{"id":"https://openalex.org/W2160341867","doi":"https://doi.org/10.1186/1687-4722-2012-6","title":"A multimodal tempo and beat-tracking system based on audiovisual information from live guitar performances","display_name":"A multimodal tempo and beat-tracking system based on audiovisual information from live guitar performances","publication_year":2012,"publication_date":"2012-01-20","ids":{"openalex":"https://openalex.org/W2160341867","doi":"https://doi.org/10.1186/1687-4722-2012-6","mag":"2160341867"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2012-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-6","any_repository_has_fulltext":true},"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":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"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/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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Otsuka","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"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/A5110835440","display_name":"Takeshi Mizumoto","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":"Takeshi Mizumoto","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"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/A5054803584","display_name":"Angelica Lim","orcid":"https://orcid.org/0000-0001-9288-0380"},"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":"Angelica Lim","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"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/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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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":["Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5078173393"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.991,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80538185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2012","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/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/T11349","display_name":"Music Technology and Sound Studies","score":0.996399998664856,"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/beat","display_name":"Beat (acoustics)","score":0.7777563333511353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6833057403564453},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5636453628540039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5117437839508057},{"id":"https://openalex.org/keywords/guitar","display_name":"Guitar","score":0.5047003030776978},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.392625629901886},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33338069915771484},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22323864698410034}],"concepts":[{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.7777563333511353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833057403564453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5636453628540039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5117437839508057},{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.5047003030776978},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.392625629901886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33338069915771484},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22323864698410034},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/1687-4722-2012-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000147283","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/187381","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2012-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3236194794","display_name":null,"funder_award_id":"Grant-in-Aid","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7167128334","display_name":null,"funder_award_id":"Grant-in-Aid for Scientific Researc","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7337825077","display_name":null,"funder_award_id":"Grant-in-Aid for Sc","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8759943101","display_name":null,"funder_award_id":"rant-in-Aid for Scientific Research","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G898064477","display_name":null,"funder_award_id":"Grant-in-Aid for Scientific Research (S)","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2160341867.pdf","grobid_xml":"https://content.openalex.org/works/W2160341867.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W22745672","https://openalex.org/W39123374","https://openalex.org/W44483785","https://openalex.org/W1578141458","https://openalex.org/W1600022730","https://openalex.org/W1622620102","https://openalex.org/W1966483388","https://openalex.org/W2024551260","https://openalex.org/W2067191022","https://openalex.org/W2085261163","https://openalex.org/W2091377065","https://openalex.org/W2105653490","https://openalex.org/W2105934661","https://openalex.org/W2108775563","https://openalex.org/W2114640443","https://openalex.org/W2118877769","https://openalex.org/W2122913673","https://openalex.org/W2123523634","https://openalex.org/W2127670691","https://openalex.org/W2130935889","https://openalex.org/W2132084923","https://openalex.org/W2135346934","https://openalex.org/W2140675419","https://openalex.org/W2155764689","https://openalex.org/W2166946988","https://openalex.org/W2503576123"],"related_works":["https://openalex.org/W4220911637","https://openalex.org/W4385984930","https://openalex.org/W4247286973","https://openalex.org/W1990291079","https://openalex.org/W1485923842","https://openalex.org/W3118230952","https://openalex.org/W4252394237","https://openalex.org/W2898671791","https://openalex.org/W3113369605","https://openalex.org/W335404152"],"abstract_inverted_index":{"The":[0,75,98,175],"aim":[1],"of":[2,43,83,108,184,191],"this":[3],"paper":[4],"is":[5,14,29,182],"to":[6,17,31,49,112,133],"improve":[7],"beat-tracking":[8,154,166],"for":[9,21,73],"live":[10,45],"guitar":[11,46,114],"performances.":[12],"Beat-tracking":[13,42],"a":[15,33,44,130,140,145,188,211],"function":[16],"estimate":[18],"musical":[19,23,39],"measurements,":[20],"example":[22],"tempo":[24,54,87],"and":[25,59,86,120,144,171],"phase.":[26],"This":[27],"method":[28,72],"critical":[30],"achieve":[32],"synchronized":[34],"ensemble":[35,201],"performance":[36,47],"such":[37],"as":[38],"robot":[40],"accompaniment.":[41],"has":[48],"deal":[50],"with":[51,64,187,202,210],"three":[52],"challenges:":[53],"fluctuation,":[55],"beat":[56,77,100,141,173],"pattern":[57],"complexity":[58],"environmental":[60],"noise.":[61,97],"To":[62],"cope":[63],"these":[65],"problems,":[66],"we":[67],"devise":[68],"an":[69,200],"audiovisual":[70],"integration":[71],"beat-tracking.":[74],"auditory":[76],"features":[78,101,126],"are":[79,102,127],"estimated":[80,103,125],"in":[81],"terms":[82],"tactus":[84],"(phase)":[85],"(period)":[88],"by":[89,104,158],"Spectro-Temporal":[90],"Pattern":[91],"Matching":[92],"(STPM),":[93],"robust":[94],"against":[95],"stationary":[96],"visual":[99],"tracking":[105],"the":[106,109,113,121,135,156,164,180,195,203,208],"position":[107],"hand":[110],"relative":[111],"using":[115,129],"optical":[116],"flow,":[117],"mean":[118],"shift":[119],"Hough":[122],"transform.":[123],"Both":[124],"integrated":[128],"particle":[131],"filter":[132],"aggregate":[134],"multimodal":[136],"information":[137],"based":[138],"on":[139,161],"location":[142],"model":[143],"hand's":[146],"trajectory":[147],"model.":[148],"Experimental":[149],"results":[150,176],"confirm":[151],"that":[152,179,206],"our":[153],"improves":[155],"F-measure":[157],"8.9":[159],"points":[160],"average":[162],"over":[163],"Murata":[165],"method,":[167],"which":[168],"uses":[169],"STPM":[170],"rule-based":[172],"detection.":[174],"also":[177],"show":[178],"system":[181],"capable":[183],"real-time":[185],"processing":[186],"suppressed":[189],"number":[190],"particles":[192],"while":[193],"preserving":[194],"estimation":[196],"accuracy.":[197],"We":[198],"demonstrate":[199],"humanoid":[204],"HRP-2":[205],"plays":[207],"theremin":[209],"human":[212],"guitarist.":[213]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
