{"id":"https://openalex.org/W2128352481","doi":"https://doi.org/10.1109/iros.2009.5354637","title":"Incremental polyphonic audio to score alignment using beat tracking for singer robots","display_name":"Incremental polyphonic audio to score alignment using beat tracking for singer robots","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2128352481","doi":"https://doi.org/10.1109/iros.2009.5354637","mag":"2128352481"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2009.5354637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2009.5354637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5005813383","display_name":"Takuma Otsuka","orcid":"https://orcid.org/0000-0001-7585-8202"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Otsuka","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065967819","display_name":"T\u00f4ru Takahashi","orcid":"https://orcid.org/0000-0002-8476-9751"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Takahashi","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"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":"Hiroshi G. Okuno","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan","Honda Research Institute Japan Company Limited, Wako, Saitama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Honda Research Institute Japan Company Limited, Wako, Saitama, Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"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/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108516910","display_name":"Kazumasa Murata","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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazumasa Murata","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5003,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89262767,"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":"2289","last_page":"2296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/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/T11349","display_name":"Music Technology and Sound Studies","score":0.9998000264167786,"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/speech-recognition","display_name":"Speech recognition","score":0.7063231468200684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.653533399105072},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6254550814628601},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.5293962359428406},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.5184330940246582},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5110801458358765},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4533284902572632},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4372100234031677},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.4302401542663574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3532745838165283},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22140872478485107},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11811086535453796},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.11769723892211914},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1093306839466095},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08003705739974976}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7063231468200684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.653533399105072},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6254550814628601},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.5293962359428406},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.5184330940246582},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5110801458358765},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4533284902572632},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4372100234031677},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.4302401542663574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3532745838165283},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22140872478485107},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11811086535453796},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11769723892211914},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1093306839466095},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08003705739974976},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2009.5354637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2009.5354637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.4032","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.4032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/members/okuno/Public/IROS2009-Ohtsuka.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1519655822","https://openalex.org/W1549486140","https://openalex.org/W1593713094","https://openalex.org/W1965537615","https://openalex.org/W2018765478","https://openalex.org/W2100291405","https://openalex.org/W2108850708","https://openalex.org/W2120202836","https://openalex.org/W2121232083","https://openalex.org/W2124097505","https://openalex.org/W2128456226","https://openalex.org/W2129373410","https://openalex.org/W2132659533","https://openalex.org/W2145458549","https://openalex.org/W2160537075","https://openalex.org/W6632893073","https://openalex.org/W6635226537","https://openalex.org/W6678265817","https://openalex.org/W6678318511","https://openalex.org/W6681547555"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"We":[0],"aim":[1],"at":[2,28],"developing":[3],"a":[4,19,24,47,123,161],"singer":[5,25],"robot":[6,26],"capable":[7],"of":[8,86,104,119,132,160,181],"listening":[9,32],"to":[10,33,63,68,110,196],"music":[11,41,193],"with":[12,18],"its":[13,69],"own":[14],"\u00bfears\u00bf":[15],"and":[16,45,96,130,156],"interacting":[17],"human's":[20],"musical":[21,70,88,98,106],"performance.":[22,107],"Such":[23],"requires":[27],"least":[29],"three":[30],"functions:":[31],"the":[34,40,56,61,76,84,93,97,105,117,127,133,137,144,153,158,179,197],"music,":[35],"understanding":[36],"what":[37],"position":[38],"in":[39,83,102,126,152,185],"is":[42,150],"being":[43],"performed,":[44],"generating":[46],"singing":[48],"voice.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"focus":[54],"on":[55,122,143],"second":[57],"function,":[58],"that":[59,146,173],"is,":[60],"capability":[62],"align":[64],"an":[65],"audio":[66,94,154],"signal":[67,95],"score":[71,77,175,186,201],"represented":[72],"symbolically.":[73],"Issues":[74],"underlying":[75],"alignment":[78,176,187],"problem":[79],"are:":[80],"(1)":[81,116],"diversity":[82],"sounds":[85],"various":[87],"instruments,":[89],"(2)":[90,135],"difference":[91],"between":[92],"score,":[99],"(3)":[100,157],"fluctuation":[101],"tempo":[103,167],"Our":[108],"solutions":[109],"these":[111],"issues":[112],"are":[113],"as":[114],"follows:":[115],"design":[118],"features":[120],"based":[121,142],"chroma":[124],"vector":[125],"12-tone":[128],"model":[129],"onset":[131],"sound,":[134],"defining":[136],"rareness":[138],"for":[139,165],"each":[140],"tone":[141,149],"idea":[145],"scarcely":[147],"used":[148],"salient":[151],"signal,":[155],"use":[159],"switching":[162],"Kalman":[163],"filter":[164],"robust":[166],"estimation.":[168],"The":[169],"experimental":[170],"result":[171],"shows":[172],"our":[174],"method":[177],"improves":[178],"average":[180],"cumulative":[182],"absolute":[183],"errors":[184],"by":[188],"29%":[189],"using":[190],"100":[191],"popular":[192],"tunes":[194],"compared":[195],"beat":[198],"tracking":[199],"without":[200],"alignment.":[202]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
