{"id":"https://openalex.org/W2140648590","doi":"https://doi.org/10.1109/icassp.2012.6287916","title":"Bayesian nonparametric music parser","display_name":"Bayesian nonparametric music parser","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2140648590","doi":"https://doi.org/10.1109/icassp.2012.6287916","mag":"2140648590"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5103244481","display_name":"Masahiro Nakano","orcid":"https://orcid.org/0009-0008-9378-0099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masahiro Nakano","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062509967","display_name":"Yasunori Ohishi","orcid":"https://orcid.org/0000-0002-7856-248X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasunori Ohishi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043759410","display_name":"Ryo Mukai","orcid":"https://orcid.org/0000-0003-1796-9232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryo Mukai","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061465935","display_name":"Kunio Kashino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kunio Kashino","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Atsugi, Kanagawa, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4861,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86137988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"461","last_page":"464"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.989300012588501,"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/computer-science","display_name":"Computer science","score":0.7588374614715576},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6334598660469055},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.49651437997817993},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48892298340797424},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4746423661708832},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.46644020080566406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.462586373090744},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43047910928726196},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40968501567840576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4086795449256897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.345392644405365},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.28247255086898804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588374614715576},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6334598660469055},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.49651437997817993},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48892298340797424},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4746423661708832},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.46644020080566406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.462586373090744},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43047910928726196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40968501567840576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4086795449256897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.345392644405365},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.28247255086898804},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6287916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1519655822","https://openalex.org/W2008565517","https://openalex.org/W2023723978","https://openalex.org/W2101998432","https://openalex.org/W2113526703","https://openalex.org/W2117155634","https://openalex.org/W2118942461","https://openalex.org/W2157381218","https://openalex.org/W2164151151","https://openalex.org/W2185743839","https://openalex.org/W2295947483","https://openalex.org/W2952104818","https://openalex.org/W6683257438","https://openalex.org/W6684410512","https://openalex.org/W6696955691"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,20,36,103,126,142],"novel":[4],"representation":[5,34,75,85],"of":[6,66,171],"music":[7,14,84],"that":[8,22],"can":[9],"be":[10],"used":[11],"for":[12,146],"similarity-based":[13],"information":[15],"retrieval,":[16],"and":[17,47,54,63,112,118,141,160],"also":[18],"presents":[19],"method":[21],"converts":[23],"an":[24,134],"input":[25],"polyphonic":[26],"audio":[27],"signal":[28],"to":[29,51,83,94],"the":[30,44,48,52,60,64,80,107,120,169,172],"proposed":[31,108,173],"representation.":[32],"The":[33,165],"involves":[35],"2-dimensional":[37,136],"tree":[38],"structure,":[39],"where":[40],"each":[41],"node":[42],"encodes":[43],"musical":[45],"note":[46,88,99,110],"dimensions":[49],"correspond":[50],"time":[53],"simultaneous":[55,67],"multiple":[56],"notes,":[57],"respectively.":[58],"Since":[59],"temporal":[61],"structure":[62,95,113],"synchrony":[65],"events":[68],"are":[69],"both":[70],"essential":[71],"in":[72],"music,":[73],"our":[74],"reflects":[76],"them":[77],"explicitly.":[78],"In":[79,106],"conventional":[81],"approaches":[82],"from":[86],"audio,":[87],"extraction":[89,100,111],"is":[90,115,123,163],"usually":[91],"performed":[92,116],"prior":[93],"analysis,":[96],"but":[97],"accurate":[98],"has":[101],"been":[102],"difficult":[104],"task.":[105],"method,":[109],"estimation":[114],"simultaneously":[117],"thus":[119],"optimal":[121],"solution":[122],"obtained":[124],"with":[125],"unified":[127],"inference":[128,151],"procedure.":[129],"That":[130],"is,":[131],"we":[132],"propose":[133],"extended":[135],"infinite":[137],"probabilistic":[138],"context-free":[139],"grammar":[140],"sparse":[143],"factor":[144],"model":[145],"spectrogram":[147],"analysis.":[148],"An":[149],"efficient":[150],"algorithm,":[152],"based":[153],"on":[154],"Markov":[155],"chain":[156],"Monte":[157],"Carlo":[158],"sampling":[159],"dynamic":[161],"programming,":[162],"presented.":[164],"experimental":[166],"results":[167],"show":[168],"effectiveness":[170],"approach.":[174]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}