{"id":"https://openalex.org/W2790326622","doi":"https://doi.org/10.1109/taslp.2018.2815268","title":"Gating Neural Network for Large Vocabulary Audiovisual Speech Recognition","display_name":"Gating Neural Network for Large Vocabulary Audiovisual Speech Recognition","publication_year":2018,"publication_date":"2018-03-12","ids":{"openalex":"https://openalex.org/W2790326622","doi":"https://doi.org/10.1109/taslp.2018.2815268","mag":"2790326622"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2815268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2815268","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101452102","display_name":"Fei Tao","orcid":"https://orcid.org/0000-0003-4834-8949"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Tao","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, US"],"raw_orcid":"https://orcid.org/0000-0003-4834-8949","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, US","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, US"],"raw_orcid":"https://orcid.org/0000-0002-4075-4072","affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, US","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":5.8658,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.96796128,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":"7","first_page":"1290","last_page":"1302"},"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":0.9994999766349792,"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":0.9969000220298767,"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":0.7947554588317871},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7547519207000732},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.726861834526062},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5506432056427002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4719716012477875},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4671245217323303},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4553719758987427},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44096195697784424},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.4102587103843689},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36496850848197937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947554588317871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7547519207000732},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.726861834526062},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5506432056427002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4719716012477875},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4671245217323303},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4553719758987427},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44096195697784424},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.4102587103843689},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36496850848197937},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2815268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2815268","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W135040384","https://openalex.org/W652928785","https://openalex.org/W1026270304","https://openalex.org/W1489488446","https://openalex.org/W1498436455","https://openalex.org/W1503933356","https://openalex.org/W1518556865","https://openalex.org/W1524333225","https://openalex.org/W1526392145","https://openalex.org/W1533861849","https://openalex.org/W1576996184","https://openalex.org/W1661756259","https://openalex.org/W1988306926","https://openalex.org/W1993882792","https://openalex.org/W2015143272","https://openalex.org/W2020586124","https://openalex.org/W2020596545","https://openalex.org/W2022799064","https://openalex.org/W2029199293","https://openalex.org/W2035777533","https://openalex.org/W2046599127","https://openalex.org/W2064675550","https://openalex.org/W2076462394","https://openalex.org/W2095705004","https://openalex.org/W2096391593","https://openalex.org/W2098923380","https://openalex.org/W2108492645","https://openalex.org/W2112796928","https://openalex.org/W2113786253","https://openalex.org/W2122817389","https://openalex.org/W2125328520","https://openalex.org/W2125336414","https://openalex.org/W2125838338","https://openalex.org/W2136922672","https://openalex.org/W2146502635","https://openalex.org/W2147768505","https://openalex.org/W2157285372","https://openalex.org/W2160815625","https://openalex.org/W2184188583","https://openalex.org/W2289925289","https://openalex.org/W2294059674","https://openalex.org/W2397098974","https://openalex.org/W2404704342","https://openalex.org/W2405180117","https://openalex.org/W2406846463","https://openalex.org/W2509591453","https://openalex.org/W2512215050","https://openalex.org/W2551572271","https://openalex.org/W2556171197","https://openalex.org/W2579335913","https://openalex.org/W2604132379","https://openalex.org/W2604379605","https://openalex.org/W2696731410","https://openalex.org/W2749694333","https://openalex.org/W2793908218","https://openalex.org/W2950621961","https://openalex.org/W2952746495","https://openalex.org/W2962826786","https://openalex.org/W2963192365","https://openalex.org/W2963266252","https://openalex.org/W2963528589","https://openalex.org/W3099202502","https://openalex.org/W3143803406","https://openalex.org/W4235765578","https://openalex.org/W6603616073","https://openalex.org/W6621596204","https://openalex.org/W6629320091","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6636969168","https://openalex.org/W6675190910","https://openalex.org/W6678412311","https://openalex.org/W6678809451","https://openalex.org/W6681435938","https://openalex.org/W6686207219","https://openalex.org/W6696761078","https://openalex.org/W6712664211","https://openalex.org/W6713551954","https://openalex.org/W6713900829","https://openalex.org/W6725548009","https://openalex.org/W6725623580","https://openalex.org/W6729699919","https://openalex.org/W6732514500","https://openalex.org/W6734790163","https://openalex.org/W6735927292","https://openalex.org/W6743327199","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W2031449089","https://openalex.org/W2112596406","https://openalex.org/W2125499229","https://openalex.org/W2053269318","https://openalex.org/W4385304246","https://openalex.org/W4379116102","https://openalex.org/W3210882018","https://openalex.org/W2970990331","https://openalex.org/W3207178610","https://openalex.org/W3211782752"],"abstract_inverted_index":{"Audio-based":[0],"automatic":[1,48],"speech":[2,49,58,175],"recognition":[3,50],"(A-ASR)":[4],"systems":[5],"are":[6,129],"affected":[7],"by":[8],"noisy":[9,148],"conditions":[10],"in":[11,55,84],"real-world":[12],"applications.":[13],"Adding":[14],"visual":[15,64,127,151],"cues":[16],"to":[17,25],"the":[18,27,30,33,53,76,79,124,145,165,209,221,231,234],"ASR":[19],"system":[20,98,210],"is":[21,52,59,134,159,189],"an":[22,94],"appealing":[23],"alternative":[24,225],"improve":[26],"robustness":[28,232],"of":[29,78,147,164,171,174,233],"system,":[31],"replicating":[32],"audiovisual":[34,47,95,166],"perception":[35],"process":[36],"used":[37],"during":[38],"human":[39],"interactions.":[40],"A":[41],"common":[42],"problem":[43,90],"observed":[44],"when":[45,57,91,126],"using":[46],"(AV-ASR)":[51],"drop":[54],"performance":[56,77,125],"clean.":[60],"In":[61],"this":[62,85,89,117],"case,":[63],"features":[65,128],"may":[66],"not":[67],"provide":[68],"complementary":[69],"information,":[70],"introducing":[71],"variability":[72],"that":[73,115,143,220],"negatively":[74],"affects":[75],"system.":[80,215],"The":[81,131,157,186,216],"experimental":[82,217],"evaluation":[83,218],"study":[86,111],"clearly":[87],"demonstrates":[88],"we":[92],"train":[93],"state-of-the-art":[96],"hybrid":[97],"with":[99,139,161,181,191,194,198,211],"a":[100,113,135,140,162,200,212],"deep":[101,136],"neural":[102],"network":[103],"(DNN)":[104],"and":[105,184],"hidden":[106],"Markov":[107],"models":[108,196],"(HMMs).":[109],"This":[110],"proposes":[112],"framework":[114,158,188,223,236],"addresses":[116],"problem,":[118],"improving,":[119],"or":[120,149,204],"at":[121],"least,":[122],"maintaining":[123],"used.":[130],"proposed":[132,187,222],"approach":[133],"learning":[137],"solution":[138],"gating":[141],"layer":[142],"diminishes":[144],"effect":[146],"uninformative":[150],"features,":[152],"keeping":[153],"only":[154],"useful":[155],"information.":[156],"implemented":[160,197],"subset":[163],"CRSS-4ENGLISH-14":[167],"corpus":[168],"which":[169],"consists":[170],"61":[172],"h":[173],"from":[176],"105":[177],"subjects":[178],"simultaneously":[179],"collected":[180],"multiple":[182],"cameras":[183],"microphones.":[185],"compared":[190],"conventional":[192],"HMMs":[193],"observation":[195],"either":[199],"Gaussian":[201],"mixture":[202],"model":[203],"DNNs.":[205],"We":[206],"also":[207],"compare":[208],"multi-stream":[213],"HMM":[214],"indicates":[219],"outperforms":[224],"methods":[226],"under":[227],"all":[228],"configurations,":[229],"showing":[230],"gating-based":[235],"for":[237],"AV-ASR.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}