{"id":"https://openalex.org/W2043406473","doi":"https://doi.org/10.1162/comj_a_00286","title":"Bayesian Audio-to-Score Alignment Based on Joint Inference of Timbre, Volume, Tempo, and Note Onset Timings","display_name":"Bayesian Audio-to-Score Alignment Based on Joint Inference of Timbre, Volume, Tempo, and Note Onset Timings","publication_year":2015,"publication_date":"2015-03-01","ids":{"openalex":"https://openalex.org/W2043406473","doi":"https://doi.org/10.1162/comj_a_00286","mag":"2043406473"},"language":"en","primary_location":{"id":"doi:10.1162/comj_a_00286","is_oa":false,"landing_page_url":"https://doi.org/10.1162/comj_a_00286","pdf_url":null,"source":{"id":"https://openalex.org/S165362224","display_name":"Computer Music Journal","issn_l":"0148-9267","issn":["0148-9267","1531-5169"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Music Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2433/198553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056563843","display_name":"Akira Maezawa","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":"Akira Maezawa","raw_affiliation_strings":["Graduate School of Informatics Department of Intelligence Science and Technology Kyoto University Yoshida-Honmachi Sakyo, Kyoto 606-8501, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics Department of Intelligence Science and Technology Kyoto University Yoshida-Honmachi Sakyo, Kyoto 606-8501, 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 Department of Intelligence Science and Technology Kyoto University Yoshida-Honmachi Sakyo, Kyoto 606-8501, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics Department of Intelligence Science and Technology Kyoto University Yoshida-Honmachi Sakyo, Kyoto 606-8501, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056563843"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":0.579,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67005397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"39","issue":"1","first_page":"74","last_page":"87"},"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":0.9995999932289124,"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":0.9990000128746033,"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/timbre","display_name":"Timbre","score":0.7858301997184753},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5922594666481018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.586592435836792},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5738272070884705},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5595483779907227},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5186014175415039},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5135748386383057},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.47694411873817444},{"id":"https://openalex.org/keywords/pitch","display_name":"Pitch (Music)","score":0.41526538133621216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3683684468269348},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.30347493290901184},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.0799139142036438}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7858301997184753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5922594666481018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.586592435836792},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5738272070884705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5595483779907227},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5186014175415039},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5135748386383057},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.47694411873817444},{"id":"https://openalex.org/C153405242","wikidata":"https://www.wikidata.org/wiki/Q118819","display_name":"Pitch (Music)","level":3,"score":0.41526538133621216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3683684468269348},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.30347493290901184},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0799139142036438},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1162/comj_a_00286","is_oa":false,"landing_page_url":"https://doi.org/10.1162/comj_a_00286","pdf_url":null,"source":{"id":"https://openalex.org/S165362224","display_name":"Computer Music Journal","issn_l":"0148-9267","issn":["0148-9267","1531-5169"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Music Journal","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000156912","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/198553","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":"Computer Music Journal","raw_type":"journal article"},{"id":"pmh:oai:muse.jhu.edu:/article/577853","is_oa":false,"landing_page_url":"https://muse.jhu.edu/article/577853","pdf_url":null,"source":{"id":"https://openalex.org/S4377196299","display_name":"Project Muse (Johns Hopkins University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145311948","host_organization_name":"Johns Hopkins University","host_organization_lineage":["https://openalex.org/I145311948"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000156912","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/198553","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":"Computer Music Journal","raw_type":"journal article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W16345605","https://openalex.org/W106639881","https://openalex.org/W185944909","https://openalex.org/W1510737763","https://openalex.org/W1532844587","https://openalex.org/W1581253957","https://openalex.org/W1807124684","https://openalex.org/W1975710323","https://openalex.org/W2028306410","https://openalex.org/W2033918847","https://openalex.org/W2072183986","https://openalex.org/W2100816929","https://openalex.org/W2108494558","https://openalex.org/W2111007352","https://openalex.org/W2113217465","https://openalex.org/W2121232083","https://openalex.org/W2128064068","https://openalex.org/W2143513973","https://openalex.org/W2144234122","https://openalex.org/W2150308923","https://openalex.org/W2150452896","https://openalex.org/W2153331925","https://openalex.org/W2160147944","https://openalex.org/W2160499613","https://openalex.org/W2275238206","https://openalex.org/W2294590576","https://openalex.org/W2294938105","https://openalex.org/W2296201206","https://openalex.org/W2395462034","https://openalex.org/W2396969863","https://openalex.org/W2397400945","https://openalex.org/W2398141343","https://openalex.org/W2404688329","https://openalex.org/W2406386391","https://openalex.org/W2789784794","https://openalex.org/W2898887637","https://openalex.org/W2982303213","https://openalex.org/W4229982299"],"related_works":["https://openalex.org/W2171508519","https://openalex.org/W4253022192","https://openalex.org/W55541205","https://openalex.org/W2037916898","https://openalex.org/W1985268485","https://openalex.org/W2946308721","https://openalex.org/W1969330155","https://openalex.org/W4253259713","https://openalex.org/W1982918643","https://openalex.org/W1982806387"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"an":[3,8],"offline":[4],"method":[5,21,102],"for":[6],"aligning":[7],"audio":[9,34,106],"signal":[10],"to":[11,31,63,88,103,107],"individual":[12],"instrumental":[13],"parts":[14],"constituting":[15],"a":[16,52,56,76],"musical":[17,65,105],"score.":[18],"The":[19,36],"proposed":[20],"is":[22,45,73,86],"based":[23],"on":[24,75],"fitting":[25],"multiple":[26],"hidden":[27],"semi-Markov":[28],"models":[29],"(HSMMs)":[30],"the":[32,43,69,94,98,101],"observed":[33],"signal.":[35],"emission":[37],"probability":[38,72],"of":[39,42,55,100],"each":[40],"state":[41,70],"HSMM":[44,61],"described":[46],"using":[47],"latent":[48],"harmonic":[49,57],"allocation":[50],"(LHA),":[51],"Bayesian":[53,84],"model":[54],"sound":[58],"mixture.":[59],"Each":[60],"corresponds":[62],"one":[64],"instrument\u2019s":[66],"part,":[67],"and":[68,93,114],"duration":[71],"conditioned":[74],"linear":[77],"dynamics":[78],"system":[79],"(LDS)":[80],"tempo":[81],"model.":[82],"Variational":[83],"inference":[85],"used":[87],"jointly":[89],"infer":[90],"LHA,":[91],"HSMM,":[92],"LDS.":[95],"We":[96],"evaluate":[97],"capability":[99],"align":[104],"its":[108],"score,":[109],"under":[110],"reverberation,":[111],"structural":[112],"variations,":[113],"fluctuations":[115],"in":[116],"onset":[117],"timing":[118],"among":[119],"different":[120],"parts.":[121]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}