{"id":"https://openalex.org/W2104484487","doi":"https://doi.org/10.1109/jstsp.2011.2158064","title":"Polyphonic Pitch Estimation and Instrument Identification by Joint Modeling of Sustained and Attack Sounds","display_name":"Polyphonic Pitch Estimation and Instrument Identification by Joint Modeling of Sustained and Attack Sounds","publication_year":2011,"publication_date":"2011-06-07","ids":{"openalex":"https://openalex.org/W2104484487","doi":"https://doi.org/10.1109/jstsp.2011.2158064","mag":"2104484487"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2011.2158064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2011.2158064","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5100779080","display_name":"Jun Wu","orcid":"https://orcid.org/0000-0002-6325-8418"},"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":"Jun Wu","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","Grad School of Information Sci. and Tech., Univ of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Grad School of Information Sci. and Tech., Univ of Tokyo, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065635001","display_name":"Emmanuel Vincent","orcid":"https://orcid.org/0000-0002-0183-7289"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210133778","display_name":"Inria Rennes - Bretagne Atlantique Research Centre","ror":"https://ror.org/04040yw90","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210133778"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["INRIA, Centre de Rennes-Bretagne Atlantique, Rennes Cedex, France","[INRIA Centre de Rennes Bretagne Atlantique, Rennes, France]"],"affiliations":[{"raw_affiliation_string":"INRIA, Centre de Rennes-Bretagne Atlantique, Rennes Cedex, France","institution_ids":["https://openalex.org/I4210133778"]},{"raw_affiliation_string":"[INRIA Centre de Rennes Bretagne Atlantique, Rennes, France]","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026391344","display_name":"Stanis\u0142aw Raczy\u0144ski","orcid":"https://orcid.org/0000-0003-1501-4205"},"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":"Stanis\u0142aw Andrzej Raczynski","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","Grad School of Information Sci. and Tech., Univ of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Grad School of Information Sci. and Tech., Univ of Tokyo, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100814456","display_name":"Takuya Nishimoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuya Nishimoto","raw_affiliation_strings":["Olarbee Japan, Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Olarbee Japan, Hiroshima, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Principles of Informatics Research Division, The National Institute of Informatics, Tokyo, Japan","Principles of Inf. Res. Div., Nat. Inst. of Inf., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Principles of Informatics Research Division, The National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"Principles of Inf. Res. Div., Nat. Inst. of Inf., Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"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":"Shigeki Sagayama","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","Grad School of Information Sci. and Tech., Univ of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Grad School of Information Sci. and Tech., Univ of Tokyo, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100779080"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.8062,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.9124439,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":"6","first_page":"1124","last_page":"1132"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9969000220298767,"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":0.9965000152587891,"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/timbre","display_name":"Timbre","score":0.6705973148345947},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6643304228782654},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6578649878501892},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6383376121520996},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.55572509765625},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.524871289730072},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5136327147483826},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4953135550022125},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4758284389972687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4693525731563568},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.46686434745788574},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.45956331491470337},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4377244710922241},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.4241478443145752},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.27276718616485596},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.14674466848373413}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6705973148345947},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6643304228782654},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6578649878501892},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6383376121520996},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.55572509765625},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.524871289730072},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5136327147483826},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4953135550022125},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4758284389972687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4693525731563568},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.46686434745788574},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.45956331491470337},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4377244710922241},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.4241478443145752},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.27276718616485596},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.14674466848373413},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2011.2158064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2011.2158064","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:inria-00594965v2","is_oa":false,"landing_page_url":"https://inria.hal.science/inria-00594965","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing, 2011, 5 (6), pp.1124-1132","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W66707721","https://openalex.org/W1494331858","https://openalex.org/W1519655822","https://openalex.org/W1584908455","https://openalex.org/W1780815862","https://openalex.org/W1981374696","https://openalex.org/W1984544290","https://openalex.org/W1999439604","https://openalex.org/W2023800933","https://openalex.org/W2026502181","https://openalex.org/W2028306410","https://openalex.org/W2029049232","https://openalex.org/W2031300154","https://openalex.org/W2049633694","https://openalex.org/W2052384514","https://openalex.org/W2096482524","https://openalex.org/W2100050692","https://openalex.org/W2113475414","https://openalex.org/W2115343003","https://openalex.org/W2119599673","https://openalex.org/W2124485076","https://openalex.org/W2125722442","https://openalex.org/W2139318943","https://openalex.org/W2144414181","https://openalex.org/W2149095746","https://openalex.org/W2155208345","https://openalex.org/W2165733362","https://openalex.org/W2324058538","https://openalex.org/W2400942170","https://openalex.org/W2402674073","https://openalex.org/W6602724556","https://openalex.org/W6629404854","https://openalex.org/W6635119349","https://openalex.org/W6638171375","https://openalex.org/W6677483676","https://openalex.org/W6712418219","https://openalex.org/W6713147047"],"related_works":["https://openalex.org/W1481643945","https://openalex.org/W2186947763","https://openalex.org/W2153275212","https://openalex.org/W2008642382","https://openalex.org/W3186846710","https://openalex.org/W2347227645","https://openalex.org/W1940741777","https://openalex.org/W2738531665","https://openalex.org/W2283125477","https://openalex.org/W2402674073"],"abstract_inverted_index":{"Polyphonic":[0],"pitch":[1,80],"estimation":[2],"and":[3,44,81,96],"musical":[4],"instrument":[5,111],"identification":[6],"are":[7],"some":[8],"of":[9,17,30,40,48,56,67,84,132,151],"the":[10,15,28,41,45,54,64,68,79,82,85,94,97,106,149],"most":[11],"challenging":[12],"tasks":[13],"in":[14],"field":[16],"music":[18,140],"information":[19],"retrieval":[20],"(MIR).":[21],"While":[22],"existing":[23],"approaches":[24,146],"have":[25],"focused":[26],"on":[27,130,148],"modeling":[29,150],"harmonic":[31,42,95,152],"partials,":[32],"we":[33],"design":[34],"a":[35,122],"joint":[36],"Gaussian":[37],"mixture":[38],"model":[39,52,108],"partials":[43,153],"inharmonic":[46],"attack":[47,69,98],"each":[49,57,114],"note.":[50],"This":[51],"encodes":[53],"power":[55],"partial":[58],"over":[59,105,144],"time":[60],"as":[61,63,135,137],"well":[62,136],"spectral":[65],"envelope":[66],"part.":[70],"We":[71,87],"derive":[72],"an":[73],"expectation-maximization":[74],"(EM)":[75],"algorithm":[76],"to":[77],"estimate":[78],"parameters":[83],"notes.":[86],"then":[88],"extract":[89],"timbre":[90],"features":[91],"both":[92],"from":[93],"part":[99],"via":[100],"principal":[101],"component":[102],"analysis":[103],"(PCA)":[104],"estimated":[107,115],"parameters.":[109],"Musical":[110],"recognition":[112],"for":[113],"note":[116],"is":[117],"finally":[118],"carried":[119],"out":[120],"with":[121],"support":[123],"vector":[124],"machine":[125],"(SVM)":[126],"classifier.":[127],"Experiments":[128],"conducted":[129],"mixtures":[131],"isolated":[133],"notes":[134],"real-world":[138],"polyphonic":[139],"show":[141],"higher":[142],"accuracy":[143],"state-of-the-art":[145],"based":[147],"only.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}