{"id":"https://openalex.org/W2139878068","doi":"https://doi.org/10.1109/icassp.2014.6854172","title":"Automatic transcription of pitched and unpitched sounds from polyphonic music","display_name":"Automatic transcription of pitched and unpitched sounds from polyphonic music","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2139878068","doi":"https://doi.org/10.1109/icassp.2014.6854172","mag":"2139878068"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Department of Computer Science, City University London, London, UK","Dept. of Comput. Sci., City Univ. London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University London, London, UK","institution_ids":["https://openalex.org/I180825142"]},{"raw_affiliation_string":"Dept. of Comput. Sci., City Univ. London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001413512","display_name":"Sebastian Ewert","orcid":"https://orcid.org/0000-0002-0718-0476"},"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":"Sebastian Ewert","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK","Centre for Digital Music, Queen Mary Univ. of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary Univ. of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018493892","display_name":"Tillman Weyde","orcid":"https://orcid.org/0000-0001-8028-9905"},"institutions":[{"id":"https://openalex.org/I180825142","display_name":"City, University of London","ror":"https://ror.org/04489at23","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I180825142"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tillman Weyde","raw_affiliation_strings":["Department of Computer Science, City University London, London, UK","Dept. of Comput. Sci., City Univ. London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University London, London, UK","institution_ids":["https://openalex.org/I180825142"]},{"raw_affiliation_string":"Dept. of Comput. Sci., City Univ. London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084672392"],"corresponding_institution_ids":["https://openalex.org/I180825142"],"apc_list":null,"apc_paid":null,"fwci":2.9441,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91999772,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3107","last_page":"3111"},"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":0.9995999932289124,"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":0.9994999766349792,"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/polyphony","display_name":"Polyphony","score":0.8968151211738586},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7248252034187317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7016977071762085},{"id":"https://openalex.org/keywords/drum","display_name":"Drum","score":0.6638675332069397},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6598427891731262},{"id":"https://openalex.org/keywords/bass","display_name":"Bass (fish)","score":0.559920608997345},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44511258602142334},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.44235724210739136},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4419921636581421},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4265567362308502},{"id":"https://openalex.org/keywords/western-music","display_name":"Western music","score":0.41780006885528564},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3547552227973938},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.30449673533439636},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1108693778514862},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08992090821266174},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.06952130794525146},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.067087322473526},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.06458070874214172}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8968151211738586},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7248252034187317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016977071762085},{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.6638675332069397},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6598427891731262},{"id":"https://openalex.org/C2777182073","wikidata":"https://www.wikidata.org/wiki/Q1224135","display_name":"Bass (fish)","level":2,"score":0.559920608997345},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44511258602142334},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.44235724210739136},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4419921636581421},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4265567362308502},{"id":"https://openalex.org/C2992949519","wikidata":"https://www.wikidata.org/wiki/Q282442","display_name":"Western music","level":3,"score":0.41780006885528564},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3547552227973938},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.30449673533439636},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1108693778514862},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08992090821266174},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.06952130794525146},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.067087322473526},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06458070874214172},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2014.6854172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:openaccess.city.ac.uk:3268","is_oa":false,"landing_page_url":"https://openaccess.city.ac.uk/id/eprint/3268/3/RWC_Jazz_Aligned_Annotations.zip","pdf_url":null,"source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.9704","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.9704","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/%7Eewerts/publications/2014_BenetosEwertWeyde_HarmonicPercussiveTranscription_ICASSP.pdf","raw_type":"text"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/9413","is_oa":false,"landing_page_url":"http://qmro.qmul.ac.uk/xmlui/handle/123456789/9413","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7824420385","display_name":null,"funder_award_id":"EP/J010375/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8217561489","display_name":null,"funder_award_id":"EP/L019981/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W144105221","https://openalex.org/W1491667773","https://openalex.org/W1607142029","https://openalex.org/W1942706070","https://openalex.org/W2000911789","https://openalex.org/W2017416504","https://openalex.org/W2017578549","https://openalex.org/W2024339477","https://openalex.org/W2049633694","https://openalex.org/W2100816929","https://openalex.org/W2104299881","https://openalex.org/W2105143211","https://openalex.org/W2110007838","https://openalex.org/W2120809168","https://openalex.org/W2129258718","https://openalex.org/W2242076280","https://openalex.org/W3129711340","https://openalex.org/W4285719527","https://openalex.org/W6605910177","https://openalex.org/W6636203886","https://openalex.org/W6640725723","https://openalex.org/W6675456757","https://openalex.org/W6690257645"],"related_works":["https://openalex.org/W2391185433","https://openalex.org/W2367773357","https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W2012034325","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Automatic":[0],"transcription":[1,31,133],"of":[2,83,94],"polyphonic":[3,66,114],"music":[4,26,67,116],"has":[5],"been":[6],"an":[7],"active":[8],"research":[9],"field":[10],"for":[11],"several":[12],"years":[13],"and":[14,62,79,108,120,131],"is":[15],"considered":[16],"by":[17],"many":[18],"to":[19,124],"be":[20],"a":[21,56],"key":[22],"enabling":[23],"technology":[24],"in":[25,128],"signal":[27],"processing.":[28],"However,":[29],"current":[30],"approaches":[32],"either":[33],"focus":[34],"on":[35,44,113],"detecting":[36,45],"pitched":[37,40,61,84,119],"sounds":[38,47,64,85,96],"(from":[39,48],"musical":[41],"instruments)":[42],"or":[43],"unpitched":[46,63,121],"drum":[49,98,132],"kits).":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"method":[57],"that":[58],"jointly":[59],"transcribes":[60],"from":[65,86,97],"recordings.":[68],"The":[69],"proposed":[70],"model":[71],"extends":[72],"the":[73,81,92],"probabilistic":[74],"latent":[75],"component":[76],"analysis":[77],"algorithm":[78],"supports":[80],"detection":[82,93,130],"multiple":[87],"instruments":[88,122],"as":[89,91],"well":[90],"un-pitched":[95],"kit":[99],"components,":[100],"including":[101],"bass":[102],"drums,":[103,105],"snare":[104],"cymbals,":[106],"hi-hats,":[107],"toms.":[109],"Our":[110],"experiments":[111],"based":[112],"Western":[115],"containing":[117],"both":[118],"led":[123],"very":[125],"encouraging":[126],"results":[127],"multi-pitch":[129],"tasks.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
