{"id":"https://openalex.org/W4229442847","doi":"https://doi.org/10.3390/s22093597","title":"End-to-End Sentence-Level Multi-View Lipreading Architecture with Spatial Attention Module Integrated Multiple CNNs and Cascaded Local Self-Attention-CTC","display_name":"End-to-End Sentence-Level Multi-View Lipreading Architecture with Spatial Attention Module Integrated Multiple CNNs and Cascaded Local Self-Attention-CTC","publication_year":2022,"publication_date":"2022-05-09","ids":{"openalex":"https://openalex.org/W4229442847","doi":"https://doi.org/10.3390/s22093597","pmid":"https://pubmed.ncbi.nlm.nih.gov/35591284"},"language":"en","primary_location":{"id":"doi:10.3390/s22093597","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22093597","pdf_url":"https://www.mdpi.com/1424-8220/22/9/3597/pdf?version=1652096174","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/1424-8220/22/9/3597/pdf?version=1652096174","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":"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":"https://orcid.org/0000-0002-6050-6594","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":2,"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":1.9315,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85598665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"22","issue":"9","first_page":"3597","last_page":"3597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11448","display_name":"Face recognition and analysis","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7553496360778809},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5839229822158813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5838342308998108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5779404640197754},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5542240142822266},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5247897505760193},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.48176905512809753},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43627864122390747},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4287658929824829},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39516016840934753},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36297738552093506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553496360778809},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5839229822158813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5838342308998108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779404640197754},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5542240142822266},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5247897505760193},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.48176905512809753},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43627864122390747},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4287658929824829},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39516016840934753},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36297738552093506},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001288","descriptor_name":"Attention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001288","descriptor_name":"Attention","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","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":true},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008085","descriptor_name":"Lipreading","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":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","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":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.3390/s22093597","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22093597","pdf_url":"https://www.mdpi.com/1424-8220/22/9/3597/pdf?version=1652096174","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:35591284","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35591284","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:b459da903c454b62a2ae0e933f392050","is_oa":true,"landing_page_url":"https://doaj.org/article/b459da903c454b62a2ae0e933f392050","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 9, p 3597 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/9/3597/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22093597","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 9; Pages: 3597","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9099765","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9099765","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/s22093597","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22093597","pdf_url":"https://www.mdpi.com/1424-8220/22/9/3597/pdf?version=1652096174","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":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4229442847.pdf","grobid_xml":"https://content.openalex.org/works/W4229442847.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1526392145","https://openalex.org/W1527482779","https://openalex.org/W1936750108","https://openalex.org/W1955857676","https://openalex.org/W1962124124","https://openalex.org/W1972777337","https://openalex.org/W2002322356","https://openalex.org/W2004143321","https://openalex.org/W2058961190","https://openalex.org/W2060510034","https://openalex.org/W2064675550","https://openalex.org/W2078517841","https://openalex.org/W2078711706","https://openalex.org/W2081258893","https://openalex.org/W2092844010","https://openalex.org/W2115252128","https://openalex.org/W2127141656","https://openalex.org/W2141399712","https://openalex.org/W2267186426","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2551572271","https://openalex.org/W2602044573","https://openalex.org/W2604769302","https://openalex.org/W2605246626","https://openalex.org/W2624385633","https://openalex.org/W2738406145","https://openalex.org/W2738829388","https://openalex.org/W2752782242","https://openalex.org/W2755403114","https://openalex.org/W2793493229","https://openalex.org/W2799800213","https://openalex.org/W2802223794","https://openalex.org/W2884585870","https://openalex.org/W2914859359","https://openalex.org/W2918178295","https://openalex.org/W2923873652","https://openalex.org/W2941870244","https://openalex.org/W2962824709","https://openalex.org/W2962912639","https://openalex.org/W2963030892","https://openalex.org/W2963032190","https://openalex.org/W2963192365","https://openalex.org/W2963295405","https://openalex.org/W2963446712","https://openalex.org/W2963552679","https://openalex.org/W2964189376","https://openalex.org/W2987952236","https://openalex.org/W2997931247","https://openalex.org/W3001079424","https://openalex.org/W3091048148","https://openalex.org/W3091641623","https://openalex.org/W3099832538","https://openalex.org/W3109715615","https://openalex.org/W3111737660","https://openalex.org/W3112742522","https://openalex.org/W3128295041","https://openalex.org/W3128750130","https://openalex.org/W3145231825","https://openalex.org/W3182697172","https://openalex.org/W3187541079","https://openalex.org/W4200484186","https://openalex.org/W6635250320","https://openalex.org/W6677618333","https://openalex.org/W6680834391","https://openalex.org/W6682137061","https://openalex.org/W6735927292","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W1024498263","https://openalex.org/W2504816413"],"abstract_inverted_index":{"Concomitant":[0],"with":[1,77,167,180],"the":[2,87,95,106,113,128,131,137,140,149,168,173,181,184,188],"recent":[3],"advances":[4],"in":[5,33,86,112,118,197],"deep":[6],"learning,":[7],"automatic":[8],"speech":[9,13,26],"recognition":[10,14],"and":[11,30,68,94,123,148,162,172,193],"visual":[12],"(VSR)":[15],"have":[16,39],"received":[17],"considerable":[18],"attention.":[19],"However,":[20],"although":[21],"VSR":[22,37,56,192],"systems":[23],"must":[24],"identify":[25],"from":[27,61],"both":[28],"frontal":[29,43],"profile":[31],"faces":[32,59],"real-world":[34,198],"scenarios,":[35],"most":[36],"studies":[38],"focused":[40],"solely":[41],"on":[42,136],"face":[44],"pictures.":[45],"To":[46,126],"address":[47],"this":[48],"issue,":[49],"we":[50],"propose":[51],"an":[52],"end-to-end":[53],"sentence-level":[54],"multi-view":[55,191],"architecture":[57],"for":[58,134],"captured":[60],"four":[62,145],"different":[63,146],"perspectives":[64],"(frontal,":[65],"30\u00b0,":[66],"45\u00b0,":[67],"60\u00b0).":[69],"The":[70],"encoder":[71],"uses":[72,97],"multiple":[73],"convolutional":[74],"neural":[75],"networks":[76],"a":[78,119],"spatial":[79],"attention":[80],"module":[81],"to":[82,104],"detect":[83],"minor":[84],"changes":[85],"mouth":[88],"patterns":[89],"of":[90,108,130,190],"similarly":[91],"pronounced":[92],"words,":[93],"decoder":[96],"cascaded":[98],"local":[99,109],"self-attention":[100],"connectionist":[101],"temporal":[102],"classification":[103],"collect":[105],"details":[107],"contextual":[110],"information":[111],"immediate":[114],"vicinity,":[115],"which":[116],"results":[117],"substantial":[120],"performance":[121,129,151,175,189],"boost":[122],"speedy":[124],"convergence.":[125],"compare":[127],"proposed":[132],"model":[133],"experiments":[135],"OuluVS2":[138],"dataset,":[139],"dataset":[141],"was":[142,153],"divided":[143],"into":[144],"perspectives,":[147],"obtained":[150],"improvement":[152],"3.31%":[154],"(0\u00b0),":[155],"4.79%":[156],"(30\u00b0),":[157],"5.51%":[158],"(45\u00b0),":[159],"6.18%":[160],"(60\u00b0),":[161],"4.95%":[163],"(mean),":[164],"respectively,":[165],"compared":[166,179],"existing":[169],"state-of-the-art":[170],"performance,":[171],"average":[174],"improved":[176],"by":[177],"9.1%":[178],"baseline.":[182],"Thus,":[183],"suggested":[185],"design":[186],"enhances":[187],"boosts":[194],"its":[195],"usefulness":[196],"applications.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}