{"id":"https://openalex.org/W2155955521","doi":"https://doi.org/10.1109/icassp.2009.4959974","title":"Making chroma features more robust to timbre changes","display_name":"Making chroma features more robust to timbre changes","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2155955521","doi":"https://doi.org/10.1109/icassp.2009.4959974","mag":"2155955521"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959974","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/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Meinard Muller","raw_affiliation_strings":["Cluster of Excellence on Multimodal Computing and Interaction (MMCI), University of Saarland, Saarbruecken, Germany"],"affiliations":[{"raw_affiliation_string":"Cluster of Excellence on Multimodal Computing and Interaction (MMCI), University of Saarland, Saarbruecken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001413512","display_name":"Sebastian Ewert","orcid":"https://orcid.org/0000-0002-0718-0476"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Ewert","raw_affiliation_strings":["Rheinische Friedrich-Wilhelms-Universitat Bonn, Bonn, Nordrhein-Westfalen, DE"],"affiliations":[{"raw_affiliation_string":"Rheinische Friedrich-Wilhelms-Universitat Bonn, Bonn, Nordrhein-Westfalen, DE","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111953865","display_name":"Sebastian Kreuzer","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Kreuzer","raw_affiliation_strings":["Informatik III, Universit\u00e4t Bonn, Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Informatik III, Universit\u00e4t Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109881851"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":3.9248,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.93925327,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1877","last_page":"1880"},"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.9573864936828613},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7585954666137695},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7413573861122131},{"id":"https://openalex.org/keywords/octave","display_name":"Octave (electronics)","score":0.7231786847114563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.624485433101654},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5719400644302368},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45093899965286255},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4338313043117523},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38419124484062195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36911094188690186},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35906320810317993},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.21770471334457397},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2155291736125946},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.19760003685951233}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9573864936828613},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7585954666137695},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7413573861122131},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.7231786847114563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.624485433101654},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5719400644302368},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45093899965286255},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4338313043117523},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38419124484062195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36911094188690186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35906320810317993},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.21770471334457397},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2155291736125946},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.19760003685951233},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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":4,"locations":[{"id":"doi:10.1109/icassp.2009.4959974","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959974","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.981","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mpi-inf.mpg.de/~mmueller/publications/2009_MuellerEwertKreuzer_ChromaFeaturesRobust_ICASSP.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:520464","is_oa":false,"landing_page_url":"http://edoc.mpg.de/520464","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, 1869-1872 (2009)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1324306","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000F-19B9-3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W152909648","https://openalex.org/W170732776","https://openalex.org/W2107048425","https://openalex.org/W2132857561","https://openalex.org/W2137319814","https://openalex.org/W2139107403","https://openalex.org/W2154473523","https://openalex.org/W6600593648","https://openalex.org/W6606150254"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2990982991","https://openalex.org/W4312238237","https://openalex.org/W4292658355","https://openalex.org/W2160011803","https://openalex.org/W4317770561","https://openalex.org/W1512398020","https://openalex.org/W1999395714","https://openalex.org/W3047703615","https://openalex.org/W4367145137"],"abstract_inverted_index":{"Chroma-based":[0],"audio":[1],"features":[2,24,46,128],"are":[3,77],"a":[4,20,26,40,100,105,132],"well-established":[5],"tool":[6],"for":[7,43],"analyzing":[8],"and":[9,54,92],"comparing":[10],"music":[11],"data.":[12],"By":[13],"identifying":[14],"spectral":[15],"components":[16],"that":[17,70,124],"differ":[18],"by":[19],"musical":[21],"octave,":[22],"chroma":[23,45,118,127],"show":[25,123],"high":[27],"degree":[28],"of":[29,84,104],"invariance":[30],"to":[31,50,80,110],"variations":[32],"in":[33,52],"timbre.":[34,81],"In":[35],"this":[36],"paper,":[37],"we":[38,89],"describe":[39],"novel":[41],"procedure":[42],"making":[44],"even":[47],"more":[48],"robust":[49],"changes":[51],"timbre":[53,136],"instrumentation":[55],"while":[56],"keeping":[57,85],"their":[58],"discriminative":[59],"power.":[60],"Our":[61,120],"idea":[62],"is":[63],"based":[64],"on":[65],"the":[66,71,86,95,112,116,125],"generally":[67],"accepted":[68],"observation":[69],"lower":[72,87],"mel-frequency":[73],"cepstral":[74],"coefficients":[75,114],"(MFCCs)":[76],"closely":[78],"related":[79],"Now,":[82],"instead":[83,103],"coefficients,":[88],"discard":[90],"them":[91],"only":[93],"keep":[94],"upper":[96],"coefficients.":[97],"Furthermore,":[98],"using":[99],"pitch":[101],"scale":[102,107],"mel":[106],"allows":[108],"us":[109],"project":[111],"remaining":[113],"onto":[115],"twelve":[117],"bins.":[119],"systematic":[121],"experiments":[122],"resulting":[126],"have":[129],"indeed":[130],"gained":[131],"significant":[133],"boost":[134],"towards":[135],"invariance.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}