{"id":"https://openalex.org/W2002911700","doi":"https://doi.org/10.1109/icassp.2013.6637598","title":"A discriminative approach to polyphonic piano note transcription using supervised non-negative matrix factorization","display_name":"A discriminative approach to polyphonic piano note transcription using supervised non-negative matrix factorization","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2002911700","doi":"https://doi.org/10.1109/icassp.2013.6637598","mag":"2002911700"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6637598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/72588/72588.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Machine Intelligence & Signal Processing Group, MMK, Germany","Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, MMK, Germany","institution_ids":[]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I4210094487","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060424744","display_name":"Christian Kirst","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Kirst","raw_affiliation_strings":["Technische Universitat Munchen, Munchen, Bayern, DE","Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universitat Munchen, Munchen, Bayern, DE","institution_ids":[]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I4210094487","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Machine Intelligence & Signal Processing Group, MMK, Germany","Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, MMK, Germany","institution_ids":[]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I4210094487","https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068403289","display_name":"Hans\u2010Joachim Bungartz","orcid":"https://orcid.org/0000-0002-0171-0712"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","PK"],"is_corresponding":false,"raw_author_name":"Hans-Joachim Bungartz","raw_affiliation_strings":["Department of Informatics, Technische Universit\u00e4t M\u00fcnchen, Germany","Dept. of Inf., Tech. Univ. Munchen, Garching, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Dept. of Inf., Tech. Univ. Munchen, Garching, Germany#TAB#","institution_ids":["https://openalex.org/I1323252656"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"6","last_page":"10"},"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9994000196456909,"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/discriminative-model","display_name":"Discriminative model","score":0.8298203349113464},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7183040380477905},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.7113678455352783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.697779655456543},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.690787672996521},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.677270770072937},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6528935432434082},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6341146230697632},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6330055594444275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5771753787994385},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5688439011573792},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.4981389045715332}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8298203349113464},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7183040380477905},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.7113678455352783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697779655456543},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.690787672996521},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.677270770072937},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6528935432434082},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6341146230697632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6330055594444275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5771753787994385},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5688439011573792},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.4981389045715332},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2013.6637598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:72588","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-725882","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/72588/72588.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.640.502","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.640.502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ//pdf/13/13wen4.pdf","raw_type":"text"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1418527","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1418527","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:72588","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-725882","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/72588/72588.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2002911700.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W142485264","https://openalex.org/W147600081","https://openalex.org/W189345193","https://openalex.org/W1483963899","https://openalex.org/W1484957289","https://openalex.org/W1603632465","https://openalex.org/W1752772649","https://openalex.org/W1987514054","https://openalex.org/W2101212989","https://openalex.org/W2104298926","https://openalex.org/W2108494558","https://openalex.org/W2110007838","https://openalex.org/W2118585731","https://openalex.org/W2121148209","https://openalex.org/W2127947624","https://openalex.org/W2129638017","https://openalex.org/W2135029798","https://openalex.org/W2144414181","https://openalex.org/W2150415460","https://openalex.org/W2152937398","https://openalex.org/W2158983491","https://openalex.org/W2167277498","https://openalex.org/W2186278341","https://openalex.org/W2295460171","https://openalex.org/W3143596294","https://openalex.org/W4285719527","https://openalex.org/W6628966375","https://openalex.org/W6629078384","https://openalex.org/W6636328019","https://openalex.org/W6637898492","https://openalex.org/W6677656871","https://openalex.org/W6678022326","https://openalex.org/W6680012447","https://openalex.org/W6686592130","https://openalex.org/W6697000175","https://openalex.org/W6930559537"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2075222291"],"abstract_inverted_index":{"We":[0,66],"introduce":[1],"a":[2,52],"novel":[3],"method":[4,71],"for":[5],"the":[6,69],"transcription":[7],"of":[8,15,58],"polyphonic":[9],"piano":[10,59],"music":[11,60],"by":[12,27],"discriminative":[13],"training":[14],"support":[16],"vector":[17],"machines":[18],"(SVMs).":[19],"As":[20],"features,":[21],"we":[22],"use":[23],"pitch":[24],"activations":[25],"computed":[26],"supervised":[28],"non-negative":[29],"matrix":[30],"factorization":[31],"from":[32],"low-level":[33,39],"spectral":[34,81],"features.":[35,82],"Different":[36],"approaches":[37],"to":[38],"feature":[40,47],"extraction,":[41],"NMF":[42],"dictionary":[43],"learning":[44],"and":[45,63,75],"activation":[46],"extraction":[48],"are":[49],"analyzed":[50],"in":[51],"large-scale":[53],"evaluation":[54],"on":[55],"eight":[56],"hours":[57],"including":[61],"synthesized":[62],"real":[64],"recordings.":[65],"conclude":[67],"that":[68],"proposed":[70],"delivers":[72],"state-of-the-art":[73],"results":[74],"clearly":[76],"outperforms":[77],"SVMs":[78],"using":[79],"simple":[80]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
