{"id":"https://openalex.org/W2155659818","doi":"https://doi.org/10.1109/icme.2003.1220871","title":"A sensor-fusion method for detecting a speaking student","display_name":"A sensor-fusion method for detecting a speaking student","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2155659818","doi":"https://doi.org/10.1109/icme.2003.1220871","mag":"2155659818"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1220871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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/A5002402277","display_name":"Shu Nishiguchi","orcid":"https://orcid.org/0000-0001-9303-8670"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Nishiguchi","raw_affiliation_strings":["Graduate School of Law, Kyoto University, Sakyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Law, Kyoto University, Sakyo, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027408196","display_name":"Kazuhide Higashi","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Higashi","raw_affiliation_strings":["Graduate School of Informatics, Institute Co. Ltd, Osaka, Japan","Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Institute Co. Ltd, Osaka, Japan","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031926485","display_name":"Yoshinari Kameda","orcid":"https://orcid.org/0000-0001-6776-1267"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Kameda","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University Kyoto, Sakyoku, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University Kyoto, Sakyoku, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006308263","display_name":"Michihiko Minoh","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Minoh","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University Kyoto, Sakyoku, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University Kyoto, Sakyoku, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"I","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9932000041007996,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9921000003814697,"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":0.7927572727203369},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7734307050704956},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6745190024375916},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.57802414894104},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5377237200737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5149458050727844},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.504226803779602},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.5035306811332703},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4979526996612549},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4866355359554291},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4236443042755127},{"id":"https://openalex.org/keywords/multilateration","display_name":"Multilateration","score":0.42303526401519775},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2992115914821625},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1040104329586029},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09505364298820496},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.06721815466880798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7927572727203369},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7734307050704956},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6745190024375916},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.57802414894104},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5377237200737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149458050727844},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.504226803779602},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5035306811332703},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4979526996612549},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4866355359554291},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4236443042755127},{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.42303526401519775},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2992115914821625},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1040104329586029},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09505364298820496},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.06721815466880798},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2003.1220871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1220871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1721259867","https://openalex.org/W1742928390","https://openalex.org/W2086892024","https://openalex.org/W2127000566","https://openalex.org/W2147547466","https://openalex.org/W2151849741","https://openalex.org/W3094595553","https://openalex.org/W6672274791"],"related_works":["https://openalex.org/W2288274698","https://openalex.org/W4385361701","https://openalex.org/W4391643140","https://openalex.org/W2068968550","https://openalex.org/W2770231486","https://openalex.org/W2187684650","https://openalex.org/W2159296145","https://openalex.org/W1879255185","https://openalex.org/W4386900535","https://openalex.org/W1983991597"],"abstract_inverted_index":{"In":[0,106],"this":[1,45,107],"paper,":[2,108],"we":[3,109],"propose":[4,110],"a":[5,16,32,35,41,55,62,73,85,98,103,111,119,147],"method":[6,112],"for":[7,113],"detecting":[8,114,143],"the":[9,12,52,70,82,122,128,139,144],"location":[10,53,71,83,117,145],"of":[11,18,34,54,72,84,94,118,142,146],"speaker":[13,120,148],"that":[14,31,138],"is":[15,29,38,48,65,78],"target":[17],"automatic":[19],"video":[20],"filming":[21],"in":[22,40,97,121],"distance":[23],"learning":[24],"and":[25],"lecture":[26,42,104,123],"archive.":[27],"It":[28],"required":[30],"face":[33],"speaking":[36],"student":[37],"filmed":[39],"video.":[43],"For":[44],"purpose,":[46],"it":[47,77],"necessary":[49],"to":[50,68,80],"detect":[51,69,81],"speaker.":[56],"An":[57],"acoustic":[58],"sensor":[59],"such":[60,101],"as":[61,102],"microphone":[63,91,129],"array":[64,92,130],"used":[66],"widely":[67],"sound":[74,86,95],"source.":[75],"However,":[76],"difficult":[79],"source":[87],"precisely":[88],"using":[89,125],"only":[90,127],"because":[93],"noise":[96],"large":[99],"space":[100],"room.":[105],"more":[115],"precise":[116],"room":[124],"not":[126],"but":[131],"also":[132],"visual":[133],"sensors.":[134],"The":[135],"result":[136],"shows":[137],"precision":[140],"ratio":[141],"was":[149],"improved":[150],"about":[151],"20%":[152],"by":[153],"our":[154],"sensor-fusion":[155],"method.":[156]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}