{"id":"https://openalex.org/W2017512687","doi":"https://doi.org/10.1145/2371456.2371464","title":"Improved music similarity computation based on tone objects","display_name":"Improved music similarity computation based on tone objects","publication_year":2012,"publication_date":"2012-09-26","ids":{"openalex":"https://openalex.org/W2017512687","doi":"https://doi.org/10.1145/2371456.2371464","mag":"2017512687"},"language":"en","primary_location":{"id":"doi:10.1145/2371456.2371464","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2371456.2371464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Audio Mostly Conference: A Conference on Interaction with Sound","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/A5060815445","display_name":"Johannes Krasser","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Johannes Krasser","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047532715","display_name":"Jakob Abe\u00dfer","orcid":"https://orcid.org/0000-0003-4689-7944"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jakob Abe\u00dfer","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074845607","display_name":"Holger Gro\u00dfmann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Holger Gro\u00dfmann","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009881719","display_name":"Christian Dittmar","orcid":"https://orcid.org/0000-0002-3220-2446"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Dittmar","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031086670","display_name":"Estefan\u00eda Cano","orcid":"https://orcid.org/0000-0002-1056-5844"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Estefan\u00eda Cano","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060815445"],"corresponding_institution_ids":["https://openalex.org/I4210138578"],"apc_list":null,"apc_paid":null,"fwci":0.7345,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72769349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"47","last_page":"54"},"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":0.9991000294685364,"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":0.9876000285148621,"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":0.7896071672439575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7254915237426758},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.688635528087616},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6840574741363525},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6802310943603516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.594909131526947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5708134174346924},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5659669637680054},{"id":"https://openalex.org/keywords/octave","display_name":"Octave (electronics)","score":0.5497090816497803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5270966291427612},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4535740613937378},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42993324995040894},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42724689841270447},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4180218577384949},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07675915956497192}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7896071672439575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254915237426758},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.688635528087616},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6840574741363525},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6802310943603516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.594909131526947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5708134174346924},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5659669637680054},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.5497090816497803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5270966291427612},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4535740613937378},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42993324995040894},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42724689841270447},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4180218577384949},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07675915956497192},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2371456.2371464","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2371456.2371464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Audio Mostly Conference: A Conference on Interaction with Sound","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/379231","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/379231","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W84529036","https://openalex.org/W127011120","https://openalex.org/W141230911","https://openalex.org/W152909648","https://openalex.org/W205731033","https://openalex.org/W286173085","https://openalex.org/W409429913","https://openalex.org/W1522155447","https://openalex.org/W1561135842","https://openalex.org/W1561317161","https://openalex.org/W1774234760","https://openalex.org/W1779538084","https://openalex.org/W2101151533","https://openalex.org/W2103662883","https://openalex.org/W2106153115","https://openalex.org/W2109943925","https://openalex.org/W2117330939","https://openalex.org/W2125324924","https://openalex.org/W2129338995","https://openalex.org/W2132857561","https://openalex.org/W2133824856","https://openalex.org/W2140304104","https://openalex.org/W2148578737","https://openalex.org/W2148899569","https://openalex.org/W2150223021","https://openalex.org/W2151816810","https://openalex.org/W2162209287","https://openalex.org/W2178339699","https://openalex.org/W2293626685","https://openalex.org/W2394506964","https://openalex.org/W2399961058","https://openalex.org/W2591695226","https://openalex.org/W3146003712","https://openalex.org/W4298266977","https://openalex.org/W6606150254"],"related_works":["https://openalex.org/W4312238237","https://openalex.org/W4292658355","https://openalex.org/W2160011803","https://openalex.org/W2148804984","https://openalex.org/W4317770561","https://openalex.org/W1512398020","https://openalex.org/W1999395714","https://openalex.org/W3047703615","https://openalex.org/W4367145137","https://openalex.org/W4317383455"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,49,66,85],"propose":[4],"a":[5,54,69,104],"novel":[6,88],"approach":[7,52,89],"for":[8],"music":[9,17,120],"similarity":[10,121],"estimation.":[11,122],"It":[12],"combines":[13],"temporal":[14],"segmentation":[15],"of":[16],"signals":[18],"with":[19],"source":[20],"separation":[21],"into":[22],"so-called":[23],"tone":[24,46,113],"objects.":[25,47],"We":[26,94],"solely":[27],"use":[28],"the":[29,44,91,100],"timbre-related":[30],"audio":[31],"features":[32,73],"Mel-Frequency":[33],"Cepstral":[34],"Coefficients":[35],"(MFCC)":[36],"and":[37,62],"Octave-based":[38],"Spectral":[39],"Contrast":[40],"(OSC)":[41],"to":[42,53],"describe":[43],"extracted":[45],"First,":[48],"compare":[50,86],"our":[51,87],"baseline":[55,101],"system":[56,70,102],"that":[57,71,96,112],"employs":[58],"frame-wise":[59],"feature":[60,116],"extraction":[61,117],"bag-of-frames":[63],"classification.":[64,83],"Second,":[65],"set":[67],"up":[68],"extracts":[72],"on":[74],"perfectly":[75],"isolated":[76],"single":[77],"track":[78],"recordings,":[79],"achieving":[80],"near":[81],"perfect":[82],"Finally,":[84],"against":[90],"basis":[92],"experiments.":[93],"find":[95],"it":[97],"clearly":[98,118],"outperforms":[99],"in":[103],"five-class":[105],"genre":[106],"classification":[107],"task.":[108],"Our":[109],"results":[110],"indicate":[111],"object":[114],"based":[115],"improves":[119]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}