{"id":"https://openalex.org/W2036403449","doi":"https://doi.org/10.1109/isspa.2003.1224833","title":"Musical instrument recognition using ICA-based transform of features and discriminatively trained HMMs","display_name":"Musical instrument recognition using ICA-based transform of features and discriminatively trained HMMs","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2036403449","doi":"https://doi.org/10.1109/isspa.2003.1224833","mag":"2036403449"},"language":"en","primary_location":{"id":"doi:10.1109/isspa.2003.1224833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2003.1224833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","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/A5076376566","display_name":"Antti Eronen","orcid":null},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"A. Eronen","raw_affiliation_strings":["Institute of Signal Proceessing, Tampere University of Technology, Tampere, Finland","[Inst. of Signal Process., Tampere Univ. of Technol., Finland]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Signal Proceessing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Inst. of Signal Process., Tampere Univ. of Technol., Finland]","institution_ids":["https://openalex.org/I150589677"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5076376566"],"corresponding_institution_ids":["https://openalex.org/I150589677","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":5.3356,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.96570244,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"136 vol.2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","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/T11447","display_name":"Blind Source Separation Techniques","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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.9968000054359436,"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/discriminative-model","display_name":"Discriminative model","score":0.8731032013893127},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7821689248085022},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6984348893165588},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6681705713272095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.665523111820221},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6494422554969788},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6035336852073669},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5628765821456909},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4757658839225769},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.4701012969017029},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4529038369655609},{"id":"https://openalex.org/keywords/independent-component-analysis","display_name":"Independent component analysis","score":0.4232219457626343},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3096001148223877},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16429701447486877},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09805876016616821},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0792505145072937}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8731032013893127},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7821689248085022},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6984348893165588},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6681705713272095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.665523111820221},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6494422554969788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6035336852073669},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5628765821456909},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4757658839225769},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.4701012969017029},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4529038369655609},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.4232219457626343},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3096001148223877},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16429701447486877},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09805876016616821},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0792505145072937},{"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},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isspa.2003.1224833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspa.2003.1224833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.65.6405","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.65.6405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/sgn/arg/music/eronen/eronen_isspa03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1600663531","https://openalex.org/W1863372652","https://openalex.org/W2012745928","https://openalex.org/W2056024012","https://openalex.org/W2141224535","https://openalex.org/W2155413697","https://openalex.org/W2163183797","https://openalex.org/W2171990114"],"related_works":["https://openalex.org/W4252230435","https://openalex.org/W2965546495","https://openalex.org/W2121429698","https://openalex.org/W2182042810","https://openalex.org/W4389116644","https://openalex.org/W2990982991","https://openalex.org/W2167155152","https://openalex.org/W2606551632","https://openalex.org/W2921344368","https://openalex.org/W2783599290"],"abstract_inverted_index":{"In":[0],"this":[1,51],"paper,":[2],"we":[3],"describe":[4,21],"a":[5,22,59],"system":[6,24],"for":[7],"the":[8,48,56,88,92],"recognition":[9,78,89],"of":[10,50,73,91,98,102],"musical":[11],"instruments":[12],"from":[13],"isolated":[14,100],"notes":[15,101],"or":[16],"drum":[17,108],"samples.":[18],"We":[19],"first":[20,32],"baseline":[23,52],"that":[25],"uses":[26],"mel-frequency":[27],"cepstral":[28],"coefficients":[29],"and":[30,36,106],"their":[31],"derivatives":[33],"as":[34],"features,":[35],"continuous-density":[37],"hidden":[38],"Markov":[39],"models":[40],"(HMMs).":[41],"Two":[42],"improvements":[43],"are":[44],"proposed":[45],"to":[46,58,85],"increase":[47],"performance":[49],"system.":[53,93],"First,":[54],"transforming":[55],"features":[57],"base":[60],"with":[61],"maximal":[62],"statistical":[63],"independence":[64],"using":[65],"independent":[66],"component":[67],"analysis":[68],"can":[69],"give":[70],"an":[71],"improvement":[72],"9":[74],"percentage":[75],"points":[76],"in":[77],"accuracy.":[79],"Secondly,":[80],"discriminative":[81],"training":[82],"is":[83],"shown":[84],"further":[86],"improve":[87],"accuracy":[90],"The":[94],"evaluation":[95],"material":[96],"consists":[97],"5895":[99],"Western":[103],"orchestral":[104],"instruments,":[105],"1798":[107],"hits.":[109]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-26T08:31:28.666265","created_date":"2025-10-10T00:00:00"}