{"id":"https://openalex.org/W1989368432","doi":"https://doi.org/10.1117/12.2038375","title":"Automatic lip reading by using multimodal visual features","display_name":"Automatic lip reading by using multimodal visual features","publication_year":2014,"publication_date":"2014-01-31","ids":{"openalex":"https://openalex.org/W1989368432","doi":"https://doi.org/10.1117/12.2038375","mag":"1989368432"},"language":"en","primary_location":{"id":"doi:10.1117/12.2038375","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2038375","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","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/A5057762669","display_name":"Shohei Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shohei Takahashi","raw_affiliation_strings":["Waseda Univ. (Japan)","Waseda University,JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda Univ. (Japan)","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University,JAPAN","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111371620","display_name":"Jun Ohya","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Ohya","raw_affiliation_strings":["Waseda Univ. (Japan)","Waseda University,JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda Univ. (Japan)","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University,JAPAN","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.2949,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53659094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"9025","issue":null,"first_page":"902508","last_page":"902508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9717000126838684,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9298999905586243,"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":0.8705778121948242},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7533654570579529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310968160629272},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.49122875928878784},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.44929635524749756},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.44507065415382385},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.420899897813797},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31042730808258057},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.16081830859184265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8705778121948242},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7533654570579529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310968160629272},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.49122875928878784},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.44929635524749756},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.44507065415382385},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.420899897813797},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31042730808258057},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.16081830859184265},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2038375","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2038375","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1547701650","https://openalex.org/W2046599127","https://openalex.org/W2106137268","https://openalex.org/W2118564005","https://openalex.org/W3044030936","https://openalex.org/W6632694911","https://openalex.org/W6781194548"],"related_works":["https://openalex.org/W4253235840","https://openalex.org/W2116497041","https://openalex.org/W2591964346","https://openalex.org/W2981428355","https://openalex.org/W2150288981","https://openalex.org/W1599055764","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2131711534","https://openalex.org/W2289873871"],"abstract_inverted_index":{"Since":[0],"long":[1],"time":[2],"ago,":[3],"speech":[4,40,45,75,106,119],"recognition":[5,76],"has":[6],"been":[7],"researched,":[8],"though":[9],"it":[10],"does":[11],"not":[12,56],"work":[13,79],"well":[14,80],"in":[15,20,24,34,68,81,137,176],"noisy":[16,82],"places":[17],"such":[18,64,117],"as":[19,65,118],"the":[21,25,44,69,105,122,133,142,150,156,162,182],"car":[22],"or":[23,32],"train.":[26],"In":[27,94],"addition,":[28],"people":[29,90],"with":[30,91],"hearing-impaired":[31],"difficulties":[33],"hearing":[35,92],"cannot":[36],"receive":[37],"benefits":[38],"from":[39,55,155],"recognition.":[41,120],"To":[42],"recognize":[43],"automatically,":[46],"visual":[47,62,110],"information":[48,63,111,116],"is":[49,127,174],"also":[50,61,88],"important.":[51],"People":[52],"understand":[53],"speeches":[54],"only":[57],"audio":[58,115],"information,":[59],"but":[60],"temporal":[66],"changes":[67],"lip":[70,136,151,157],"shape.":[71],"A":[72],"vision":[73],"based":[74],"method":[77,102],"could":[78,85],"places,":[83],"and":[84,131,135,146,180],"be":[86],"useful":[87],"for":[89,103,186],"disabilities.":[93],"this":[95,194],"paper,":[96],"we":[97],"propose":[98],"an":[99],"automatic":[100],"lip-reading":[101],"recognizing":[104],"by":[107,159],"using":[108,113],"multimodal":[109,164],"without":[112],"any":[114],"First,":[121],"ASM":[123],"(Active":[124],"Shape":[125],"Model)":[126],"used":[128],"to":[129,178],"track":[130],"detect":[132],"face":[134],"a":[138],"video":[139],"sequence.":[140],"Second,":[141],"shape,":[143],"optical":[144],"flow":[145],"spatial":[147],"frequencies":[148],"of":[149,193],"features":[152,165],"are":[153,166],"extracted":[154,163],"detected":[158],"ASM.":[160],"Next,":[161],"ordered":[167],"chronologically":[168],"so":[169],"that":[170],"Support":[171],"Vector":[172],"Machine":[173],"performed":[175],"order":[177],"learn":[179],"classify":[181],"spoken":[183],"words.":[184],"Experiments":[185],"classifying":[187],"several":[188],"words":[189],"show":[190],"promising":[191],"results":[192],"proposed":[195],"method.":[196]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}