{"id":"https://openalex.org/W2151909846","doi":"https://doi.org/10.1109/icassp.2012.6287833","title":"Shift-variant non-negative matrix deconvolution for music transcription","display_name":"Shift-variant non-negative matrix deconvolution for music transcription","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2151909846","doi":"https://doi.org/10.1109/icassp.2012.6287833","mag":"2151909846"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5074883610","display_name":"Holger Kirchhoff","orcid":"https://orcid.org/0009-0008-4655-729X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Holger Kirchhoff","raw_affiliation_strings":["Centre for Digital Music, Queen's Mary, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen's Mary, University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077484271","display_name":"Simon Dixon","orcid":"https://orcid.org/0000-0002-6098-481X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Dixon","raw_affiliation_strings":["Centre for Digital Music, Queen's Mary, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen's Mary, University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035987859","display_name":"Anssi Klapuri","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anssi Klapuri","raw_affiliation_strings":["Centre for Digital Music, Queen's Mary, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen's Mary, University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074883610"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":3.7146,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.95273899,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"401","issue":null,"first_page":"125","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T11349","display_name":"Music Technology and Sound Studies","score":0.9987000226974487,"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/deconvolution","display_name":"Deconvolution","score":0.6220862865447998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5189192295074463},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4399879574775696},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31915539503097534},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08917573094367981},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07448238134384155}],"concepts":[{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.6220862865447998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5189192295074463},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4399879574775696},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31915539503097534},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08917573094367981},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07448238134384155}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6287833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.414.7186","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.414.7186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecs.qmul.ac.uk/~simond/pub/2012/Kirchhoff-Dixon-Klapuri-ICASSP-2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W86499233","https://openalex.org/W129413713","https://openalex.org/W1519655822","https://openalex.org/W1580974668","https://openalex.org/W1626927927","https://openalex.org/W1863372652","https://openalex.org/W1902027874","https://openalex.org/W2104298926","https://openalex.org/W2106582496","https://openalex.org/W2143959252","https://openalex.org/W6631117800","https://openalex.org/W6634590497","https://openalex.org/W6676113301","https://openalex.org/W6676199445"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4251527294","https://openalex.org/W3090782779","https://openalex.org/W4296701479","https://openalex.org/W3149087629","https://openalex.org/W4231036715","https://openalex.org/W2032074591","https://openalex.org/W1986156575","https://openalex.org/W4242983818","https://openalex.org/W2970288912"],"abstract_inverted_index":{"In":[0],"this":[1,32],"paper,":[2],"we":[3],"address":[4],"the":[5,13,19,61,67,87,91,129,132,136],"task":[6,33],"of":[7,54,63,69,80,83,103,105,112,131],"semi-automatic":[8],"music":[9],"transcription":[10,79],"in":[11,120],"which":[12,65,85],"user":[14,55],"provides":[15],"prior":[16],"information":[17,59],"about":[18,60],"polyphonic":[20],"mixture":[21],"under":[22,93],"analysis.":[23],"We":[24],"propose":[25],"a":[26,41,77,81,100,110,117],"non-negative":[27],"matrix":[28],"deconvolution":[29],"framework":[30],"for":[31,45],"that":[34],"allows":[35],"instruments":[36,107],"to":[37,109],"be":[38],"represented":[39],"by":[40],"different":[42,52],"basis":[43,70],"function":[44],"each":[46],"fundamental":[47],"frequency":[48],"(\u201cshift":[49],"variance\u201d).":[50],"Two":[51],"types":[53,62],"input":[56],"are":[57,97,125],"studied:":[58],"instruments,":[64],"enables":[66,86],"use":[68],"functions":[71],"from":[72,90],"an":[73],"instrument":[74],"database,":[75],"and":[76,127],"manual":[78],"number":[82],"notes":[84],"template":[88],"estimation":[89],"data":[92,101],"analysis":[94],"itself.":[95],"Experiments":[96],"performed":[98],"on":[99],"set":[102],"mixtures":[104],"acoustical":[106],"up":[108],"polyphony":[111],"five.":[113],"The":[114],"results":[115],"confirm":[116],"significant":[118],"loss":[119],"accuracy":[121],"when":[122],"database":[123],"templates":[124],"used":[126],"show":[128],"superiority":[130],"Kullback-Leibler":[133],"divergence":[134],"over":[135],"least":[137],"squares":[138],"error":[139],"cost":[140],"function.":[141]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}