{"id":"https://openalex.org/W2787944098","doi":"https://doi.org/10.1109/icassp.2018.8461326","title":"End-to-End Audiovisual Speech Recognition","display_name":"End-to-End Audiovisual Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2787944098","doi":"https://doi.org/10.1109/icassp.2018.8461326","mag":"2787944098"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/1802.06424","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Dept. of Computing, Imperial College London, UK","Department of Computing Imperial College London UK"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing Imperial College London UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Computer Vision Laboratory, University of Nottingham, UK"],"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, University of Nottingham, UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pingehuan Ma","raw_affiliation_strings":["Dept. of Computing, Imperial College London, UK","Department of Computing Imperial College London UK"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing Imperial College London UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031069397","display_name":"Feipeng Cai","orcid":"https://orcid.org/0000-0002-1186-1848"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Feipeng Cai","raw_affiliation_strings":["Dept. of Computing, Imperial College London, UK","Department of Computing Imperial College London UK"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing Imperial College London UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024224610","display_name":"Georgios Tzimiropoulos","orcid":"https://orcid.org/0000-0002-1803-5338"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Tzimiropoulos","raw_affiliation_strings":["Computer Vision Laboratory, University of Nottingham, UK"],"affiliations":[{"raw_affiliation_string":"Computer Vision Laboratory, University of Nottingham, UK","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Dept. of Computing, Imperial College London, UK","Department of Computing Imperial College London UK"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing Imperial College London UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009475700"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":1.80609479,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84441498,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6548","last_page":"6552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9975000023841858,"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":0.9818999767303467,"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":0.8258273005485535},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7355104684829712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6977102756500244},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5600103735923767},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5084421038627625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4864828288555145},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48344001173973083},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.43890050053596497},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.35082051157951355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33541420102119446},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.18425408005714417},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17141523957252502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258273005485535},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7355104684829712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6977102756500244},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5600103735923767},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5084421038627625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4864828288555145},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48344001173973083},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.43890050053596497},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.35082051157951355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33541420102119446},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.18425408005714417},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17141523957252502},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp.2018.8461326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.nottingham.ac.uk:51132","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402013","display_name":"Nottingham ePrints (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:arXiv.org:1802.06424","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06424","pdf_url":"https://arxiv.org/pdf/1802.06424","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:2787944098","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1802.06424v2","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":"pmh:oai:nottingham-repository.worktribe.com:925044","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/925044","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"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":null,"raw_type":"acceptedVersion"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/73205","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/73205","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.1802.06424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.06424","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:1802.06424","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.06424","pdf_url":"https://arxiv.org/pdf/1802.06424","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1503933356","https://openalex.org/W1974387177","https://openalex.org/W2015143272","https://openalex.org/W2096391593","https://openalex.org/W2121486117","https://openalex.org/W2194775991","https://openalex.org/W2261706002","https://openalex.org/W2267805933","https://openalex.org/W2399733683","https://openalex.org/W2404704342","https://openalex.org/W2474638510","https://openalex.org/W2516412152","https://openalex.org/W2963192365","https://openalex.org/W2963295405","https://openalex.org/W6631564540","https://openalex.org/W6681898093","https://openalex.org/W6686207219","https://openalex.org/W6698183232","https://openalex.org/W6713551954","https://openalex.org/W6734491695","https://openalex.org/W6734790163","https://openalex.org/W6737474859","https://openalex.org/W6765296696"],"related_works":["https://openalex.org/W2754826374","https://openalex.org/W2594690981","https://openalex.org/W3130492967","https://openalex.org/W2793122029","https://openalex.org/W2963192365","https://openalex.org/W1869491686","https://openalex.org/W3121029767","https://openalex.org/W2952746495","https://openalex.org/W2076462394","https://openalex.org/W2063425879","https://openalex.org/W2182448868","https://openalex.org/W2897067191","https://openalex.org/W2980600748","https://openalex.org/W2039679570","https://openalex.org/W2959214850","https://openalex.org/W3129434801","https://openalex.org/W2788241093","https://openalex.org/W2572763611","https://openalex.org/W3009620048","https://openalex.org/W1833616679"],"abstract_inverted_index":{"Several":[0],"end-to-end":[1,30,42,147,171],"deep":[2],"learning":[3],"approaches":[4],"have":[5],"been":[6],"recently":[7],"presented":[8],"which":[9,68,104],"extract":[10,72,105],"either":[11],"audio":[12,21,80,156],"or":[13,20],"visual":[14],"features":[15,73,106],"from":[16,75,108],"the":[17,56,63,76,127,142,170],"input":[18],"images":[19],"signals":[22],"and":[23,49,79,82,111,126,149,158],"perform":[24],"speech":[25],"recognition.":[26],"However,":[27],"research":[28],"on":[29,46,87],"audiovisual":[31,43,65,172],"models":[32],"is":[33,62,152],"very":[34],"limited.":[35],"In":[36,163],"this":[37,61],"work,":[38],"we":[39],"present":[40],"an":[41,146],"model":[44,67,95,151,173],"based":[45],"residual":[47],"networks":[48],"Bidirectional":[50],"Gated":[51],"Recurrent":[52],"Units":[53],"(BGRUs).":[54],"To":[55],"best":[57],"of":[58,97,129,161,165,168],"our":[59],"knowledge,":[60],"first":[64],"fusion":[66,128],"simultaneously":[69],"learns":[70],"to":[71],"directly":[74,107],"image":[77],"pixels":[78],"waveforms":[81],"performs":[83],"within-context":[84],"word":[85],"recognition":[86],"a":[88,123],"large":[89],"publicly":[90],"available":[91],"dataset":[92],"(LRW).":[93],"The":[94,114],"consists":[96],"two":[98],"streams,":[99],"one":[100],"for":[101],"each":[102,118],"modality,":[103],"mouth":[109],"regions":[110],"raw":[112],"waveforms.":[113],"temporal":[115],"dynamics":[116],"in":[117,141,154],"stream/modality":[119],"are":[120],"modeled":[121],"by":[122],"2-layer":[124,136],"BGRU":[125],"multiple":[130],"streams/modalities":[131],"takes":[132],"place":[133],"via":[134],"another":[135],"BGRU.":[137],"A":[138],"slight":[139],"improvement":[140],"classification":[143],"rate":[144],"over":[145],"audio-only":[148,177],"MFCC-based":[150],"reported":[153],"clean":[155],"conditions":[157],"low":[159],"levels":[160,167],"noise.":[162],"presence":[164],"high":[166],"noise,":[169],"significantly":[174],"outperforms":[175],"both":[176],"models.":[178]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}
