{"id":"https://openalex.org/W2433636802","doi":"https://doi.org/10.1109/icassp.2015.7178333","title":"A hybrid recurrent neural network for music transcription","display_name":"A hybrid recurrent neural network for music transcription","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W2433636802","doi":"https://doi.org/10.1109/icassp.2015.7178333","mag":"2433636802"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/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 EECS, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music EECS, Queen Mary University of London, London, UK","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/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":"Emmanouil Benetos","raw_affiliation_strings":["\u2020 Department of Computer Science, City University London, London, UK"],"affiliations":[{"raw_affiliation_string":"\u2020 Department of Computer Science, City University London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037330846","display_name":"Nicolas Boulanger-Lewandowski","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nicolas Boulanger-Lewandowski","raw_affiliation_strings":["\u2021Dept. IRO, Universite de Montr\u00e9al, Montr\u00e9al (QC), Canada"],"affiliations":[{"raw_affiliation_string":"\u2021Dept. IRO, Universite de Montr\u00e9al, Montr\u00e9al (QC), Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","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":["\u2020 Department of Computer Science, City University London, London, UK"],"affiliations":[{"raw_affiliation_string":"\u2020 Department of Computer Science, City University London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060005929","display_name":"Artur d\u2019Avila Garcez","orcid":"https://orcid.org/0000-0001-7375-9518"},"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":"Artur S. d'Avila Garcez","raw_affiliation_strings":["\u2020 Department of Computer Science, City University London, London, UK"],"affiliations":[{"raw_affiliation_string":"\u2020 Department of Computer Science, City University London, London, UK","institution_ids":["https://openalex.org/I180825142"]}]},{"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 EECS, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Digital Music EECS, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113798270"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":5.7916,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9679055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2061","last_page":"2065"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7682757377624512},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6808497905731201},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6188299059867859},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.601791501045227},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5948675274848938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5886722803115845},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.5613540410995483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4638305902481079},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4475994110107422},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4335183799266815},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4276992082595825},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41020888090133667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35215020179748535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682757377624512},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6808497905731201},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6188299059867859},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.601791501045227},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5948675274848938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5886722803115845},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.5613540410995483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4638305902481079},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4475994110107422},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4335183799266815},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4276992082595825},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41020888090133667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35215020179748535},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178333","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.762.2430","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.762.2430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1411.1623.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W89231944","https://openalex.org/W129413713","https://openalex.org/W1408639475","https://openalex.org/W1498436455","https://openalex.org/W1819710477","https://openalex.org/W1828163288","https://openalex.org/W1888154959","https://openalex.org/W1967442998","https://openalex.org/W2036317923","https://openalex.org/W2054567599","https://openalex.org/W2075449699","https://openalex.org/W2105728138","https://openalex.org/W2110007838","https://openalex.org/W2127141656","https://openalex.org/W2144414181","https://openalex.org/W2147880316","https://openalex.org/W2152937398","https://openalex.org/W2160815625","https://openalex.org/W2162911105","https://openalex.org/W2163762452","https://openalex.org/W2295460171","https://openalex.org/W2962968839","https://openalex.org/W6628131027","https://openalex.org/W6682082992","https://openalex.org/W6684101036"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W2160451571","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"We":[0,20,51],"investigate":[1],"the":[2,72,93,102,109],"problem":[3],"of":[4,92],"incorporating":[5],"higher-level":[6],"symbolic":[7],"score-like":[8],"information":[9],"into":[10],"Automatic":[11],"Music":[12],"Transcription":[13],"(AMT)":[14],"systems":[15],"to":[16],"improve":[17],"their":[18,27],"performance.":[19],"use":[21],"recurrent":[22],"neural":[23,55],"networks":[24],"(RNNs)":[25],"and":[26,34,76,105],"variants":[28],"as":[29],"music":[30,100],"language":[31],"models":[32,42],"(MLMs)":[33],"present":[35,78],"a":[36,46,65,83],"generative":[37],"architecture":[38],"for":[39,58,81,86],"combining":[40],"these":[41],"with":[43],"predictions":[44],"from":[45,101],"frame":[47],"level":[48],"acoustic":[49,59,73],"classifier.":[50],"also":[52],"compare":[53],"different":[54],"network":[56],"architectures":[57],"modeling.":[60],"The":[61,90],"proposed":[62,94,110],"model":[63,95,111],"computes":[64],"distribution":[66],"over":[67],"possible":[68],"output":[69],"sequences":[70],"given":[71],"input":[74],"signal":[75],"we":[77,106],"an":[79],"algorithm":[80],"performing":[82],"global":[84],"search":[85],"good":[87],"candidate":[88],"transcriptions.":[89],"performance":[91],"is":[96],"evaluated":[97],"on":[98],"piano":[99],"MAPS":[103],"dataset":[104],"observe":[107],"that":[108],"consistently":[112],"outperforms":[113],"existing":[114],"transcription":[115],"methods.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}