{"id":"https://openalex.org/W3111737660","doi":"https://doi.org/10.1109/slt48900.2021.9383540","title":"Speaker-Independent Visual Speech Recognition with the Inception V3 Model","display_name":"Speaker-Independent Visual Speech Recognition with the Inception V3 Model","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3111737660","doi":"https://doi.org/10.1109/slt48900.2021.9383540","mag":"3111737660"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5011262994","display_name":"Timothy Israel Santos","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Timothy Israel Santos","raw_affiliation_strings":["Research Institute of Big Data Analytics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","Research Institute of Big Data Analytics, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute of Big Data Analytics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"Research Institute of Big Data Analytics, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004036080","display_name":"Andrew Abel","orcid":"https://orcid.org/0000-0002-3631-8753"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andrew Abel","raw_affiliation_strings":["Research Institute of Big Data Analytics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","Research Institute of Big Data Analytics, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute of Big Data Analytics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"Research Institute of Big Data Analytics, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087947336","display_name":"Nick Wilson","orcid":"https://orcid.org/0000-0002-8496-3933"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nick Wilson","raw_affiliation_strings":["Macquarie University, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051481965","display_name":"Yan Xu","orcid":"https://orcid.org/0000-0002-4981-0165"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Xu","raw_affiliation_strings":["Research Institute of Big Data Analytics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","Research Institute of Big Data Analytics, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute of Big Data Analytics, Xi\u2019an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"Research Institute of Big Data Analytics, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6986,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83932517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"613","last_page":"620"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.8381987810134888},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7152554392814636},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6567281484603882},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.56816565990448},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4791509509086609},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4544917941093445},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4240868091583252},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4213936924934387},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4151734411716461},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4116177558898926},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4005579352378845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381987810134888},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7152554392814636},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6567281484603882},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.56816565990448},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4791509509086609},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4544917941093445},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4240868091583252},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4213936924934387},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4151734411716461},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4116177558898926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4005579352378845},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383540","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383540","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W335832833","https://openalex.org/W1503933356","https://openalex.org/W2000399372","https://openalex.org/W2007415209","https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2107435954","https://openalex.org/W2139055331","https://openalex.org/W2183341477","https://openalex.org/W2235946352","https://openalex.org/W2267805933","https://openalex.org/W2295107390","https://openalex.org/W2302255633","https://openalex.org/W2481971738","https://openalex.org/W2511073133","https://openalex.org/W2547018007","https://openalex.org/W2557728737","https://openalex.org/W2594690981","https://openalex.org/W2734984521","https://openalex.org/W2802223794","https://openalex.org/W2886945201","https://openalex.org/W2890952074","https://openalex.org/W2893436174","https://openalex.org/W2913906888","https://openalex.org/W2921533993","https://openalex.org/W2945999334","https://openalex.org/W2952746495","https://openalex.org/W2963030892","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W3003256084","https://openalex.org/W6611594693","https://openalex.org/W6676349587","https://openalex.org/W6698183232","https://openalex.org/W6754392867","https://openalex.org/W6758886315","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2077542787","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2070401501","https://openalex.org/W2121496884","https://openalex.org/W2387910809"],"abstract_inverted_index":{"The":[0,80],"natural":[1],"process":[2],"of":[3,26,114],"understanding":[4],"speech":[5,69],"involves":[6],"combining":[7],"auditory":[8],"and":[9,77,94],"visual":[10],"cues.":[11],"CNN":[12,54],"based":[13],"lip":[14,81,101],"reading":[15,82],"systems":[16,28],"have":[17],"become":[18],"very":[19],"popular":[20],"in":[21,122],"recent":[22],"years.":[23],"However,":[24],"many":[25],"these":[27],"consider":[29],"lipreading":[30],"to":[31,86,99],"be":[32],"a":[33],"black":[34],"box":[35],"problem,":[36],"with":[37,63,72],"limited":[38],"detailed":[39],"performance":[40,121],"analysis.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"performed":[46],"transfer":[47],"learning":[48,120],"by":[49],"training":[50],"the":[51,64,104],"Inception":[52],"v3":[53],"model,":[55],"which":[56],"has":[57],"pre-trained":[58],"weights":[59],"produced":[60],"from":[61],"IMAGENET,":[62],"GRID":[65,105],"corpus,":[66],"delivering":[67],"good":[68],"recognition":[70],"results,":[71],"0.61":[73],"precision,":[74],"0.53":[75],"recall,":[76],"0.51":[78],"F1-score.":[79],"model":[83],"was":[84],"able":[85],"automatically":[87],"learn":[88],"pertinent":[89],"features,":[90],"demonstrated":[91],"using":[92],"visualisation,":[93],"achieve":[95],"speaker-independent":[96],"results":[97],"comparable":[98],"human":[100],"readers":[102],"on":[103],"corpus.":[106],"We":[107],"also":[108],"identify":[109],"limitations":[110],"that":[111],"match":[112],"those":[113],"humans,":[115],"therefore":[116],"limiting":[117],"potential":[118],"deep":[119],"real":[123],"world":[124],"situations.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}