{"id":"https://openalex.org/W2073995819","doi":"https://doi.org/10.1109/icassp.2010.5494889","title":"Robot-directed speech detection using Multimodal Semantic Confidence based on speech, image, and motion","display_name":"Robot-directed speech detection using Multimodal Semantic Confidence based on speech, image, and motion","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2073995819","doi":"https://doi.org/10.1109/icassp.2010.5494889","mag":"2073995819"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5494889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5494889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5081759820","display_name":"Xiang Zuo","orcid":"https://orcid.org/0000-0003-3814-1151"},"institutions":[{"id":"https://openalex.org/I27429435","display_name":"Kyoto Institute of Technology","ror":"https://ror.org/00965ax52","country_code":"JP","type":"education","lineage":["https://openalex.org/I27429435"]},{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiang Zuo","raw_affiliation_strings":["Kyoto Institute of Technology, Japan","Advanced Telecommunication Research Labs, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto Institute of Technology, Japan","institution_ids":["https://openalex.org/I27429435"]},{"raw_affiliation_string":"Advanced Telecommunication Research Labs, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112415166","display_name":"Naoto Iwahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoto Iwahashi","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","Advanced Telecommunication Research Labs, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Advanced Telecommunication Research Labs, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001868908","display_name":"Ryo Taguchi","orcid":"https://orcid.org/0000-0003-1933-2868"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]},{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Taguchi","raw_affiliation_strings":["Nagoya Institute of Technology, Japan","Advanced Telecommunication Research Labs, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Advanced Telecommunication Research Labs, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077037266","display_name":"Shigeki Matsuda","orcid":"https://orcid.org/0000-0001-9156-8133"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Matsuda","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033744547","display_name":"Komei Sugiura","orcid":"https://orcid.org/0000-0002-0261-0510"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Komei Sugiura","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069989297","display_name":"Kotaro Funakoshi","orcid":"https://orcid.org/0000-0002-4529-4634"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kotaro Funakoshi","raw_affiliation_strings":["Honda Research Institute Japan Company Limited, Japan","Honda Research Institute Japan, Co. Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan, Co. Ltd., Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085401834","display_name":"Mikio Nakano","orcid":"https://orcid.org/0000-0001-6057-3132"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mikio Nakano","raw_affiliation_strings":["Honda Research Institute Japan Company Limited, Japan","Honda Research Institute Japan, Co. Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Japan","institution_ids":["https://openalex.org/I1283473643"]},{"raw_affiliation_string":"Honda Research Institute Japan, Co. Ltd., Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101441136","display_name":"Natsuki Oka","orcid":"https://orcid.org/0000-0003-3396-671X"},"institutions":[{"id":"https://openalex.org/I27429435","display_name":"Kyoto Institute of Technology","ror":"https://ror.org/00965ax52","country_code":"JP","type":"education","lineage":["https://openalex.org/I27429435"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Natsuki Oka","raw_affiliation_strings":["Kyoto Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto Institute of Technology, Japan","institution_ids":["https://openalex.org/I27429435"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2006","issue":null,"first_page":"2458","last_page":"2461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"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":0.7436020374298096},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.7320379018783569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6217387318611145},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5955501794815063},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5249826312065125},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5231900811195374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112390518188477},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5009856224060059},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43433430790901184},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42793920636177063},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.09556308388710022},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06491756439208984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436020374298096},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.7320379018783569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6217387318611145},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5955501794815063},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5249826312065125},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5231900811195374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112390518188477},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5009856224060059},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43433430790901184},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42793920636177063},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.09556308388710022},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06491756439208984},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5494889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5494889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W35070573","https://openalex.org/W1490321952","https://openalex.org/W1947346786","https://openalex.org/W1973948212","https://openalex.org/W2001676056","https://openalex.org/W2034537249","https://openalex.org/W2085157346","https://openalex.org/W2108313113","https://openalex.org/W2108370224","https://openalex.org/W2131642018","https://openalex.org/W2144647101","https://openalex.org/W4298222310","https://openalex.org/W6681201638"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,35,74],"novel":[6],"method":[7,76],"to":[8,26],"detect":[9],"robot-directed":[10],"(RD)":[11],"speech":[12,30,79,91,96],"that":[13,62,77],"adopts":[14],"the":[15,29,39],"Multimodal":[16],"Semantic":[17],"Confidence":[18],"(MSC)":[19],"measure.":[20],"The":[21],"MSC":[22,82],"measure":[23,49],"is":[24,50],"used":[25],"decide":[27],"whether":[28],"can":[31],"be":[32],"interpreted":[33],"as":[34],"feasible":[36],"action":[37],"under":[38],"current":[40],"physical":[41],"situation":[42],"in":[43,97],"an":[44,84],"object":[45],"manipulation":[46],"task.":[47],"This":[48],"calculated":[51],"by":[52,65],"integrating":[53],"speech,":[54],"image,":[55],"and":[56,92],"motion":[57],"confidence":[58,80],"measures":[59],"with":[60,73],"weightings":[61],"are":[63],"optimized":[64],"logistic":[66],"regression.":[67],"Experimental":[68],"results":[69],"show":[70],"that,":[71],"compared":[72],"baseline":[75],"uses":[78],"only,":[81],"achieved":[83],"absolute":[85],"increase":[86],"of":[87,99],"5%":[88],"for":[89,94],"clean":[90],"12%":[93],"noisy":[95],"terms":[98],"average":[100],"maximum":[101],"F-measure.":[102]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
