{"id":"https://openalex.org/W2148494253","doi":"https://doi.org/10.1109/icassp.2011.5946367","title":"Nonlinear audio recurrence analysis with application to genre classification","display_name":"Nonlinear audio recurrence analysis with application to genre classification","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2148494253","doi":"https://doi.org/10.1109/icassp.2011.5946367","mag":"2148494253"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946367","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/A5103092198","display_name":"Joan Serr\u00e0","orcid":"https://orcid.org/0000-0003-1303-6558"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Joan Serra","raw_affiliation_strings":["Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043042125","display_name":"Carlos A. de los Santos","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos A. de los Santos","raw_affiliation_strings":["Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045873975","display_name":"Ralph G. Andrzejak","orcid":"https://orcid.org/0000-0002-7400-2098"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ralph G. Andrzejak","raw_affiliation_strings":["Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":1.5603,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84266736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"169","last_page":"172"},"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":0.9966999888420105,"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":0.9911999702453613,"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/histogram","display_name":"Histogram","score":0.8041555285453796},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6604951620101929},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6390552520751953},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6138841509819031},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5861589908599854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5669981837272644},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.559353768825531},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5435949563980103},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4945025146007538},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47297587990760803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4653288722038269},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4486272633075714},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4472726285457611},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11309877038002014},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07499584555625916}],"concepts":[{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.8041555285453796},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6604951620101929},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6390552520751953},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6138841509819031},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5861589908599854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5669981837272644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.559353768825531},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5435949563980103},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4945025146007538},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47297587990760803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4653288722038269},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4486272633075714},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4472726285457611},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11309877038002014},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07499584555625916},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5946367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946367","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:10.1.1.297.3963","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.297.3963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mtg.upf.edu/system/files/publications/serraetal_icassp2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W152909648","https://openalex.org/W1570448133","https://openalex.org/W2001014535","https://openalex.org/W2038678505","https://openalex.org/W2081681829","https://openalex.org/W2101151533","https://openalex.org/W2122468004","https://openalex.org/W2131739315","https://openalex.org/W2133824856","https://openalex.org/W2133990480","https://openalex.org/W2408751413","https://openalex.org/W3124661333","https://openalex.org/W4293074267","https://openalex.org/W4299429830","https://openalex.org/W6678174738","https://openalex.org/W6714403382"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W3110605476","https://openalex.org/W1803351015","https://openalex.org/W2363106653"],"abstract_inverted_index":{"In":[0,108],"this":[1,38,117],"paper":[2],"we":[3,16,76],"apply":[4,17],"nonlinear":[5,101],"signal":[6,102],"analysis":[7,103],"to":[8,26,90,121],"a":[9,41,50],"music":[10,30,106],"information":[11,28,114,123],"retrieval":[12],"task.":[13],"More":[14],"concretely,":[15],"the":[18,35,61,68,72,79,98,113,122],"concept":[19],"of":[20,37,81,100],"recurrence":[21,24],"plots":[22],"and":[23,46],"histograms":[25],"extract":[27],"from":[29,53,116],"audio":[31],"frames.":[32],"We":[33],"evaluate":[34],"effectiveness":[36],"approach":[39,118],"with":[40],"typical":[42],"genre":[43],"classification":[44],"framework":[45],"compare":[47],"it":[48,110],"against":[49],"baseline":[51],"obtained":[52,124],"standard":[54],"spectrum-based":[55],"descriptors.":[56,74],"The":[57],"accuracy":[58],"reached":[59],"by":[60,71],"histogram-based":[62],"descriptors":[63],"alone":[64],"does":[65],"not":[66],"surpass":[67],"one":[69],"achieved":[70],"spectral-based":[73],"However,":[75],"show":[77],"that":[78,112],"combination":[80],"both":[82],"descriptor":[83],"sources":[84],"results":[85],"in":[86],"consistent":[87],"improvements":[88],"up":[89],"5":[91],"absolute":[92],"percent":[93],"points.":[94],"This":[95],"high":[96],"lights":[97],"potential":[99],"for":[104],"quantitative":[105],"description.":[107],"particular,":[109],"suggests":[111],"resulting":[115],"is":[119],"complementary":[120],"through":[125],"tile":[126],"commonly":[127],"used":[128],"spectral":[129],"representation.":[130]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"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":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}