{"id":"https://openalex.org/W2883383043","doi":"https://doi.org/10.21437/interspeech.2019-1669","title":"Large-Scale Visual Speech Recognition","display_name":"Large-Scale Visual Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2883383043","doi":"https://doi.org/10.21437/interspeech.2019-1669","mag":"2883383043"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1669","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1807.05162","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012498862","display_name":"Brendan Shillingford","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Brendan Shillingford","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043118390","display_name":"Yannis Assael","orcid":"https://orcid.org/0000-0001-7408-3847"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Assael","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110357506","display_name":"Matthew W. Hoffman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew W. Hoffman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032856983","display_name":"Thomas Paine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Paine","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022377551","display_name":"C\u00edan Hughes","orcid":"https://orcid.org/0000-0001-6901-0985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C\u00edan Hughes","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110145189","display_name":"Utsav Prabhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Utsav Prabhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110698977","display_name":"Hank Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hank Liao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108537573","display_name":"Ha\u015fim Sak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hasim Sak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111514705","display_name":"Kanishka Rao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kanishka Rao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000212710","display_name":"Lorrayne Bennett","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lorrayne Bennett","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044746626","display_name":"Marie Mulville","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marie Mulville","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Misha Denil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Misha Denil","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089424256","display_name":"Ben Coppin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Coppin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069096861","display_name":"Ben Laurie","orcid":"https://orcid.org/0000-0002-3490-3473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Laurie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105472688","display_name":"Andrew Senior","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Senior","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082304130","display_name":"Nando de Freitas","orcid":"https://orcid.org/0000-0003-4770-7217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nando de Freitas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5012498862"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0325,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.9697358,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4135","last_page":"4139"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8147337436676025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7624838352203369},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6743921041488647},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5242103338241577},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5032145380973816},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5000805854797363},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.471641480922699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43928900361061096},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43138137459754944},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4249621331691742},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13796931505203247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8147337436676025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7624838352203369},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6743921041488647},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5242103338241577},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5032145380973816},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5000805854797363},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.471641480922699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43928900361061096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43138137459754944},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4249621331691742},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13796931505203247},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1669","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1807.05162","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.05162","pdf_url":"https://arxiv.org/pdf/1807.05162","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":"","raw_type":"text"},{"id":"mag:2883383043","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1807.05162","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1807.05162","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1807.05162","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1807.05162","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.05162","pdf_url":"https://arxiv.org/pdf/1807.05162","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2883383043.pdf","grobid_xml":"https://content.openalex.org/works/W2883383043.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W98035269","https://openalex.org/W124434589","https://openalex.org/W142803501","https://openalex.org/W1211870555","https://openalex.org/W1503762774","https://openalex.org/W1522301498","https://openalex.org/W1571194703","https://openalex.org/W1736701665","https://openalex.org/W1988074515","https://openalex.org/W2015143272","https://openalex.org/W2033256038","https://openalex.org/W2040454151","https://openalex.org/W2053972292","https://openalex.org/W2060510034","https://openalex.org/W2064675550","https://openalex.org/W2099601760","https://openalex.org/W2102863932","https://openalex.org/W2106284211","https://openalex.org/W2113814270","https://openalex.org/W2118258383","https://openalex.org/W2121015323","https://openalex.org/W2123045220","https://openalex.org/W2124397839","https://openalex.org/W2127141656","https://openalex.org/W2130112859","https://openalex.org/W2136155248","https://openalex.org/W2142075667","https://openalex.org/W2160815625","https://openalex.org/W2171209807","https://openalex.org/W2184188583","https://openalex.org/W2193413348","https://openalex.org/W2208724044","https://openalex.org/W2243738093","https://openalex.org/W2295983515","https://openalex.org/W2365880764","https://openalex.org/W2398406965","https://openalex.org/W2404704342","https://openalex.org/W2406846463","https://openalex.org/W2507287275","https://openalex.org/W2509591453","https://openalex.org/W2516412152","https://openalex.org/W2545177271","https://openalex.org/W2556171197","https://openalex.org/W2578229578","https://openalex.org/W2594690981","https://openalex.org/W2596627958","https://openalex.org/W2604379605","https://openalex.org/W2612434330","https://openalex.org/W2625027024","https://openalex.org/W2734984521","https://openalex.org/W2742601054","https://openalex.org/W2744890653","https://openalex.org/W2750499125","https://openalex.org/W2766960583","https://openalex.org/W2790322981","https://openalex.org/W2797090057","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2891226622","https://openalex.org/W2949229618","https://openalex.org/W2950479517","https://openalex.org/W2951015274","https://openalex.org/W2951700231","https://openalex.org/W2952746495","https://openalex.org/W2962835968","https://openalex.org/W2962912639","https://openalex.org/W2963414781","https://openalex.org/W3031391047","https://openalex.org/W3099202502","https://openalex.org/W3099206234"],"related_works":["https://openalex.org/W2952746495","https://openalex.org/W2594690981","https://openalex.org/W2578229578","https://openalex.org/W2963528589","https://openalex.org/W2890952074","https://openalex.org/W2127141656","https://openalex.org/W2015143272","https://openalex.org/W2891205112","https://openalex.org/W2964121744","https://openalex.org/W2963785710","https://openalex.org/W2963654155","https://openalex.org/W2194775991","https://openalex.org/W2550980560","https://openalex.org/W2963403868","https://openalex.org/W2963030892","https://openalex.org/W2886945201","https://openalex.org/W2604379605","https://openalex.org/W2029199293","https://openalex.org/W2113814270","https://openalex.org/W1531976713"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,50,67,83,96,106],"scalable":[4,68],"solution":[5],"to":[6,58,77,126],"open-vocabulary":[7],"visual":[8,19],"speech":[9,20,85],"recognition.":[10],"To":[11],"achieve":[12,113],"this,":[13],"we":[14,40],"constructed":[15],"the":[16,74,120],"largest":[17],"existing":[18],"recognition":[21],"dataset,":[22],"consisting":[23,48],"of":[24,26,31,36,49,61,65,79,90,101,129,142,145,155],"pairs":[25],"text":[27],"and":[28,42,63,82,144,148,157],"video":[29,51,57],"clips":[30],"faces":[32],"speaking":[33],"(3,886":[34],"hours":[35],"video).":[37],"In":[38,109],"tandem,":[39],"designed":[41],"trained":[43],"an":[44],"integrated":[45],"lipreading":[46,138],"system,":[47],"processing":[52],"pipeline":[53],"that":[54,72,87],"maps":[55,73],"raw":[56],"stable":[59],"videos":[60,76],"lips":[62],"sequences":[64,78,89],"phonemes,":[66],"deep":[69],"neural":[70],"network":[71],"lip":[75],"phoneme":[80],"distributions,":[81],"production-level":[84],"decoder":[86],"outputs":[88],"words.":[91],"The":[92],"proposed":[93],"system":[94],"achieves":[95],"word":[97],"error":[98],"rate":[99],"(WER)":[100],"40.9%":[102],"as":[103],"measured":[104],"on":[105,119,136],"held-out":[107],"set.":[108],"comparison,":[110],"professional":[111],"lipreaders":[112],"either":[114],"86.4%":[115],"or":[116],"92.9%":[117],"WER":[118,159],"same":[121],"dataset":[122],"when":[123],"having":[124],"access":[125],"additional":[127],"types":[128],"contextual":[130],"information.":[131],"Our":[132],"approach":[133],"significantly":[134],"improves":[135],"other":[137],"approaches,":[139],"including":[140],"variants":[141],"LipNet":[143],"Watch,":[146],"Attend,":[147],"Spell":[149],"(WAS),":[150],"which":[151],"are":[152],"only":[153],"capable":[154],"89.8%":[156],"76.8%":[158],"respectively.":[160]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}