{"id":"https://openalex.org/W4223941643","doi":"https://doi.org/10.3390/s22082938","title":"End-to-End Lip-Reading Open Cloud-Based Speech Architecture","display_name":"End-to-End Lip-Reading Open Cloud-Based Speech Architecture","publication_year":2022,"publication_date":"2022-04-12","ids":{"openalex":"https://openalex.org/W4223941643","doi":"https://doi.org/10.3390/s22082938","pmid":"https://pubmed.ncbi.nlm.nih.gov/35458932"},"language":"en","primary_location":{"id":"doi:10.3390/s22082938","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22082938","pdf_url":"https://www.mdpi.com/1424-8220/22/8/2938/pdf?version=1649759304","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/1424-8220/22/8/2938/pdf?version=1649759304","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":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":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":1.783,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.84297038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"22","issue":"8","first_page":"2938","last_page":"2938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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/cloud-computing","display_name":"Cloud computing","score":0.6818966269493103},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6427487134933472},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5691659450531006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5324515104293823},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.509383499622345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38638803362846375},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3560619354248047},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19166654348373413},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19141343235969543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1826368272304535},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09881740808486938},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.09307414293289185}],"concepts":[{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6818966269493103},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6427487134933472},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5691659450531006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5324515104293823},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.509383499622345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38638803362846375},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3560619354248047},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19166654348373413},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19141343235969543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1826368272304535},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09881740808486938},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.09307414293289185},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000067917","descriptor_name":"Cloud Computing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000067917","descriptor_name":"Cloud Computing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000067917","descriptor_name":"Cloud Computing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","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":"D013060","descriptor_name":"Speech","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":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":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s22082938","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22082938","pdf_url":"https://www.mdpi.com/1424-8220/22/8/2938/pdf?version=1649759304","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:35458932","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35458932","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:e5c40c93c04e46d4b9fd49aedabfa041","is_oa":true,"landing_page_url":"https://doaj.org/article/e5c40c93c04e46d4b9fd49aedabfa041","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 8, p 2938 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/8/2938/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22082938","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 8; Pages: 2938","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9029225","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9029225","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/s22082938","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22082938","pdf_url":"https://www.mdpi.com/1424-8220/22/8/2938/pdf?version=1649759304","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":0.800000011920929,"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/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4223941643.pdf","grobid_xml":"https://content.openalex.org/works/W4223941643.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W328004665","https://openalex.org/W1516675360","https://openalex.org/W1878981136","https://openalex.org/W1983364832","https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2034705742","https://openalex.org/W2054530828","https://openalex.org/W2054608764","https://openalex.org/W2058961190","https://openalex.org/W2060510034","https://openalex.org/W2083648150","https://openalex.org/W2084339293","https://openalex.org/W2102409316","https://openalex.org/W2115252128","https://openalex.org/W2125081437","https://openalex.org/W2127141656","https://openalex.org/W2153579005","https://openalex.org/W2194775991","https://openalex.org/W2267805933","https://openalex.org/W2404704342","https://openalex.org/W2556171197","https://openalex.org/W2596075132","https://openalex.org/W2735043505","https://openalex.org/W2793493229","https://openalex.org/W2916979304","https://openalex.org/W2963032190","https://openalex.org/W2964170943","https://openalex.org/W3082696729","https://openalex.org/W3097018422","https://openalex.org/W3119462944","https://openalex.org/W3119913666","https://openalex.org/W3121047153","https://openalex.org/W4200484186","https://openalex.org/W4232282348","https://openalex.org/W4313177291","https://openalex.org/W6631155274","https://openalex.org/W6675401909","https://openalex.org/W6677618333"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W4244478748","https://openalex.org/W3179968364","https://openalex.org/W4223488648","https://openalex.org/W2134969820","https://openalex.org/W2251605416","https://openalex.org/W1997222214","https://openalex.org/W2560439919","https://openalex.org/W4389340727","https://openalex.org/W3150465815"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"technology":[2],"has":[3,21],"encouraged":[4],"research":[5],"on":[6,53,88],"noise-robust":[7,49],"automatic":[8],"speech":[9,29,122],"recognition":[10,30],"(ASR).":[11],"The":[12,109,157,179],"combination":[13],"of":[14,26,126,192],"cloud":[15],"computing":[16],"technologies":[17],"and":[18,71,136,151],"artificial":[19],"intelligence":[20],"significantly":[22],"improved":[23,183],"the":[24,76,84,90,102,116,143,161,176,190],"performance":[25,184],"open":[27],"cloud-based":[28],"application":[31,39],"programming":[32],"interfaces":[33],"(OCSR":[34],"APIs).":[35],"Noise-robust":[36],"ASRs":[37],"for":[38,58,120,195],"in":[40,61,142,185],"different":[41],"environments":[42],"are":[43],"being":[44],"developed.":[45],"This":[46],"study":[47],"proposes":[48],"OCSR":[50,65,162,193],"APIs":[51,194],"based":[52],"an":[54],"end-to-end":[55],"lip-reading":[56,118,145],"architecture":[57,119,159],"practical":[59,196],"applications":[60],"various":[62,186],"environments.":[63],"Several":[64],"APIs,":[66],"including":[67],"Google,":[68],"Microsoft,":[69],"Amazon,":[70],"Naver,":[72],"were":[73,140,153],"evaluated":[74],"using":[75,169],"Google":[77],"Voice":[78],"Command":[79],"Dataset":[80],"v2":[81],"to":[82,100],"obtain":[83],"optimum":[85],"performance.":[86],"Based":[87],"performance,":[89],"Microsoft":[91],"API":[92,150,163],"was":[93,113],"integrated":[94,114],"with":[95,104,115,175],"Google's":[96],"trained":[97],"word2vec":[98],"model":[99,181],"enhance":[101],"keywords":[103],"more":[105],"complete":[106],"semantic":[107],"information.":[108],"extracted":[110,148],"word":[111],"vector":[112],"proposed":[117,144,158,180],"audio-visual":[121],"recognition.":[123],"Three":[124],"forms":[125],"convolutional":[127],"neural":[128],"networks":[129],"(3D":[130],"CNN,":[131,135],"3D":[132,138],"dense":[133],"connection":[134],"multilayer":[137],"CNN)":[139],"used":[141],"architecture.":[146],"Vectors":[147],"from":[149],"vision":[152],"classified":[154],"after":[155],"concatenation.":[156],"enhanced":[160],"average":[164],"accuracy":[165],"rate":[166],"by":[167],"14.42%":[168],"standard":[170],"ASR":[171],"evaluation":[172],"measures":[173],"along":[174],"signal-to-noise":[177],"ratio.":[178],"exhibits":[182],"noise":[187],"settings,":[188],"increasing":[189],"dependability":[191],"applications.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
