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10373014211654663},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","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":"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}],"locations_count":4,"locations":[{"id":"doi:10.1109/tpami.2018.2889052","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2018.2889052","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:30582526","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30582526","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:arXiv.org:1809.02108","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.02108","pdf_url":"https://arxiv.org/pdf/1809.02108","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:430e1ab8-42f6-418d-b2f0-012faaecffaa","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:430e1ab8-42f6-418d-b2f0-012faaecffaa","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements at Oxford","raw_type":"Journal article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.02108","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.02108","pdf_url":"https://arxiv.org/pdf/1809.02108","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G1277543710","display_name":null,"funder_award_id":"EP/M013774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":100,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1503933356","https://openalex.org/W1522301498","https://openalex.org/W1586532344","https://openalex.org/W1686810756","https://openalex.org/W1736374775","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2015143272","https://openalex.org/W2029996593","https://openalex.org/W2060510034","https://openalex.org/W2076029968","https://openalex.org/W2076462394","https://openalex.org/W2097117768","https://openalex.org/W2102113734","https://openalex.org/W2115252128","https://openalex.org/W2117539524","https://openalex.org/W2118877769","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2184045248","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2243738093","https://openalex.org/W2267805933","https://openalex.org/W2271840356","https://openalex.org/W2289925289","https://openalex.org/W2293858598","https://openalex.org/W2342662179","https://openalex.org/W2404704342","https://openalex.org/W2520160253","https://openalex.org/W2525778437","https://openalex.org/W2550980560","https://openalex.org/W2551572271","https://openalex.org/W2556171197","https://openalex.org/W2570575067","https://openalex.org/W2578229578","https://openalex.org/W2593910181","https://openalex.org/W2594690981","https://openalex.org/W2596627958","https://openalex.org/W2604379605","https://openalex.org/W2626778328","https://openalex.org/W2775766866","https://openalex.org/W2787944098","https://openalex.org/W2792764867","https://openalex.org/W2808195542","https://openalex.org/W2883383043","https://openalex.org/W2891205112","https://openalex.org/W2949547965","https://openalex.org/W2949888546","https://openalex.org/W2950635152","https://openalex.org/W2951015274","https://openalex.org/W2952746495","https://openalex.org/W2953022181","https://openalex.org/W2953084276","https://openalex.org/W2962824709","https://openalex.org/W2962835968","https://openalex.org/W2962901777","https://openalex.org/W2963240019","https://openalex.org/W2963403664","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963920996","https://openalex.org/W2964121744","https://openalex.org/W2964283370","https://openalex.org/W2964308564","https://openalex.org/W2972756321","https://openalex.org/W3106250896","https://openalex.org/W3144828656","https://openalex.org/W4297818305","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6635078382","https://openalex.org/W6637373629","https://openalex.org/W6637571906","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6675365184","https://openalex.org/W6677548441","https://openalex.org/W6677618333","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6684191040","https://openalex.org/W6694517276","https://openalex.org/W6727336983","https://openalex.org/W6729540071","https://openalex.org/W6734241735","https://openalex.org/W6734491695","https://openalex.org/W6735927292","https://openalex.org/W6739901393","https://openalex.org/W6747270024","https://openalex.org/W6749825310","https://openalex.org/W6753038255","https://openalex.org/W6754420807","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2017776670","https://openalex.org/W2952760143","https://openalex.org/W2347897961","https://openalex.org/W2979236518","https://openalex.org/W2358318464","https://openalex.org/W2340870721","https://openalex.org/W3091955004"],"abstract_inverted_index":{"The":[0,134],"goal":[1],"of":[2,33,85,126,128,142],"this":[3],"work":[4,145],"is":[5,98,109],"to":[6,93,100],"recognise":[7],"phrases":[8],"and":[9,50,72,114],"sentences":[10,130],"being":[11],"spoken":[12],"by":[13,152],"a":[14,30,69,76,117,147,153],"talking":[15],"face,":[16],"with":[17],"or":[18,35],"without":[19],"the":[20,52,73,86,106,140],"audio.":[21],"Unlike":[22],"previous":[23,144],"works":[24],"that":[25,136],"have":[26],"focussed":[27],"on":[28,83,146],"recognising":[29],"limited":[31],"number":[32],"words":[34],"phrases,":[36],"we":[37,60,91,112,137],"tackle":[38],"lip":[39,65,96,148],"reading":[40,97,149],"as":[41],"an":[42],"open-world":[43],"problem":[44],"-":[45],"unconstrained":[46],"natural":[47,129],"language":[48],"sentences,":[49],"in":[51],"wild":[53],"videos.":[54],"Our":[55],"key":[56],"contributions":[57],"are:":[58],"(1)":[59],"compare":[61],"two":[62],"models":[63,80,135],"for":[64,120],"reading,":[66],"one":[67],"using":[68,75],"CTC":[70],"loss,":[71],"other":[74],"sequence-to-sequence":[77],"loss.":[78],"Both":[79],"are":[81],"built":[82],"top":[84],"transformer":[87],"self-attention":[88],"architecture;":[89],"(2)":[90],"investigate":[92],"what":[94],"extent":[95],"complementary":[99],"audio":[101,107],"speech":[102,122],"recognition,":[103,123],"especially":[104],"when":[105],"signal":[108],"noisy;":[110],"(3)":[111],"introduce":[113],"publicly":[115],"release":[116],"new":[118],"dataset":[119,151],"audio-visual":[121],"LRS2-BBC,":[124],"consisting":[125],"thousands":[127],"from":[131],"British":[132],"television.":[133],"train":[138],"surpass":[139],"performance":[141],"all":[143],"benchmark":[150],"significant":[154],"margin.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":129},{"year":2024,"cited_by_count":153},{"year":2023,"cited_by_count":125},{"year":2022,"cited_by_count":101},{"year":2021,"cited_by_count":114},{"year":2020,"cited_by_count":93},{"year":2019,"cited_by_count":38},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}