{"id":"https://openalex.org/W2116033347","doi":"https://doi.org/10.1109/icassp.2009.4959548","title":"Polyphonic musical instrument recognition based on a dynamic model of the spectral envelope","display_name":"Polyphonic musical instrument recognition based on a dynamic model of the spectral envelope","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2116033347","doi":"https://doi.org/10.1109/icassp.2009.4959548","mag":"2116033347"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5018307087","display_name":"Juan Jos\u00e9 Burred","orcid":"https://orcid.org/0000-0001-9755-4162"},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Juan Jose Burred","raw_affiliation_strings":["Analysis/Synthesis Team, IRCAM-CNRS-STMS, Paris, France","Analysis/Synthesis Team, IRCAM - CNRS STMS, 75004 Paris, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Analysis/Synthesis Team, IRCAM-CNRS-STMS, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Analysis/Synthesis Team, IRCAM - CNRS STMS, 75004 Paris, France#TAB#","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108509054","display_name":"Axel R\u00f6bel","orcid":null},"institutions":[{"id":"https://openalex.org/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Axel Robel","raw_affiliation_strings":["Analysis/Synthesis Team, IRCAM-CNRS-STMS, Paris, France","Analysis/Synthesis Team, IRCAM - CNRS STMS, 75004 Paris, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Analysis/Synthesis Team, IRCAM-CNRS-STMS, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Analysis/Synthesis Team, IRCAM - CNRS STMS, 75004 Paris, France#TAB#","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113970295","display_name":"Thomas Sikora","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Sikora","raw_affiliation_strings":["Communication Systems Group, Technical University Berlin, Berlin, Germany","Communication Systems Group, Technical University of Berlin, 10587, Germany"],"affiliations":[{"raw_affiliation_string":"Communication Systems Group, Technical University Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Communication Systems Group, Technical University of Berlin, 10587, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018307087"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I35345632","https://openalex.org/I4389425508"],"apc_list":null,"apc_paid":null,"fwci":2.1148,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.87133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"173","last_page":"176"},"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":0.9983999729156494,"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":0.9959999918937683,"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":0.7285522222518921},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7155447006225586},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.6920278668403625},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6901274919509888},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6556965112686157},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6217154264450073},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.560382604598999},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5434314608573914},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5149989128112793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4732316732406616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4694119393825531},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4683643579483032},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4504030644893646},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43688151240348816},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.41380929946899414},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3504435420036316},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.28965651988983154},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14525750279426575},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11231842637062073},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07958608865737915},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07473048567771912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285522222518921},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7155447006225586},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.6920278668403625},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6901274919509888},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6556965112686157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6217154264450073},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.560382604598999},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5434314608573914},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5149989128112793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4732316732406616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4694119393825531},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4683643579483032},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4504030644893646},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43688151240348816},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.41380929946899414},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3504435420036316},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.28965651988983154},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14525750279426575},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11231842637062073},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07958608865737915},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07473048567771912},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.1109/icassp.2009.4959548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1607142029","https://openalex.org/W2103978280","https://openalex.org/W2169905519","https://openalex.org/W2402007405","https://openalex.org/W2738531665","https://openalex.org/W6636203886","https://openalex.org/W6713032922","https://openalex.org/W6741770958"],"related_works":["https://openalex.org/W2066980424","https://openalex.org/W2916760817","https://openalex.org/W3108094971","https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4243888788","https://openalex.org/W2100375615"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,17,51,66,79],"new":[3],"method":[4],"for":[5,22],"detecting":[6],"the":[7,58,62],"musical":[8],"instruments":[9],"that":[10],"are":[11,88],"present":[12],"in":[13],"single-channel":[14],"mixtures.":[15],"Such":[16],"task":[18],"is":[19,33,72],"of":[20,53,61,65,69,82,86],"interest":[21],"audio":[23],"and":[24,28,43],"multimedia":[25],"content":[26],"analysis":[27],"indexing":[29],"applications.":[30],"The":[31],"approach":[32],"based":[34,73],"on":[35,74],"grouping":[36],"sinusoidal":[37],"trajectories":[38],"according":[39],"to":[40,92],"common":[41],"onsets,":[42],"comparing":[44],"each":[45],"group's":[46],"overall":[47],"amplitude":[48],"evolution":[49,60],"with":[50,90],"set":[52,68],"pre-trained":[54],"probabilistic":[55,80],"templates":[56],"describing":[57],"temporal":[59],"spectral":[63],"envelopes":[64],"given":[67],"instruments.":[70],"Classification":[71],"either":[75],"an":[76],"Euclidean":[77],"or":[78],"definition":[81],"timbral":[83],"similarity,":[84],"both":[85],"which":[87],"compared":[89],"respect":[91],"detection":[93],"accuracy.":[94]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
