{"id":"https://openalex.org/W2160499613","doi":"https://doi.org/10.1109/icassp.2011.5946371","title":"Polyphonic audio-to-score alignment based on Bayesian Latent Harmonic Allocation Hidden Markov Model","display_name":"Polyphonic audio-to-score alignment based on Bayesian Latent Harmonic Allocation Hidden Markov Model","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2160499613","doi":"https://doi.org/10.1109/icassp.2011.5946371","mag":"2160499613"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"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/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":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, 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":["Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute for Advanced Industrial Science and Technology, Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute for Advanced Industrial Science and Technology, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056563843"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":2.8076,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91586961,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"i","issue":null,"first_page":"185","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9965999722480774,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9908999800682068,"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":0.7398722171783447},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7287794351577759},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6538512110710144},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6202254295349121},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5874626636505127},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5002188682556152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4742128849029541},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.4312340021133423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41493797302246094},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14231368899345398}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398722171783447},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7287794351577759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6538512110710144},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6202254295349121},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5874626636505127},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5002188682556152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4742128849029541},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.4312340021133423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41493797302246094},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14231368899345398},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5946371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.7340","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.7340","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/ICASSP2011-Maezawa.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W16345605","https://openalex.org/W106639881","https://openalex.org/W1496777823","https://openalex.org/W2028306410","https://openalex.org/W2110913111","https://openalex.org/W2115979064","https://openalex.org/W2121224416","https://openalex.org/W2121232083","https://openalex.org/W2128064068","https://openalex.org/W2153331925","https://openalex.org/W2160147944","https://openalex.org/W2186196505","https://openalex.org/W2275238206","https://openalex.org/W2294590576","https://openalex.org/W2294938105","https://openalex.org/W2296201206","https://openalex.org/W2395462034","https://openalex.org/W2397400945","https://openalex.org/W2404688329","https://openalex.org/W2406386391","https://openalex.org/W2885029858","https://openalex.org/W6600679824","https://openalex.org/W6604351559","https://openalex.org/W6678265817","https://openalex.org/W6682222477","https://openalex.org/W6686287241","https://openalex.org/W6694178644","https://openalex.org/W6697095839","https://openalex.org/W6697195199","https://openalex.org/W6697237593","https://openalex.org/W6711855267","https://openalex.org/W6712505711","https://openalex.org/W6713934767","https://openalex.org/W6753762981"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2419138286","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W101156158","https://openalex.org/W2182848507","https://openalex.org/W2387825067","https://openalex.org/W2506414444","https://openalex.org/W4283026649","https://openalex.org/W4378498754"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,9,57,67,77,123,160],"Bayesian":[4,58,68,78],"method":[5,61,91,113,138,157],"for":[6,152],"temporally":[7],"aligning":[8],"music":[10,64,121],"score":[11],"and":[12,31,102],"an":[13],"audio":[14,35],"rendition.":[15,36],"A":[16],"critical":[17],"problem":[18],"in":[19,23,159],"audio-to-score":[20,59],"alignment":[21,60,141],"is":[22,92,114],"dealing":[24],"with":[25,39],"the":[26,34,97,103,110,140],"wide":[27],"variety":[28,124],"of":[29,33,52,74,109,119,122,125],"timbre":[30],"volume":[32,104],"In":[37],"contrast":[38],"existing":[40],"works":[41,118],"that":[42,136],"achieve":[43],"this":[44],"through":[45],"ad-hoc":[46],"feature":[47],"design":[48],"or":[49,155],"careful":[50],"training":[51],"tone":[53,100],"models,":[54],"we":[55],"propose":[56],"by":[62],"modeling":[63],"performance":[65],"as":[66],"Hidden":[69],"Markov":[70],"Model,":[71],"each":[72,107],"state":[73],"which":[75],"emits":[76],"signal":[79],"model":[80,101],"based":[81,148],"on":[82,149],"Latent":[83],"Harmonic":[84],"Allocation.":[85],"After":[86],"attenuating":[87],"reverberation,":[88],"variational":[89],"Bayes":[90],"used":[93],"to":[94,131,144],"iteratively":[95],"adapt":[96],"alignment,":[98],"instrument":[99],"balance":[105],"at":[106],"position":[108],"score.":[111],"The":[112],"evaluated":[115],"using":[116],"sixty":[117],"classical":[120],"instrumentation":[126],"ranging":[127],"from":[128],"solo":[129],"piano":[130],"full":[132],"orchestra.":[133],"We":[134],"verify":[135],"our":[137,156],"improves":[139],"accuracy":[142],"compared":[143],"dynamic":[145],"time":[146],"warping":[147],"chroma":[150],"vector":[151],"orchestral":[153],"music,":[154],"employed":[158],"maximum":[161],"likelihood":[162],"setting.":[163]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
