{"id":"https://openalex.org/W2097492332","doi":"https://doi.org/10.1109/icassp.2011.5946319","title":"Multipitch estimation by joint modeling of harmonic and transient sounds","display_name":"Multipitch estimation by joint modeling of harmonic and transient sounds","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2097492332","doi":"https://doi.org/10.1109/icassp.2011.5946319","mag":"2097492332"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946319","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/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":["University of Tokyo, Tokoyo, Japan","The University of Tokyo, 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokoyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"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":["Centre de Rennes-Bretagne Atlantique, INRIA, Rennes, France","INRIA, Centre de Rennes - Bretagne Atlantique, 35042Cedex, France"],"affiliations":[{"raw_affiliation_string":"Centre de Rennes-Bretagne Atlantique, INRIA, Rennes, France","institution_ids":["https://openalex.org/I4210133778","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"INRIA, Centre de Rennes - Bretagne Atlantique, 35042Cedex, 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":"Stanislaw Andrzej Raczynski","raw_affiliation_strings":["University of Tokyo, Tokoyo, Japan","The University of Tokyo, 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokoyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100814456","display_name":"Takuya Nishimoto","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":"Takuya Nishimoto","raw_affiliation_strings":["University of Tokyo, Tokoyo, Japan","The University of Tokyo, 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokoyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"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/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":"Nobutaka Ono","raw_affiliation_strings":["University of Tokyo, Tokoyo, Japan","The University of Tokyo, 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokoyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"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":["University of Tokyo, Tokoyo, Japan","The University of Tokyo, 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokoyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"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":3.4315,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93148546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"28"},"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":0.9997000098228455,"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":0.9962999820709229,"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":0.6276305317878723},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.6027938723564148},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5879932045936584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5370376110076904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5328313112258911},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5201135873794556},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4854896366596222},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.46824395656585693},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.4649098813533783},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4623587727546692},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.45137423276901245},{"id":"https://openalex.org/keywords/spectral-density-estimation","display_name":"Spectral density estimation","score":0.44162479043006897},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.4270455241203308},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.41313862800598145},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.4103175699710846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3099267780780792},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.267769455909729},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25113189220428467},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.18882113695144653},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.16748255491256714},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12711963057518005},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.1154024600982666},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11086243391036987},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10246112942695618}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6276305317878723},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.6027938723564148},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5879932045936584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5370376110076904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5328313112258911},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5201135873794556},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4854896366596222},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.46824395656585693},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.4649098813533783},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4623587727546692},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.45137423276901245},{"id":"https://openalex.org/C30049272","wikidata":"https://www.wikidata.org/wiki/Q6555326","display_name":"Spectral density estimation","level":3,"score":0.44162479043006897},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4270455241203308},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.41313862800598145},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.4103175699710846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3099267780780792},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.267769455909729},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25113189220428467},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.18882113695144653},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.16748255491256714},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12711963057518005},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.1154024600982666},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11086243391036987},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10246112942695618},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2011.5946319","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946319","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:10.1.1.220.4178","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.220.4178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/56/71/75/PDF/wu_ICASSP11.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00567175v1","is_oa":false,"landing_page_url":"https://inria.hal.science/inria-00567175","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":"2011 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), May 2011, Prague, Czech Republic. pp.25 - 28","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1519655822","https://openalex.org/W1984544290","https://openalex.org/W1999439604","https://openalex.org/W2023800933","https://openalex.org/W2026502181","https://openalex.org/W2096482524","https://openalex.org/W2119599673","https://openalex.org/W2125722442","https://openalex.org/W2144414181","https://openalex.org/W2149095746","https://openalex.org/W2155208345","https://openalex.org/W2400942170"],"related_works":["https://openalex.org/W2473373438","https://openalex.org/W2368486525","https://openalex.org/W2077224612","https://openalex.org/W2153481672","https://openalex.org/W2153238387","https://openalex.org/W4312864369","https://openalex.org/W84255947","https://openalex.org/W2014842417","https://openalex.org/W2891133681","https://openalex.org/W2061347451"],"abstract_inverted_index":{"Multipitch":[0],"estimation":[1,109],"techniques":[2],"are":[3],"widely":[4],"used":[5],"for":[6,104],"music":[7],"transcription":[8],"and":[9,89,101,112],"acquisition":[10],"of":[11,33,73,86,94,107],"musical":[12],"data":[13],"from":[14],"digital":[15],"signals.":[16],"In":[17],"this":[18,87],"paper,":[19],"we":[20],"propose":[21],"a":[22,49],"flexible":[23],"harmonic":[24,66],"temporal":[25],"timbre":[26],"model":[27,58,88],"to":[28,61,82],"decompose":[29],"the":[30,34,37,56,65,70,84,91,95,105],"spectral":[31],"energy":[32],"signal":[35],"in":[36],"time-frequency":[38],"domain":[39],"into":[40],"individual":[41],"pitched":[42],"notes.":[43],"Each":[44],"note":[45],"is":[46,59],"modeled":[47],"with":[48],"2-dimensional":[50],"Gaussian":[51],"mixture.":[52],"Unlike":[53],"previous":[54],"approaches,":[55],"proposed":[57,96],"able":[60],"represent":[62],"not":[63],"only":[64],"partials":[67],"but":[68],"also":[69],"inharmonic":[71],"attack":[72],"each":[74],"note.":[75],"We":[76],"derive":[77],"an":[78],"Expectation-Maximization":[79],"(EM)":[80],"algorithm":[81,97,100,103],"estimate":[83],"parameters":[85],"illustrate":[90],"higher":[92],"performance":[93],"than":[98],"NMF":[99],"HTC":[102],"task":[106],"multipitch":[108],"over":[110],"synthetic":[111],"real-world":[113],"data.":[114]},"counts_by_year":[{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}