{"id":"https://openalex.org/W2124174353","doi":"https://doi.org/10.1109/icassp.1996.543247","title":"Integrating audio and visual information to provide highly robust speech recognition","display_name":"Integrating audio and visual information to provide highly robust speech recognition","publication_year":2002,"publication_date":"2002-12-23","ids":{"openalex":"https://openalex.org/W2124174353","doi":"https://doi.org/10.1109/icassp.1996.543247","mag":"2124174353"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1996.543247","doi":"https://doi.org/10.1109/icassp.1996.543247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1996.543247","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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":null,"display_name":"M.J. Tomlinson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M.J. Tomlinson","raw_affiliation_strings":["DRA Malvern, Worcs., Speech Research Unit, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DRA Malvern, Worcs., Speech Research Unit, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079477816","display_name":"Martin J. Russell","orcid":"https://orcid.org/0000-0002-8324-4961","observed_orcids":["https://orcid.org/0000-0002-8324-4961"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M.J. Russell","raw_affiliation_strings":["DRA Malvern, Worcs., Speech Research Unit, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DRA Malvern, Worcs., Speech Research Unit, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113323230","display_name":"N. Michael Brooke","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"N.M. Brooke","raw_affiliation_strings":["School of Mathematical Sciences, University of Bath, Bath, Avon, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, University of Bath, Bath, Avon, UK","institution_ids":["https://openalex.org/I51601045"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.8025,"has_fulltext":false,"cited_by_count":108,"citation_normalized_percentile":{"value":0.99085342,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":"2","issue":null,"first_page":"821","last_page":"824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6157000064849854,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6157000064849854,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.3806000053882599,"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/T12031","display_name":"Speech and dialogue systems","score":0.0008999999845400453,"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/speech-recognition","display_name":"speech recognition","score":0.7379999756813049},{"id":"https://openalex.org/keywords/lip-reading","display_name":"lip reading","score":0.7129999995231628},{"id":"https://openalex.org/keywords/audiovisual-integration","display_name":"audiovisual integration","score":0.8169999718666077},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.4880000054836273},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.9269999861717224},{"id":"https://openalex.org/keywords/speaker-dependent-speech-recognition","display_name":"speaker-dependent recognition","score":0.7900000214576721},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.7739999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827168107032776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6816914081573486},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5908340811729431},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4274910092353821},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3820473253726959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3634723424911499},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25341203808784485}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1996.543247","doi":"https://doi.org/10.1109/icassp.1996.543247","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1996.543247","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W1499738427","https://openalex.org/W1535702289","https://openalex.org/W1611485867","https://openalex.org/W1800365115","https://openalex.org/W1934584000","https://openalex.org/W1988089926","https://openalex.org/W2133575725","https://openalex.org/W4246961297"],"related_works":["https://openalex.org/W2341627864","https://openalex.org/W7056515674","https://openalex.org/W2157190406","https://openalex.org/W2121486117","https://openalex.org/W111284038","https://openalex.org/W2098419325","https://openalex.org/W2366864536","https://openalex.org/W1566941554","https://openalex.org/W7207909570","https://openalex.org/W1514860245"],"abstract_inverted_index":{"There":[0],"is":[1,123],"a":[2,42,64,84,90,131],"requirement":[3],"in":[4,15,31,56],"many":[5],"human":[6],"machine":[7],"interactions":[8],"to":[9,83,95,125],"provide":[10],"accurate":[11],"automatic":[12],"speech":[13],"recognition":[14,32,87,99],"the":[16,25,48,51,57,74],"presence":[17],"of":[18,21,50,59,120,135],"high":[19],"levels":[20],"interfering":[22,96],"noise.":[23,97],"The":[24,98,118],"paper":[26],"shows":[27],"that":[28],"performance":[29,129],"improvements":[30],"accuracy":[33],"can":[34],"be":[35,126],"obtained":[36,101],"by":[37],"including":[38],"data":[39,55],"derived":[40],"from":[41],"speaker's":[43],"lip":[44],"images.":[45],"We":[46],"describe":[47],"combination":[49],"audio":[52,75],"and":[53,63,76,93,105],"visual":[54,77],"construction":[58],"composite":[60,103],"feature":[61,116],"vectors":[62,104],"hidden":[65],"Markov":[66],"model":[67],"structure":[68],"which":[69],"allows":[70],"for":[71],"asynchrony":[72],"between":[73],"components.":[78],"These":[79],"ideas":[80],"are":[81,108],"applied":[82],"speaker":[85],"dependent":[86],"task":[88],"involving":[89],"small":[91],"vocabulary":[92],"subject":[94],"results":[100],"using":[102],"cross-product":[106],"models":[107],"compared":[109],"with":[110],"those":[111],"based":[112],"on":[113],"an":[114,127],"audio-only":[115],"vector.":[117],"benefit":[119],"this":[121],"approach":[122],"shown":[124],"increased":[128],"over":[130],"very":[132],"wide":[133],"range":[134],"noise":[136],"levels.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":10}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}