{"id":"https://openalex.org/W2221575906","doi":"https://doi.org/10.1109/iros.2015.7354164","title":"Audio-visual beat tracking based on a state-space model for a music robot dancing with humans","display_name":"Audio-visual beat tracking based on a state-space model for a music robot dancing with humans","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2221575906","doi":"https://doi.org/10.1109/iros.2015.7354164","mag":"2221575906"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2015.7354164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5049476804","display_name":"Misato Ohkita","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":"Misato Ohkita","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"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":"Yoshiaki Bando","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087321595","display_name":"Yukara Ikemiya","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":"Yukara Ikemiya","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"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":"Katsutoshi Itoyama","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"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":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, 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":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"5555","last_page":"5560"},"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":0.9998000264167786,"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":0.9977999925613403,"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":0.7224107384681702},{"id":"https://openalex.org/keywords/beat","display_name":"Beat (acoustics)","score":0.6429068446159363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5360162258148193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5326504111289978},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5098599791526794},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4937206208705902},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43246617913246155},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4191579818725586},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41869550943374634},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2010037899017334},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15968838334083557}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224107384681702},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.6429068446159363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360162258148193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5326504111289978},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5098599791526794},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4937206208705902},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43246617913246155},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4191579818725586},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41869550943374634},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2010037899017334},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15968838334083557},{"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:10.1109/iros.2015.7354164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.6808","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.6808","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/%7Eyoshii/papers/iros-2015-ohkita.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5300062852","display_name":null,"funder_award_id":"24220006","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W96364408","https://openalex.org/W2006048584","https://openalex.org/W2011890278","https://openalex.org/W2024551260","https://openalex.org/W2052872069","https://openalex.org/W2054459540","https://openalex.org/W2069432516","https://openalex.org/W2075384961","https://openalex.org/W2099035325","https://openalex.org/W2105471354","https://openalex.org/W2106803048","https://openalex.org/W2112824765","https://openalex.org/W2114640443","https://openalex.org/W2118305863","https://openalex.org/W2122913673","https://openalex.org/W2123523634","https://openalex.org/W2130935889","https://openalex.org/W2134679199","https://openalex.org/W2160337655","https://openalex.org/W2167455298","https://openalex.org/W2170217103","https://openalex.org/W2994098994","https://openalex.org/W3036781352","https://openalex.org/W6603867583","https://openalex.org/W6677677300","https://openalex.org/W6771357970"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2157165686","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2088690926"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,8],"audio-visual":[4],"beat-tracking":[5,191],"method":[6,120,170],"for":[7,36,176],"entertainment":[9],"robot":[10,47],"that":[11,86,105,166],"can":[12],"dance":[13],"in":[14,42,112,188,193],"synchronization":[15],"with":[16,65],"music":[17,22,28,51,92,130],"and":[18,38,69,109,126,133,146,196],"human":[19,141],"dancers.":[20],"Conventional":[21],"robots":[23],"have":[24],"focused":[25],"on":[26],"either":[27],"audio":[29,52,93,108,131],"signals":[30,53,61,94,132],"or":[31],"dancing":[32,84],"movements":[33,85,138],"of":[34,139,190],"humans":[35],"detecting":[37],"predicting":[39],"beat":[40,79,149],"times":[41,80],"real":[43,82],"time.":[44],"Since":[45],"a":[46,102,113,140,160,172,194],"needs":[48],"to":[49,76],"record":[50],"by":[54,158,184],"using":[55,159,171],"its":[56],"own":[57],"microphones,":[58],"however,":[59],"the":[60,119,147,167],"are":[62,151],"severely":[63],"contaminated":[64],"loud":[66],"environmental":[67],"noise":[68],"reverberant":[70,197],"sounds.":[71],"Moreover,":[72],"it":[73],"is":[74],"difficult":[75],"visually":[77],"detect":[78],"from":[81,129,137,154],"complicated":[83],"exhibit":[87],"weaker":[88],"repetitive":[89],"characteristics":[90],"than":[91],"do.":[95],"To":[96],"solve":[97],"these":[98],"problems,":[99],"we":[100],"propose":[101],"state-space":[103],"model":[104],"integrates":[106],"both":[107],"visual":[110],"information":[111],"probabilistic":[114],"manner.":[115],"At":[116],"each":[117],"frame,":[118],"extracts":[121,134],"acoustic":[122],"features":[123,136,157,179],"(audio":[124],"tempos":[125],"onset":[127],"likelihoods)":[128],"skeleton":[135,178],"dancer.":[142],"The":[143],"current":[144],"tempo":[145],"next":[148],"time":[150],"then":[152],"estimated":[153],"those":[155],"observed":[156],"particle":[161],"filter.":[162],"Experimental":[163],"results":[164],"showed":[165],"proposed":[168],"multi-modal":[169],"depth":[173],"sensor":[174],"(Kinect)":[175],"extracting":[177],"outperformed":[180],"conventional":[181],"mono-modal":[182],"methods":[183],"0.20":[185],"(F":[186],"measure)":[187],"terms":[189],"accuracy":[192],"noisy":[195],"environment.":[198]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
