{"id":"https://openalex.org/W2198584637","doi":"https://doi.org/10.1109/taslp.2016.2533858","title":"An End-to-End Neural Network for Polyphonic Piano Music Transcription","display_name":"An End-to-End Neural Network for Polyphonic Piano Music Transcription","publication_year":2016,"publication_date":"2016-02-23","ids":{"openalex":"https://openalex.org/W2198584637","doi":"https://doi.org/10.1109/taslp.2016.2533858","mag":"2198584637"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2533858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2533858","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":["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/A5113798270","display_name":"Siddharth Sigtia","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":true,"raw_author_name":"Siddharth Sigtia","raw_affiliation_strings":["Centre for Digital Music, School of Electronic Engineering, and Computer Science, Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, School of Electronic Engineering, and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","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":"Emmanouil Benetos","raw_affiliation_strings":["Centre for Digital Music, School of Electronic Engineering, and Computer Science, Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, School of Electronic Engineering, and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","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, School of Electronic Engineering, and Computer Science, Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, School of Electronic Engineering, and Computer Science, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113798270"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":30.2617,"has_fulltext":false,"cited_by_count":282,"citation_normalized_percentile":{"value":0.99845183,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"24","issue":"5","first_page":"927","last_page":"939"},"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":0.9991999864578247,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.7665596008300781},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6541086435317993},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.618939220905304},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.618781566619873},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5874751806259155},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4768192172050476},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4606679677963257},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4427715539932251},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4331516623497009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36596617102622986},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24387133121490479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7665596008300781},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6541086435317993},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.618939220905304},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.618781566619873},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5874751806259155},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4768192172050476},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4606679677963257},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4427715539932251},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4331516623497009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36596617102622986},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24387133121490479},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2016.2533858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2533858","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:qmro.qmul.ac.uk:123456789/17623","is_oa":false,"landing_page_url":"http://qmro.qmul.ac.uk/xmlui/handle/123456789/17623","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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G4327335547","display_name":null,"funder_award_id":"RF/128","funder_id":"https://openalex.org/F4320320005","funder_display_name":"Royal Academy of Engineering"}],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W89231944","https://openalex.org/W129413713","https://openalex.org/W189345193","https://openalex.org/W648786980","https://openalex.org/W1498436455","https://openalex.org/W1560013842","https://openalex.org/W1602017060","https://openalex.org/W1819710477","https://openalex.org/W1822807512","https://openalex.org/W1828163288","https://openalex.org/W1888154959","https://openalex.org/W1967442998","https://openalex.org/W1982446897","https://openalex.org/W2042390666","https://openalex.org/W2045135321","https://openalex.org/W2075449699","https://openalex.org/W2076608692","https://openalex.org/W2083380015","https://openalex.org/W2086127342","https://openalex.org/W2095705004","https://openalex.org/W2096354165","https://openalex.org/W2096482524","https://openalex.org/W2104298926","https://openalex.org/W2104299881","https://openalex.org/W2105343238","https://openalex.org/W2108563286","https://openalex.org/W2110007838","https://openalex.org/W2125838338","https://openalex.org/W2129638017","https://openalex.org/W2135151673","https://openalex.org/W2135181320","https://openalex.org/W2137619888","https://openalex.org/W2144414181","https://openalex.org/W2147962362","https://openalex.org/W2150355110","https://openalex.org/W2152937398","https://openalex.org/W2155208345","https://openalex.org/W2155273149","https://openalex.org/W2156387975","https://openalex.org/W2162911105","https://openalex.org/W2163762452","https://openalex.org/W2167969117","https://openalex.org/W2168231600","https://openalex.org/W2188183693","https://openalex.org/W2295460171","https://openalex.org/W2395935897","https://openalex.org/W2398597216","https://openalex.org/W2433636802","https://openalex.org/W2914484425","https://openalex.org/W2919115771","https://openalex.org/W2946046356","https://openalex.org/W2962968839","https://openalex.org/W3145128584","https://openalex.org/W4255949318","https://openalex.org/W4285719527","https://openalex.org/W6600284362","https://openalex.org/W6603626069","https://openalex.org/W6607768639","https://openalex.org/W6621543089","https://openalex.org/W6629815555","https://openalex.org/W6633431331","https://openalex.org/W6635989145","https://openalex.org/W6638749077","https://openalex.org/W6639341926","https://openalex.org/W6674330103","https://openalex.org/W6675456757","https://openalex.org/W6679714990","https://openalex.org/W6684101036","https://openalex.org/W6684859321","https://openalex.org/W6697000175"],"related_works":["https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2118730790","https://openalex.org/W2126322296","https://openalex.org/W2037564206","https://openalex.org/W7946549","https://openalex.org/W2890297197","https://openalex.org/W2955724459","https://openalex.org/W2921005841","https://openalex.org/W2037769829"],"abstract_inverted_index":{"We":[0,115,121,148,179],"present":[1,194],"a":[2,30,38,49,57,99],"supervised":[3],"neural":[4,39,59,124,153,167],"network":[5,40,60,125,168],"model":[6,17,28,36,55,72,94,142,214],"for":[7,42,127,216],"polyphonic":[8,81],"piano":[9],"music":[10,31,82,140,189],"transcription.":[11],"The":[12,34,53,70,90],"architecture":[13],"of":[14,46,51,119,136,151,187,198,210],"the":[15,44,63,88,105,111,128,134,145,152,172,185,188,213],"proposed":[16,71,146],"is":[18,37,56,73,108],"analogous":[19],"to":[20,79],"speech":[21],"recognition":[22],"systems":[23],"and":[24,29,75,92,131,139,204],"comprises":[25],"an":[26,195,208],"acoustic":[27,35,91,129,138,155,161,169],"language":[32,54,93,141,190],"model.":[33,102],"used":[41,78],"estimating":[43],"probabilities":[45],"pitches":[47],"in":[48],"frame":[50],"audio.":[52],"recurrent":[58],"that":[61,165,201],"models":[62,130,156,170],"correlations":[64],"between":[65],"pitch":[66],"combinations":[67],"over":[68,104],"time.":[69],"general":[74],"can":[76],"be":[77],"transcribe":[80],"without":[83],"imposing":[84],"any":[85],"constraints":[86],"on":[87],"polyphony.":[89],"predictions":[95,143],"are":[96],"combined":[97],"using":[98,110,144],"probabilistic":[100],"graphical":[101],"Inference":[103],"output":[106],"variables":[107],"performed":[109],"beam":[112,199],"search":[113,200],"algorithm.":[114],"perform":[116],"two":[117,158],"sets":[118],"experiments.":[120],"investigate":[122,133],"various":[123],"architectures":[126],"also":[132,180],"effect":[135],"combining":[137],"architecture.":[147],"compare":[149],"performance":[150,174,183,203],"network-based":[154],"with":[157,184],"popular":[159],"unsupervised":[160],"models.":[162,191],"Results":[163],"show":[164],"convolutional":[166],"yield":[171],"best":[173],"across":[175],"all":[176],"evaluation":[177],"metrics.":[178],"observe":[181],"improved":[182],"application":[186],"Finally,":[192],"we":[193],"efficient":[196],"variant":[197],"improves":[202],"reduces":[205],"run-times":[206],"by":[207],"order":[209],"magnitude,":[211],"making":[212],"suitable":[215],"real-time":[217],"applications.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":36},{"year":2018,"cited_by_count":41},{"year":2017,"cited_by_count":35},{"year":2016,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}