{"id":"https://openalex.org/W2180849752","doi":"https://doi.org/10.1109/taslp.2016.2530409","title":"Unsupervised Incremental Online Learning and Prediction of Musical Audio Signals","display_name":"Unsupervised Incremental Online Learning and Prediction of Musical Audio Signals","publication_year":2016,"publication_date":"2016-02-15","ids":{"openalex":"https://openalex.org/W2180849752","doi":"https://doi.org/10.1109/taslp.2016.2530409","mag":"2180849752"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2530409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2530409","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1502.00524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"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"]},{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["ES","GB"],"is_corresponding":false,"raw_author_name":"Ricard Marxer","raw_affiliation_strings":["The Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","The Speech and Hearing Group, Department of Computer Science, University of Sheffield, Sheffield, U.K"],"raw_orcid":"https://orcid.org/0000-0001-5099-5059","affiliations":[{"raw_affiliation_string":"The Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"The Speech and Hearing Group, Department of Computer Science, University of Sheffield, Sheffield, U.K","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074839324","display_name":"H.\u2010G. Purwins","orcid":"https://orcid.org/0000-0002-0053-215X"},"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"]},{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DE","DK"],"is_corresponding":false,"raw_author_name":"Hendrik Purwins","raw_affiliation_strings":["The Audio Analysis Lab and Sound and Music Computing Group, Aalborg Universitet K\u00f8benhavn, Copenhagen, Denmark","The Neurotechnology Group, Berlin Institute of Technology, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Audio Analysis Lab and Sound and Music Computing Group, Aalborg Universitet K\u00f8benhavn, Copenhagen, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"The Neurotechnology Group, Berlin Institute of Technology, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2504,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.79306596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"24","issue":"5","first_page":"863","last_page":"874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9988999962806702,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9824000000953674,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.6172614097595215},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5834404826164246},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.45175209641456604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44982215762138367},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4412471652030945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3477477729320526},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08455252647399902},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.0681944191455841},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.05462554097175598}],"concepts":[{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.6172614097595215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5834404826164246},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.45175209641456604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44982215762138367},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4412471652030945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3477477729320526},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08455252647399902},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0681944191455841},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.05462554097175598}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2016.2530409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2530409","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1502.00524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1502.00524","pdf_url":"https://arxiv.org/pdf/1502.00524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:eprints.whiterose.ac.uk:100592","is_oa":true,"landing_page_url":null,"pdf_url":"http://eprints.whiterose.ac.uk/100592/1/1502.00524v2.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:HAL:hal-04931712v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04931712","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2016, 24 (5), pp.863-874. ⟨10.1109/TASLP.2016.2530409⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1502.00524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1502.00524","pdf_url":"https://arxiv.org/pdf/1502.00524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G3446780202","display_name":null,"funder_award_id":"INSPIRE-ITN FP7-PEOPLE-2011-290000","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3819085203","display_name":null,"funder_award_id":"EmCAP FP6-IST 013123","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W41924313","https://openalex.org/W43410621","https://openalex.org/W67320657","https://openalex.org/W85840116","https://openalex.org/W166614460","https://openalex.org/W175070741","https://openalex.org/W192383697","https://openalex.org/W360531859","https://openalex.org/W1509169784","https://openalex.org/W1512798169","https://openalex.org/W1538359790","https://openalex.org/W1577552086","https://openalex.org/W1595111316","https://openalex.org/W1813659000","https://openalex.org/W1967957118","https://openalex.org/W1972260496","https://openalex.org/W2007964250","https://openalex.org/W2011485152","https://openalex.org/W2011760672","https://openalex.org/W2039558625","https://openalex.org/W2042492924","https://openalex.org/W2042737139","https://openalex.org/W2064675550","https://openalex.org/W2066680326","https://openalex.org/W2070412788","https://openalex.org/W2073308541","https://openalex.org/W2098580349","https://openalex.org/W2099064293","https://openalex.org/W2103028434","https://openalex.org/W2110644158","https://openalex.org/W2111066885","https://openalex.org/W2115026158","https://openalex.org/W2128558479","https://openalex.org/W2132991226","https://openalex.org/W2133119264","https://openalex.org/W2137619888","https://openalex.org/W2139280638","https://openalex.org/W2154686727","https://openalex.org/W2155073615","https://openalex.org/W2157305458","https://openalex.org/W2163747209","https://openalex.org/W2169264582","https://openalex.org/W2174443198","https://openalex.org/W2175320824","https://openalex.org/W2182486909","https://openalex.org/W2277957941","https://openalex.org/W2571012312","https://openalex.org/W2949115596","https://openalex.org/W2963618051","https://openalex.org/W2980286501","https://openalex.org/W3091227345","https://openalex.org/W3104490327","https://openalex.org/W4234536190","https://openalex.org/W4248943602","https://openalex.org/W4255825300","https://openalex.org/W6601728941","https://openalex.org/W6601813835","https://openalex.org/W6602702551","https://openalex.org/W6603539467","https://openalex.org/W6607890289","https://openalex.org/W6612268706","https://openalex.org/W6632029529","https://openalex.org/W6634434589","https://openalex.org/W6634986005","https://openalex.org/W6635557383","https://openalex.org/W6638304892","https://openalex.org/W6674749460","https://openalex.org/W6674927801","https://openalex.org/W6677156367","https://openalex.org/W6694665639","https://openalex.org/W6765850333","https://openalex.org/W6768798221","https://openalex.org/W6783894077"],"related_works":["https://openalex.org/W2150284098","https://openalex.org/W4252843888","https://openalex.org/W2350758546","https://openalex.org/W4390012055","https://openalex.org/W4244412922","https://openalex.org/W2098811573","https://openalex.org/W4235276350","https://openalex.org/W2330938685","https://openalex.org/W2807987393","https://openalex.org/W1975265014"],"abstract_inverted_index":{"Guided":[0],"by":[1,61,70,77,99],"the":[2,40,54,96,100,116,123,132,144,149,152,169,201,204],"idea":[3],"that":[4,38,90,129],"musical":[5,45],"human-computer":[6],"interaction":[7],"may":[8],"become":[9],"more":[10,22],"effective,":[11],"intuitive,":[12],"and":[13,122,140,166,188,200],"creative":[14],"when":[15],"basing":[16],"its":[17],"computer":[18],"part":[19],"on":[20,95],"cognitively":[21],"plausible":[23],"learning":[24,31],"principles,":[25],"we":[26],"employ":[27],"unsupervised":[28],"incremental":[29,78],"online":[30],"(i.e.":[32],"clustering)":[33],"to":[34,131,164],"build":[35],"a":[36,44,81,106],"system":[37,55,206],"predicts":[39],"next":[41,145],"event":[42,147],"in":[43,105,137,148,172],"sequence,":[46,109,118,150],"given":[47,151],"as":[48,57],"audio":[49],"input.":[50],"The":[51,157],"flow":[52],"of":[53,67,83,112,115,143,168,180,185,198,203,210],"is":[56,160],"follows:":[58],"1)":[59],"segmentation":[60],"onset":[62],"detection,":[63],"2)":[64],"timbre":[65,88],"representation":[66],"each":[68],"segment":[69],"Mel":[71],"frequency":[72],"cepstrum":[73],"coefficients,":[74],"3)":[75,138],"discretization":[76],"clustering,":[79],"yielding":[80],"tree":[82,136],"different":[84],"sound":[85,102,146],"classes":[86],"(e.g.":[87],"categories/instruments)":[89],"can":[91],"grow":[92],"or":[93],"shrink":[94],"fly":[97],"driven":[98],"instantaneous":[101],"events,":[103],"resulting":[104],"discrete":[107],"symbol":[108,117],"4)":[110],"extraction":[111],"statistical":[113],"regularities":[114],"using":[119],"hierarchical":[120],"N-grams":[121],"newly":[124],"introduced":[125],"conceptual":[126],"Boltzmann":[127],"machine":[128],"adapt":[130],"dynamically":[133],"changing":[134],"clustering":[135,194],",":[139],"5)":[141],"prediction":[142,202],"last":[153],"$n$":[154],"previous":[155],"events.":[156],"system's":[158],"robustness":[159],"assessed":[161],"with":[162,193],"respect":[163],"complexity":[165],"noisiness":[167],"signal.":[170],"Clustering":[171],"isolation":[173],"yields":[174,207],"an":[175,196,208],"adjusted":[176],"Rand":[177],"index":[178],"(ARI)":[179],"82.7%/85.7%":[181],"for":[182],"data":[183],"sets":[184],"singing":[186],"voice":[187],"drums.":[189],"Onset":[190],"detection":[191],"jointly":[192],"achieve":[195],"ARI":[197,209],"81.3%/76.3%":[199],"entire":[205],"27.2%/39.2%.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}