{"id":"https://openalex.org/W2169784142","doi":"https://doi.org/10.1109/mmsp.2002.1203337","title":"Hidden Markov model for automatic transcription of MIDI signals","display_name":"Hidden Markov model for automatic transcription of MIDI signals","publication_year":2004,"publication_date":"2004-01-23","ids":{"openalex":"https://openalex.org/W2169784142","doi":"https://doi.org/10.1109/mmsp.2002.1203337","mag":"2169784142"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2002.1203337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2002.1203337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE Workshop on Multimedia Signal Processing.","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://era.ed.ac.uk/bitstream/1842/961/1/Takeda.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048355992","display_name":"Haruto Takeda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"H. Takeda","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Bunkyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102863896","display_name":"Noriyuki Saito","orcid":"https://orcid.org/0000-0001-6124-4648"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"N. Saito","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Bunkyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074474640","display_name":"Takashi \u00d4tsuki","orcid":"https://orcid.org/0000-0002-0075-510X"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Otsuki","raw_affiliation_strings":["Graduate School of Information Science, Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066137210","display_name":"Masaaki Nakai","orcid":"https://orcid.org/0000-0002-5307-2230"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Nakai","raw_affiliation_strings":["Graduate School of Information Science, Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062792381","display_name":"Hiroshi Shimodaira","orcid":"https://orcid.org/0000-0001-8956-2816"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Shimodaira","raw_affiliation_strings":["Graduate School of Information Science, Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Japan Advanced Institute of Science and Technology, Tatsunokuchi, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003450550","display_name":"Shigeki Sagayama","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S. Sagayama","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Bunkyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Bunkyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048355992"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.4285,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.83298517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"428","last_page":"431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919000267982483,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.902809739112854},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.8944915533065796},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.7862231731414795},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6721352338790894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6584355235099792},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5690752267837524},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5403814911842346},{"id":"https://openalex.org/keywords/forward-algorithm","display_name":"Forward algorithm","score":0.4856458902359009},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4495396614074707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43526941537857056},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.43459415435791016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3945148289203644},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.35954466462135315},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3488740921020508},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.2525595426559448},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20760083198547363}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.902809739112854},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.8944915533065796},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.7862231731414795},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6721352338790894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6584355235099792},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5690752267837524},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5403814911842346},{"id":"https://openalex.org/C196455857","wikidata":"https://www.wikidata.org/wiki/Q5473264","display_name":"Forward algorithm","level":5,"score":0.4856458902359009},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4495396614074707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43526941537857056},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.43459415435791016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3945148289203644},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.35954466462135315},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3488740921020508},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.2525595426559448},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20760083198547363},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/mmsp.2002.1203337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2002.1203337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE Workshop on Multimedia Signal Processing.","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/961","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/961","pdf_url":"https://era.ed.ac.uk/bitstream/1842/961/1/Takeda.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.3831","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.3831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hil.t.u-tokyo.ac.jp/~lab/publications/2002/Takeda2002MMSP12.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/961","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/961","pdf_url":"https://era.ed.ac.uk/bitstream/1842/961/1/Takeda.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2169784142.pdf","grobid_xml":"https://content.openalex.org/works/W2169784142.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1576420969","https://openalex.org/W2113219752","https://openalex.org/W2120053230","https://openalex.org/W2942471022","https://openalex.org/W4210890610","https://openalex.org/W6633431331","https://openalex.org/W6762376497"],"related_works":["https://openalex.org/W2161328464","https://openalex.org/W2382132287","https://openalex.org/W2076166534","https://openalex.org/W3044198794","https://openalex.org/W2100295236","https://openalex.org/W2379938888","https://openalex.org/W2593596363","https://openalex.org/W2116722627","https://openalex.org/W2096837052","https://openalex.org/W2143650221"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,29,52,60,90,114],"Hidden":[4],"Markov":[5],"Model":[6],"(HMM)-based":[7],"method":[8],"of":[9,12,19,28,32,55,66,72,80,93,105,121],"automatic":[10],"transcription":[11],"MIDI":[13],"(Musical":[14],"Instrument":[15],"Digital":[16],"Interface)":[17],"signals":[18],"performed":[20],"music.":[21],"The":[22,83],"problem":[23,92],"is":[24,76,86],"formulated":[25],"as":[26],"recognition":[27,49],"given":[30],"sequence":[31,43,75],"fluctuating":[33],"note":[34,42,57,74],"durations":[35,58,104,120],"to":[36,89,112],"find":[37],"the":[38,45,68,73,122,127],"most":[39],"likely":[40],"intended":[41],"utilizing":[44],"modern":[46],"continuous":[47],"speech":[48],"technique.":[50],"Combining":[51],"stochastic":[53,61],"model":[54],"deviating":[56],"and":[59,100,124],"grammar":[62],"representing":[63,117],"possible":[64],"sequences":[65],"notes,":[67],"maximum":[69],"likelihood":[70],"estimate":[71],"searched":[77],"in":[78,126],"terms":[79],"Viterbi":[81],"algorithm.":[82],"same":[84,128],"principle":[85],"successfully":[87],"applied":[88],"joint":[91],"bar":[94],"line":[95],"allocation,":[96],"time":[97],"measure":[98],"recognition,":[99],"tempo":[101],"estimation.":[102],"Finally,":[103],"consecutive":[106],"/spl":[107],"eta/n":[108],"notes":[109,123],"are":[110,137],"combined":[111],"form":[113],"\"rhythm":[115],"vector\"":[116],"tempo-free":[118],"relative":[119],"treated":[125],"framework.":[129],"Significant":[130],"improvements":[131],"compared":[132],"with":[133],"conventional":[134],"\"quantization\"":[135],"techniques":[136],"shown.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}