{"id":"https://openalex.org/W4200484186","doi":"https://doi.org/10.3390/s22010072","title":"Lipreading Architecture Based on Multiple Convolutional Neural Networks for Sentence-Level Visual Speech Recognition","display_name":"Lipreading Architecture Based on Multiple Convolutional Neural Networks for Sentence-Level Visual Speech Recognition","publication_year":2021,"publication_date":"2021-12-23","ids":{"openalex":"https://openalex.org/W4200484186","doi":"https://doi.org/10.3390/s22010072","pmid":"https://pubmed.ncbi.nlm.nih.gov/35009612"},"language":"en","primary_location":{"id":"doi:10.3390/s22010072","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22010072","pdf_url":"https://www.mdpi.com/1424-8220/22/1/72/pdf?version=1640255368","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/22/1/72/pdf?version=1640255368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009004504","display_name":"Sanghun Jeon","orcid":"https://orcid.org/0000-0003-4705-1254"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghun Jeon","raw_affiliation_strings":["Center for Healthcare Robotics, Gwangju Institute of Science and Technology (GIST), School of Integrated Technology, Gwangju 61005, Korea"],"raw_orcid":"https://orcid.org/0000-0003-4705-1254","affiliations":[{"raw_affiliation_string":"Center for Healthcare Robotics, Gwangju Institute of Science and Technology (GIST), School of Integrated Technology, Gwangju 61005, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060340490","display_name":"Ahmed Elsharkawy","orcid":"https://orcid.org/0000-0002-1522-5064"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ahmed Elsharkawy","raw_affiliation_strings":["Center for Healthcare Robotics, Gwangju Institute of Science and Technology (GIST), School of Integrated Technology, Gwangju 61005, Korea"],"raw_orcid":"https://orcid.org/0000-0002-1522-5064","affiliations":[{"raw_affiliation_string":"Center for Healthcare Robotics, Gwangju Institute of Science and Technology (GIST), School of Integrated Technology, Gwangju 61005, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084294297","display_name":"Mun Sang Kim","orcid":"https://orcid.org/0000-0002-6050-6594"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Mun Sang Kim","raw_affiliation_strings":["Center for Healthcare Robotics, Gwangju Institute of Science and Technology (GIST), School of Integrated Technology, Gwangju 61005, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Healthcare Robotics, Gwangju Institute of Science and Technology (GIST), School of Integrated Technology, Gwangju 61005, Korea","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084294297"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":4.1678,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95097448,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"22","issue":"1","first_page":"72","last_page":"72"},"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":0.9983000159263611,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.7856764197349548},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7081100940704346},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6177265644073486},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6013306379318237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.587439775466919},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5482292175292969},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4981815814971924},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4863205850124359},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.4547911286354065},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4520922601222992},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.439848393201828},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3571411073207855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856764197349548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7081100940704346},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6177265644073486},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6013306379318237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.587439775466919},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5482292175292969},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4981815814971924},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4863205850124359},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.4547911286354065},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4520922601222992},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.439848393201828},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3571411073207855},{"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":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s22010072","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22010072","pdf_url":"https://www.mdpi.com/1424-8220/22/1/72/pdf?version=1640255368","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:35009612","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35009612","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:38ab2edde2f042de83dbb983691731b5","is_oa":true,"landing_page_url":"https://doaj.org/article/38ab2edde2f042de83dbb983691731b5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 22, Iss 1, p 72 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/1/72/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22010072","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Sensors; Volume 22; Issue 1; Pages: 72","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8747278","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8747278","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Sensors (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s22010072","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22010072","pdf_url":"https://www.mdpi.com/1424-8220/22/1/72/pdf?version=1640255368","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G1865052789","display_name":null,"funder_award_id":"NRF-2018X1A3A1069795","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200484186.pdf","grobid_xml":"https://content.openalex.org/works/W4200484186.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W124434589","https://openalex.org/W1936750108","https://openalex.org/W1983364832","https://openalex.org/W2000399372","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2058961190","https://openalex.org/W2060510034","https://openalex.org/W2071096833","https://openalex.org/W2106284211","https://openalex.org/W2112796928","https://openalex.org/W2115252128","https://openalex.org/W2127141656","https://openalex.org/W2130112859","https://openalex.org/W2194775991","https://openalex.org/W2267805933","https://openalex.org/W2404704342","https://openalex.org/W2493477844","https://openalex.org/W2551572271","https://openalex.org/W2556171197","https://openalex.org/W2793493229","https://openalex.org/W2886945201","https://openalex.org/W2963030892","https://openalex.org/W2963032190","https://openalex.org/W2963173190","https://openalex.org/W2963446712","https://openalex.org/W2972852451","https://openalex.org/W2999889591","https://openalex.org/W3001079424","https://openalex.org/W3080253586","https://openalex.org/W3086926995","https://openalex.org/W3091048148","https://openalex.org/W3091641623","https://openalex.org/W3093337631","https://openalex.org/W3099231112","https://openalex.org/W3103801904","https://openalex.org/W3108999607","https://openalex.org/W3109715615","https://openalex.org/W3128750130","https://openalex.org/W3159027270","https://openalex.org/W3165010056","https://openalex.org/W3187541079","https://openalex.org/W6677618333"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W3005627584","https://openalex.org/W2899027234"],"abstract_inverted_index":{"In":[0],"visual":[1,10,72,189],"speech":[2,5,152],"recognition":[3,153],"(VSR),":[4],"is":[6,48,70],"transcribed":[7],"using":[8,42,142],"only":[9],"information":[11,73],"to":[12,60],"interpret":[13],"tongue":[14],"and":[15,87,120,164,174],"teeth":[16],"movements.":[17],"Recently,":[18],"deep":[19],"learning":[20,80],"has":[21],"shown":[22],"outstanding":[23],"performance":[24,186],"in":[25],"VSR,":[26],"with":[27,53],"accuracy":[28],"exceeding":[29],"that":[30,71,104,157],"of":[31,51,66,148,168],"lipreaders":[32],"on":[33],"benchmark":[34],"datasets.":[35],"However,":[36],"several":[37],"problems":[38],"still":[39],"exist":[40],"when":[41,188],"VSR":[43,68,194],"systems.":[44],"A":[45],"major":[46],"challenge":[47],"the":[49,149,158,162,169,178],"distinction":[50],"words":[52,81],"similar":[54],"pronunciation,":[55],"called":[56],"homophones;":[57],"these":[58],"lead":[59],"word":[61,165],"ambiguity.":[62],"Another":[63],"technical":[64],"limitation":[65],"traditional":[67],"systems":[69],"does":[74],"not":[75],"provide":[76],"sufficient":[77],"data":[78],"for":[79,177,196],"such":[82],"as":[83],"\"a\",":[84],"\"an\",":[85],"\"eight\",":[86],"\"bin\"":[88],"because":[89],"their":[90],"lengths":[91],"are":[92,128],"shorter":[93],"than":[94],"0.02":[95],"s.":[96],"This":[97],"report":[98],"proposes":[99],"a":[100,112,115,121,131],"novel":[101],"lipreading":[102],"architecture":[103,160,183],"combines":[105],"three":[106],"different":[107],"convolutional":[108],"neural":[109],"networks":[110],"(CNNs;":[111],"3D":[113,118,125],"CNN,":[114,119],"densely":[116],"connected":[117],"multi-layer":[122],"feature":[123],"fusion":[124],"CNN),":[126],"which":[127],"followed":[129],"by":[130,172],"two-layer":[132],"bi-directional":[133],"gated":[134],"recurrent":[135],"unit.":[136],"The":[137,146],"entire":[138],"network":[139],"was":[140],"trained":[141],"connectionist":[143],"temporal":[144],"classification.":[145],"results":[147],"standard":[150],"automatic":[151],"evaluation":[154],"metrics":[155],"show":[156],"proposed":[159,182],"reduced":[161],"character":[163],"error":[166],"rates":[167],"baseline":[170],"model":[171],"5.681%":[173],"11.282%,":[175],"respectively,":[176],"unseen-speaker":[179],"dataset.":[180],"Our":[181],"exhibits":[184],"improved":[185],"even":[187],"ambiguity":[190],"arises,":[191],"thereby":[192],"increasing":[193],"reliability":[195],"practical":[197],"applications.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}