{"id":"https://openalex.org/W4304775708","doi":"https://doi.org/10.3390/s22207738","title":"Noise-Robust Multimodal Audio-Visual Speech Recognition System for Speech-Based Interaction Applications","display_name":"Noise-Robust Multimodal Audio-Visual Speech Recognition System for Speech-Based Interaction Applications","publication_year":2022,"publication_date":"2022-10-12","ids":{"openalex":"https://openalex.org/W4304775708","doi":"https://doi.org/10.3390/s22207738","pmid":"https://pubmed.ncbi.nlm.nih.gov/36298089"},"language":"en","primary_location":{"id":"doi:10.3390/s22207738","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22207738","pdf_url":"https://www.mdpi.com/1424-8220/22/20/7738/pdf?version=1665568041","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/1424-8220/22/20/7738/pdf?version=1665568041","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":1.4858,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81902378,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"22","issue":"20","first_page":"7738","last_page":"7738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9986000061035156,"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":0.9878000020980835,"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/speech-recognition","display_name":"Speech recognition","score":0.814121663570404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7563449144363403},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5640851259231567},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5585564970970154},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5464675426483154},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4839916229248047},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41210728883743286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37069225311279297}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.814121663570404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563449144363403},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5640851259231567},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5585564970970154},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5464675426483154},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4839916229248047},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41210728883743286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37069225311279297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","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":"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},{"descriptor_ui":"D059629","descriptor_name":"Signal-To-Noise Ratio","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059629","descriptor_name":"Signal-To-Noise Ratio","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059629","descriptor_name":"Signal-To-Noise Ratio","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3390/s22207738","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22207738","pdf_url":"https://www.mdpi.com/1424-8220/22/20/7738/pdf?version=1665568041","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:36298089","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36298089","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:7cf3efced9c04066aa3b3060a678a2f2","is_oa":true,"landing_page_url":"https://doaj.org/article/7cf3efced9c04066aa3b3060a678a2f2","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 20, p 7738 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/22/20/7738/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s22207738","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 20; Pages: 7738","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9609693","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9609693","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/s22207738","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s22207738","pdf_url":"https://www.mdpi.com/1424-8220/22/20/7738/pdf?version=1665568041","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","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304775708.pdf","grobid_xml":"https://content.openalex.org/works/W4304775708.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W328004665","https://openalex.org/W1516675360","https://openalex.org/W1936750108","https://openalex.org/W1955857676","https://openalex.org/W1983364832","https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2034705742","https://openalex.org/W2036613402","https://openalex.org/W2043238171","https://openalex.org/W2054530828","https://openalex.org/W2054608764","https://openalex.org/W2083648150","https://openalex.org/W2115252128","https://openalex.org/W2125081437","https://openalex.org/W2127141656","https://openalex.org/W2146502635","https://openalex.org/W2153579005","https://openalex.org/W2267805933","https://openalex.org/W2404704342","https://openalex.org/W2556171197","https://openalex.org/W2596075132","https://openalex.org/W2807342784","https://openalex.org/W2884585870","https://openalex.org/W2888003177","https://openalex.org/W2916979304","https://openalex.org/W2947918020","https://openalex.org/W2950054078","https://openalex.org/W2963030892","https://openalex.org/W2963446712","https://openalex.org/W2991377192","https://openalex.org/W3003744889","https://openalex.org/W3006595947","https://openalex.org/W3021970402","https://openalex.org/W3037340973","https://openalex.org/W3119462944","https://openalex.org/W3121047153","https://openalex.org/W3176400644","https://openalex.org/W3181148910","https://openalex.org/W3217229075","https://openalex.org/W4223941643","https://openalex.org/W4280536924","https://openalex.org/W6631155274","https://openalex.org/W6677618333","https://openalex.org/W6681435938"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351","https://openalex.org/W1911859126","https://openalex.org/W642007152","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Speech":[0],"is":[1,11,28,50,81,188],"a":[2,12,72,78,87,95],"commonly":[3],"used":[4],"interaction-recognition":[5],"technique":[6],"in":[7,36,181],"edutainment-based":[8],"systems":[9,56],"and":[10,19,44,108,138,148,163,171,197],"key":[13],"technology":[14],"for":[15,136,144],"smooth":[16],"educational":[17],"learning":[18],"user-system":[20],"interaction.":[21],"However,":[22],"its":[23],"application":[24],"to":[25,31,60,62,65,167],"real":[26,37],"environments":[27],"limited":[29],"owing":[30],"the":[32,102,106,118],"various":[33,182],"noise":[34,130],"disruptions":[35],"environments.":[38,131],"In":[39],"this":[40],"study,":[41],"an":[42],"audio":[43,149,170],"visual":[45,146,172],"information-based":[46],"multimode":[47],"interaction":[48],"system":[49,120],"proposed":[51,119],"that":[52,57],"enables":[53],"virtual":[54],"aquarium":[55],"use":[58],"speech":[59,70,79,92,150,160,186],"interact":[61],"be":[63,179],"robust":[64],"ambient":[66],"noise.":[67],"For":[68],"audio-based":[69],"recognition,":[71],"list":[73],"of":[74,117,129],"words":[75],"recognized":[76],"by":[77,165],"API":[80,107],"expressed":[82],"as":[83,192],"word":[84],"vectors":[85,103],"using":[86],"pretrained":[88],"model.":[89],"Meanwhile,":[90],"vision-based":[91],"recognition":[93,154,187],"uses":[94],"composite":[96],"end-to-end":[97],"deep":[98],"neural":[99],"network.":[100],"Subsequently,":[101],"derived":[104],"from":[105,126],"vision":[109],"are":[110],"classified":[111],"after":[112],"concatenation.":[113],"The":[114],"signal-to-noise":[115],"ratio":[116],"was":[121,134,156,161],"determined":[122],"based":[123],"on":[124],"data":[125],"four":[127],"types":[128],"Furthermore,":[132],"it":[133],"tested":[135],"accuracy":[137],"efficiency":[139],"against":[140],"existing":[141],"single-mode":[142],"strategies":[143],"extracting":[145],"features":[147],"recognition.":[151],"Its":[152],"average":[153],"rate":[155],"91.42%":[157],"when":[158,169],"only":[159],"used,":[162],"improved":[164],"6.7%":[166],"98.12%":[168],"information":[173],"were":[174],"combined.":[175],"This":[176],"method":[177],"can":[178],"helpful":[180],"real-world":[183],"settings":[184],"where":[185],"regularly":[189],"utilized,":[190],"such":[191],"caf\u00e9s,":[193],"museums,":[194],"music":[195],"halls,":[196],"kiosks.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
