{"id":"https://openalex.org/W1980370676","doi":"https://doi.org/10.1109/humanoids.2012.6651577","title":"Improvement of audio-visual score following in robot ensemble with human guitarist","display_name":"Improvement of audio-visual score following in robot ensemble with human guitarist","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W1980370676","doi":"https://doi.org/10.1109/humanoids.2012.6651577","mag":"1980370676"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2012.6651577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2012.6651577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)","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/A5078173393","display_name":"Tatsuhiko Itohara","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":true,"raw_author_name":"Tatsuhiko Itohara","raw_affiliation_strings":["Kyoto Univ., Japan","Kyoto University, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Kyoto Univ., Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"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":"Kazuhiro Nakadai","raw_affiliation_strings":["Honda Res. Inst. Japan Co., Ltd., Japan","Honda Research Institute Japan, Co. Ltd., Japan"],"affiliations":[{"raw_affiliation_string":"Honda Res. Inst. Japan Co., Ltd., 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/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"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":"Tetsuya Ogata","raw_affiliation_strings":["Waseda Univ., Japan","Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda Univ., Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"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":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto Univ., Japan","Kyoto University, Kyoto, Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"Kyoto Univ., Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University, Kyoto, Japan#TAB#","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078173393"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.7429,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72319454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"574","last_page":"579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7566543817520142},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.7321774363517761},{"id":"https://openalex.org/keywords/guitar","display_name":"Guitar","score":0.6750062704086304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6322333812713623},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.6237701773643494},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6013809442520142},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4693008065223694},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.43715110421180725},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08314236998558044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566543817520142},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.7321774363517761},{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.6750062704086304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322333812713623},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.6237701773643494},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6013809442520142},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4693008065223694},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.43715110421180725},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08314236998558044},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids.2012.6651577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2012.6651577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W22745672","https://openalex.org/W1549486140","https://openalex.org/W1964443764","https://openalex.org/W1995410514","https://openalex.org/W2006048584","https://openalex.org/W2037803315","https://openalex.org/W2085261163","https://openalex.org/W2108775563","https://openalex.org/W2114640443","https://openalex.org/W2118877769","https://openalex.org/W2123523634","https://openalex.org/W2140675419","https://openalex.org/W2150452896","https://openalex.org/W2160341867","https://openalex.org/W6676035551","https://openalex.org/W6680927614"],"related_works":["https://openalex.org/W4220911637","https://openalex.org/W4385984930","https://openalex.org/W1990291079","https://openalex.org/W3118230952","https://openalex.org/W1521076561","https://openalex.org/W2232760491","https://openalex.org/W3033873164","https://openalex.org/W195768781","https://openalex.org/W4236830223","https://openalex.org/W2980733656"],"abstract_inverted_index":{"Our":[0],"goal":[1],"is":[2,53,90,105,149,187],"to":[3,22,150,154,163,243],"create":[4],"an":[5,54,138,141,244],"ensemble":[6],"between":[7,179],"human":[8],"guitarists":[9,73,89],"and":[10,15,26,34,39,77,117,160,182,212,221,232],"music":[11],"robots,":[12],"e.g.,":[13],"singing":[14],"playing":[16],"instruments":[17],"robots.":[18],"Such":[19],"robots":[20],"need":[21],"detect":[23],"the":[24,30,94,100,119,174,180,190,200,207,230,233],"tempo":[25,231],"beat":[27,35,82,86,97,143],"time":[28],"of":[29,96,102,140,157,166,176,203,219,236],"music.":[31],"Score":[32,51],"following":[33,52,61,133,227],"tracking,":[36],"which":[37],"requires":[38,42],"does":[40],"not":[41,114],"a":[43,67,130,135,183,204,215,237],"score,":[44,69],"are":[45,171],"commonly":[46],"used":[47,172,188],"for":[48,72,88,134,173,199],"this":[49,103,126],"purpose.":[50],"incremental":[55],"audio-to-score":[56],"alignment.":[57],"Although":[58],"most":[59,70],"score":[60,132,210,226,234],"methods":[62],"assume":[63],"that":[64,92],"players":[65],"have":[66,74],"precise":[68],"scores":[71],"only":[75,111],"melody":[76],"chord":[78,152,177],"sequences":[79,153,170],"without":[80],"any":[81],"patterns.":[83],"An":[84],"audio-visual":[85,142],"tracking":[87,121,144,156,165],"reported":[91],"improves":[93,229],"accuracy":[95],"detection.":[98],"However,":[99],"result":[101],"method":[104],"still":[106],"insufficient":[107],"because":[108,118],"it":[109],"uses":[110],"onset":[112],"information,":[113,116],"pitch":[115],"hand":[120],"shows":[122],"low":[123],"accuracy.":[124],"In":[125],"paper,":[127],"we":[128],"report":[129],"multimodal":[131],"guitar":[136,167,191],"performance,":[137],"extension":[139],"method.":[145],"The":[146,224],"main":[147],"difference":[148],"use":[151],"improve":[155,164],"audio":[158,220],"signals":[159],"depth":[161],"information":[162,186],"playing.":[168],"Chord":[169],"calculation":[175],"correlation":[178],"input":[181],"score.":[184],"Depth":[185],"in":[189],"plane":[192],"masking":[193],"by":[194,214,239],"three":[195],"dimensional":[196],"Hough":[197],"transform,":[198],"stable":[201],"detection":[202],"hand.":[205],"Finally,":[206],"system":[208,228],"extracts":[209],"positions":[211],"tempos":[213],"particle-filter":[216],"based":[217],"integration":[218],"visual":[222],"features,":[223],"resulting":[225],"position":[235],"performance":[238],"0.2":[240],"[sec]":[241],"compared":[242],"existing":[245],"system.":[246]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}