{"id":"https://openalex.org/W2117061651","doi":"https://doi.org/10.1109/icme.2002.1035609","title":"Real time face detection for multimodal speech recognition","display_name":"Real time face detection for multimodal speech recognition","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2117061651","doi":"https://doi.org/10.1109/icme.2002.1035609","mag":"2117061651"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2002.1035609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046029799","display_name":"Kazumasa Murai","orcid":null},"institutions":[{"id":"https://openalex.org/I15009632","display_name":"Fuji Xerox (Japan)","ror":"https://ror.org/02w528w58","country_code":"JP","type":"company","lineage":["https://openalex.org/I15009632"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Murai","raw_affiliation_strings":["ATR Spoken Language Translation Research Laboratories, Japan","Inf. Media Lab., Fuji Xerox, Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Japan","institution_ids":[]},{"raw_affiliation_string":"Inf. Media Lab., Fuji Xerox, Kanagawa, Japan","institution_ids":["https://openalex.org/I15009632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Nakamura","raw_affiliation_strings":["ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5895,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83398285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"373","last_page":"376"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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/T10057","display_name":"Face and Expression Recognition","score":0.9900000095367432,"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/T11448","display_name":"Face recognition and analysis","score":0.9835000038146973,"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":0.8066143989562988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7294009923934937},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.6733317971229553},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6453790068626404},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6398626565933228},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5870262384414673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.571292519569397},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.553338885307312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5451844930648804},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.5295872092247009},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.51836758852005},{"id":"https://openalex.org/keywords/three-dimensional-face-recognition","display_name":"Three-dimensional face recognition","score":0.4674801528453827},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4342820644378662},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.42849260568618774},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42087244987487793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8066143989562988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7294009923934937},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.6733317971229553},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6453790068626404},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6398626565933228},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5870262384414673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.571292519569397},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.553338885307312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5451844930648804},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.5295872092247009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.51836758852005},{"id":"https://openalex.org/C88799230","wikidata":"https://www.wikidata.org/wiki/Q3398329","display_name":"Three-dimensional face recognition","level":5,"score":0.4674801528453827},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4342820644378662},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.42849260568618774},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42087244987487793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2002.1035609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W97324877","https://openalex.org/W160552598","https://openalex.org/W2100009494","https://openalex.org/W2108891849","https://openalex.org/W2170158200","https://openalex.org/W2228387523","https://openalex.org/W2404660328","https://openalex.org/W2487271655","https://openalex.org/W6603930416","https://openalex.org/W6606522495","https://openalex.org/W6689065797","https://openalex.org/W6713584497"],"related_works":["https://openalex.org/W325114128","https://openalex.org/W4206923589","https://openalex.org/W3034828634","https://openalex.org/W3014491775","https://openalex.org/W2184186800","https://openalex.org/W980171259","https://openalex.org/W4360994936","https://openalex.org/W1571439987","https://openalex.org/W2548308221","https://openalex.org/W74006108"],"abstract_inverted_index":{"We":[0,111],"propose":[1],"a":[2,79,135],"real":[3,74],"time":[4],"system":[5,77],"to":[6,41,68,115,137,145],"detect":[7],"the":[8,37,52,57,60,70,97,100,104,117,121,127,130,143,158,164,171],"speaker's":[9,38,53,71],"frontal":[10,165],"face":[11,72,166],"for":[12,120],"multimodal":[13],"speech":[14,22],"recognition.":[15],"It":[16],"is":[17,78,92],"widely":[18],"acknowledged":[19],"that":[20],"automatic":[21],"recognizers,":[23],"as":[24,26,51,134],"well":[25],"humans,":[27],"can":[28],"improve":[29],"recognition":[30],"performance":[31],"by":[32,170],"adding":[33],"visual":[34],"modality,":[35],"i.e.,":[36],"facial":[39,54,128],"image":[40],"audio":[42],"modality.":[43],"Visual":[44],"modality":[45],"also":[46],"provides":[47],"inaudible":[48],"information,":[49,65],"such":[50],"orientation,":[55,129],"and":[56,85,99,161],"location":[58],"of":[59,81,142,157,163],"mouth.":[61],"To":[62],"acquire":[63],"this":[64],"we":[66],"have":[67],"localize":[69],"in":[73,140],"time.":[75],"Our":[76],"combination":[80],"skin":[82,98],"color":[83,154],"detection":[84,91,107],"spatial":[86,122,173],"feature":[87,106,123],"detection.":[88,124],"The":[89],"color-based":[90,113],"fast":[93],"but":[94],"depends":[95],"on":[96,153],"background":[101],"color,":[102],"while":[103],"special":[105],"requires":[108],"more":[109],"computation.":[110],"applied":[112],"pruning":[114,151],"reduce":[116],"search":[118,159],"space":[119],"By":[125],"detecting":[126],"proposed":[131],"method":[132],"functions":[133],"\"face":[136],"talk\"":[138,146],"switch":[139],"place":[141],"\"push":[144],"switch.":[147],"In":[148],"our":[149],"experiment,":[150],"based":[152],"reduced":[155],"53-97%":[156],"space,":[160],"98.9%":[162],"was":[167],"detected":[168],"correctly":[169],"subsequent":[172],"detector.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}