{"id":"https://openalex.org/W3110319481","doi":"https://doi.org/10.1109/iicaiet49801.2020.9257839","title":"Speech Enhancement System Using Lip-reading","display_name":"Speech Enhancement System Using Lip-reading","publication_year":2020,"publication_date":"2020-09-26","ids":{"openalex":"https://openalex.org/W3110319481","doi":"https://doi.org/10.1109/iicaiet49801.2020.9257839","mag":"3110319481"},"language":"en","primary_location":{"id":"doi:10.1109/iicaiet49801.2020.9257839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iicaiet49801.2020.9257839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","raw_type":"proceedings-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/A5102948461","display_name":"Kenji Matsui","orcid":"https://orcid.org/0009-0007-4980-6151"},"institutions":[{"id":"https://openalex.org/I72375662","display_name":"Osaka Institute of Technology","ror":"https://ror.org/02znffm54","country_code":"JP","type":"education","lineage":["https://openalex.org/I72375662"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenji Matsui","raw_affiliation_strings":["Faculty of Robotics & Design, Osaka Institute of Technology, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Robotics & Design, Osaka Institute of Technology, Osaka, Japan","institution_ids":["https://openalex.org/I72375662"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043416551","display_name":"Kohei Fukuyama","orcid":null},"institutions":[{"id":"https://openalex.org/I72375662","display_name":"Osaka Institute of Technology","ror":"https://ror.org/02znffm54","country_code":"JP","type":"education","lineage":["https://openalex.org/I72375662"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Fukuyama","raw_affiliation_strings":["Faculty of Robotics & Design, Osaka Institute of Technology, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Robotics & Design, Osaka Institute of Technology, Osaka, Japan","institution_ids":["https://openalex.org/I72375662"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083014247","display_name":"Yoshihisa Nakatoh","orcid":"https://orcid.org/0000-0002-5614-5204"},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihisa Nakatoh","raw_affiliation_strings":["Electrical and Electronic Engineering, Kyushu Institute of Technology, Kitakyushu, Japan"],"affiliations":[{"raw_affiliation_string":"Electrical and Electronic Engineering, Kyushu Institute of Technology, Kitakyushu, Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105938075","display_name":"Yumiko Kato","orcid":null},"institutions":[{"id":"https://openalex.org/I163917720","display_name":"St. Marianna University School of Medicine","ror":"https://ror.org/043axf581","country_code":"JP","type":"education","lineage":["https://openalex.org/I163917720"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yumiko O. Kato","raw_affiliation_strings":["School of Medicine, St. Marianna University, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"School of Medicine, St. Marianna University, Kawasaki, Japan","institution_ids":["https://openalex.org/I163917720"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102948461"],"corresponding_institution_ids":["https://openalex.org/I72375662"],"apc_list":null,"apc_paid":null,"fwci":0.4546,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.62824226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9927999973297119,"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/T11448","display_name":"Face recognition and analysis","score":0.983299970626831,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.8139494061470032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8030296564102173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6843795776367188},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5271969437599182},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.513936460018158},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5122179388999939},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4790857434272766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44505345821380615},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44415411353111267},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43124592304229736},{"id":"https://openalex.org/keywords/wearable-computer","display_name":"Wearable computer","score":0.41344892978668213},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40709030628204346},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3955666720867157},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2626303434371948},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.16291892528533936}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.8139494061470032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8030296564102173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6843795776367188},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5271969437599182},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.513936460018158},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5122179388999939},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4790857434272766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44505345821380615},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44415411353111267},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43124592304229736},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.41344892978668213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40709030628204346},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3955666720867157},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2626303434371948},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.16291892528533936},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iicaiet49801.2020.9257839","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iicaiet49801.2020.9257839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1813599753","https://openalex.org/W2008120082","https://openalex.org/W2087681821","https://openalex.org/W2152205330","https://openalex.org/W2578229578","https://openalex.org/W2793257307","https://openalex.org/W2903346628","https://openalex.org/W2906178486","https://openalex.org/W4298112588","https://openalex.org/W4299586661","https://openalex.org/W6672279060"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2053099149","https://openalex.org/W1559261064","https://openalex.org/W2299511660","https://openalex.org/W2124254345","https://openalex.org/W2105537028","https://openalex.org/W1910748333","https://openalex.org/W1493438996","https://openalex.org/W1567397589","https://openalex.org/W2013149918"],"abstract_inverted_index":{"We":[0],"have":[1],"been":[2],"developing":[3],"a":[4,97,120,150],"practical":[5],"speech":[6,53,90,213],"enhancement":[7,54,214],"system":[8,86],"that":[9,57,100,107,113],"supports":[10],"for":[11,116,142,217],"laryngectomee.":[12],"By":[13],"interviewing":[14],"users":[15,59,173],"we":[16,44,95],"captured":[17],"essential":[18],"issues,":[19],"such":[20,78],"as":[21],"\u201cutilization":[22],"of":[23,83,123,152,178,223],"existing":[24],"device\u201d,":[25],"\u201cthe":[26,33],"appearance":[27,156],"needs":[28],"to":[29,38,46,69,76,110,168,171],"be":[30,36,169],"inconspicuous\u201d,":[31],"and":[32,51,64,89,112,188,203,207,226],"device":[34],"should":[35],"easy":[37],"use\u201d.":[39],"Considering":[40],"those":[41],"user's":[42],"needs,":[43],"plan":[45],"use":[47],"smart":[48],"phone":[49],"platform":[50],"develop":[52],"application":[55],"so":[56],"the":[58,80,105,117,139,158],"are":[60],"just":[61],"ordinary":[62],"looking,":[63],"there":[65],"is":[66,114,149],"no":[67],"need":[68],"buy":[70],"any":[71],"additional":[72],"device.":[73],"In":[74,92],"order":[75],"realize":[77],"system,":[79],"key":[81],"concept":[82],"our":[84],"proposed":[85],"performs":[87],"lip-reading":[88,98,211],"synthesis.":[91],"this":[93],"study,":[94],"examined":[96],"method":[99],"can":[101],"recognize":[102],"by":[103],"registering":[104],"words":[106],"you":[108],"want":[109],"speak":[111],"optimized":[115],"user":[118],"using":[119,134,185],"small":[121,132,176,227],"amount":[122,177],"data.":[124],"36":[125],"viseme":[126,161],"images":[127],"were":[128],"converted":[129],"into":[130],"very":[131,175],"data":[133,141,180],"VAE(Variational":[135],"Auto":[136],"Encoder),":[137],"then":[138],"training":[140,179],"word":[143],"recognition":[144,183,201,229],"model":[145],"was":[146,166,190],"generated.":[147],"Viseme":[148],"group":[151],"phonemes":[153],"with":[154,164,174,192],"identical":[155],"on":[157],"lips.":[159],"Our":[160],"sequence":[162],"representation":[163],"VAE":[165,186],"used":[167],"able":[170],"adapt":[172],"set.":[181],"Word":[182],"experiment":[184],"encoder":[187],"CNN":[189],"performed":[191],"20":[193],"Japanese":[194],"words.":[195],"The":[196,210],"experimental":[197],"result":[198],"showed":[199],"65%":[200],"accuracy,":[202],"100%":[204],"including":[205],"1st":[206],"2nd":[208],"candidates.":[209],"type":[212],"seems":[215],"appropriate":[216],"embedding":[218],"mobile":[219],"devices":[220],"in":[221],"consideration":[222],"both":[224],"usability":[225],"vocabulary":[228],"accuracy.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}