{"id":"https://openalex.org/W3006974783","doi":"https://doi.org/10.1109/asru46091.2019.9004036","title":"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition","display_name":"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3006974783","doi":"https://doi.org/10.1109/asru46091.2019.9004036","mag":"3006974783"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004036","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5108496023","display_name":"Takaki Makino","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Takaki Makino","raw_affiliation_strings":["Google Inc., CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110698977","display_name":"Hank Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hank Liao","raw_affiliation_strings":["Google Inc., CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043118390","display_name":"Yannis Assael","orcid":"https://orcid.org/0000-0001-7408-3847"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yannis Assael","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012498862","display_name":"Brendan Shillingford","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Brendan Shillingford","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033485749","display_name":"Basilio Garcia","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Basilio Garcia","raw_affiliation_strings":["Google Inc., CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048852285","display_name":"Otavio Braga","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Otavio Braga","raw_affiliation_strings":["Google Inc., CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":["Google Inc., CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5108496023"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":8.5149,"has_fulltext":false,"cited_by_count":126,"citation_normalized_percentile":{"value":0.98355063,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"905","last_page":"912"},"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":0.9993000030517578,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8477650284767151},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7098771929740906},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6179391741752625},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5641746520996094},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5486368536949158},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5267812013626099},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5017528533935547},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4429132044315338},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4408688545227051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43470993638038635},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3280012011528015},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26843735575675964},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1030091643333435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8477650284767151},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7098771929740906},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6179391741752625},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5641746520996094},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5486368536949158},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5267812013626099},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5017528533935547},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4429132044315338},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4408688545227051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43470993638038635},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3280012011528015},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26843735575675964},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1030091643333435},{"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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9004036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004036","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1525636403","https://openalex.org/W1686810756","https://openalex.org/W1828163288","https://openalex.org/W1974387177","https://openalex.org/W1999940674","https://openalex.org/W2014621385","https://openalex.org/W2033256038","https://openalex.org/W2051091181","https://openalex.org/W2096391593","https://openalex.org/W2096733369","https://openalex.org/W2127141656","https://openalex.org/W2136439176","https://openalex.org/W2148154194","https://openalex.org/W2157331557","https://openalex.org/W2551572271","https://openalex.org/W2570575067","https://openalex.org/W2578229578","https://openalex.org/W2594690981","https://openalex.org/W2714726990","https://openalex.org/W2750499125","https://openalex.org/W2883383043","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2893436174","https://openalex.org/W2935794029","https://openalex.org/W2951152347","https://openalex.org/W2952746495","https://openalex.org/W2962835968","https://openalex.org/W2963403868","https://openalex.org/W2963785710","https://openalex.org/W2964121744","https://openalex.org/W2964171275","https://openalex.org/W2964283370","https://openalex.org/W2972756321","https://openalex.org/W3099206234","https://openalex.org/W3123318516","https://openalex.org/W4231869218","https://openalex.org/W4250482878","https://openalex.org/W4298112588","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631321126","https://openalex.org/W6637373629","https://openalex.org/W6638749077","https://openalex.org/W6650052345","https://openalex.org/W6732872814","https://openalex.org/W6734491695","https://openalex.org/W6739955027","https://openalex.org/W6754392867","https://openalex.org/W6761392404","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W2059520982","https://openalex.org/W2012540220","https://openalex.org/W2129546932","https://openalex.org/W2152158029","https://openalex.org/W2313372908","https://openalex.org/W2079675168","https://openalex.org/W2128790081","https://openalex.org/W2142694085","https://openalex.org/W4323767349","https://openalex.org/W2511749153"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,11,24,28,65],"large-scale":[4],"audio-visual":[5,30,46,56],"speech":[6],"recognition":[7],"system":[8,57,97,117],"based":[9],"on":[10,60,98,122],"recurrent":[12],"neural":[13],"network":[14],"transducer":[15],"(RNN-T)":[16],"architecture.":[17],"To":[18,82,110],"support":[19],"the":[20,77,84,87,93,99,111,120,123],"development":[21],"of":[22,33,45,51,67,86,95,113],"such":[23],"system,":[25],"we":[26,90],"built":[27],"large":[29],"(A/V)":[31],"dataset":[32],"segmented":[34],"utterances":[35],"extracted":[36],"from":[37,70],"YouTube":[38,72],"public":[39,71],"videos,":[40],"leading":[41],"to":[42],"31k":[43],"hours":[44],"training":[47],"content.":[48],"The":[49],"performance":[50,94],"an":[52],"audio-only,":[53],"visual-only,":[54],"and":[55,76,107],"are":[58],"compared":[59],"two":[61],"large-vocabulary":[62],"test":[63],"sets:":[64],"set":[66,101],"utterance":[68],"segments":[69],"videos":[73],"called":[74],"YTDEV18":[75,100],"publicly":[78],"available":[79],"LRS3-TED":[80,124],"set.":[81,125],"highlight":[83],"contribution":[85],"visual":[88],"modality,":[89],"also":[91],"evaluated":[92],"our":[96,114,116],"artificially":[102],"corrupted":[103],"with":[104],"background":[105],"noise":[106],"overlapping":[108],"speech.":[109],"best":[112],"knowledge,":[115],"significantly":[118],"improves":[119],"state-of-the-art":[121]},"counts_by_year":[{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":8}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}