{"id":"https://openalex.org/W4391640266","doi":"https://doi.org/10.1109/lsp.2024.3363646","title":"A Data-Driven Analysis of Robust Automatic Piano Transcription","display_name":"A Data-Driven Analysis of Robust Automatic Piano Transcription","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391640266","doi":"https://doi.org/10.1109/lsp.2024.3363646"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3363646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3363646","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/94700/2/Edwards%20A%20Data-Driven%202034%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055602158","display_name":"Drew Edwards","orcid":"https://orcid.org/0009-0004-6111-835X"},"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":"Drew Edwards","raw_affiliation_strings":["Queen Mary University of London (QMUL), London, U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London (QMUL), London, U.K","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":["Queen Mary University of London (QMUL), London, U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London (QMUL), 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":["Queen Mary University of London (QMUL), London, U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London (QMUL), London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078424070","display_name":"Akira Maezawa","orcid":"https://orcid.org/0009-0002-9827-5434"},"institutions":[{"id":"https://openalex.org/I1295929820","display_name":"Yamaha (Japan)","ror":"https://ror.org/05s7fvh27","country_code":"JP","type":"company","lineage":["https://openalex.org/I1295929820"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Maezawa","raw_affiliation_strings":["Yamaha Corporation, Hamamatsu, Japan"],"affiliations":[{"raw_affiliation_string":"Yamaha Corporation, Hamamatsu, Japan","institution_ids":["https://openalex.org/I1295929820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049938038","display_name":"Yuta Kusaka","orcid":"https://orcid.org/0009-0004-4921-5253"},"institutions":[{"id":"https://openalex.org/I1295929820","display_name":"Yamaha (Japan)","ror":"https://ror.org/05s7fvh27","country_code":"JP","type":"company","lineage":["https://openalex.org/I1295929820"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Kusaka","raw_affiliation_strings":["Yamaha Corporation, Hamamatsu, Japan"],"affiliations":[{"raw_affiliation_string":"Yamaha Corporation, Hamamatsu, Japan","institution_ids":["https://openalex.org/I1295929820"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055602158"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":2.453,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89002069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"681","last_page":"685"},"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8137401938438416},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7993313074111938},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.7066775560379028},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5108213424682617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49977850914001465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4786866307258606},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4262063801288605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4053806960582733},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34150615334510803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137401938438416},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7993313074111938},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.7066775560379028},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5108213424682617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49977850914001465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4786866307258606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4262063801288605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4053806960582733},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34150615334510803},{"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/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},{"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/lsp.2024.3363646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3363646","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/94700","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/94700","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/94700/2/Edwards%20A%20Data-Driven%202034%20Accepted.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/94700","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/94700","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/94700/2/Edwards%20A%20Data-Driven%202034%20Accepted.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1595280774","display_name":"JADE: Joint Academic Data science Endeavour - 2","funder_award_id":"EP/T022205/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320311061","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391640266.pdf","grobid_xml":"https://content.openalex.org/works/W4391640266.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2144346840","https://openalex.org/W2198584637","https://openalex.org/W2509065397","https://openalex.org/W2566755135","https://openalex.org/W2954996726","https://openalex.org/W2963045359","https://openalex.org/W3016970897","https://openalex.org/W3098357269","https://openalex.org/W3103934428","https://openalex.org/W3209419355","https://openalex.org/W4372260308","https://openalex.org/W6603626069","https://openalex.org/W6712594816","https://openalex.org/W6712738854","https://openalex.org/W6730401039","https://openalex.org/W6731203071","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6798855526","https://openalex.org/W6803088475","https://openalex.org/W6810809420","https://openalex.org/W6847461587","https://openalex.org/W6854061045"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Algorithms":[0],"for":[1,87],"automatic":[2],"piano":[3,63],"transcription":[4,47],"have":[5,20],"improved":[6],"dramatically":[7],"in":[8,35,93,146],"recent":[9],"years":[10],"due":[11],"to":[12,37,73,152],"new":[13,25,83],"datasets":[14],"and":[15,33,113],"modeling":[16],"techniques.":[17],"Recent":[18],"developments":[19],"focused":[21],"primarily":[22],"on":[23,60,128,157],"adapting":[24],"neural":[26],"network":[27],"architectures,":[28],"such":[29],"as":[30],"the":[31,50,77,88,111,117,129,158],"Transformer":[32],"Perceiver,":[34],"order":[36],"yield":[38],"more":[39],"accurate":[40],"systems.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,65,120],"study":[46],"systems":[48],"from":[49],"perspective":[51],"of":[52,76,85,116,125,135,149],"their":[53,58,155],"training":[54,78,109,137],"data.":[55,79,138],"By":[56],"measuring":[57],"performance":[59],"out-of-distribution":[61],"annotated":[62],"data,":[64],"show":[66],"how":[67],"these":[68,142],"models":[69],"can":[70],"severely":[71],"overfit":[72],"acoustic":[74],"properties":[75],"We":[80,139],"create":[81],"a":[82,94,147],"set":[84],"audio":[86],"MAESTRO":[89,118],"dataset,":[90,119,131],"captured":[91],"automatically":[92],"professional":[95],"studio":[96],"recording":[97],"environment":[98],"via":[99],"Yamaha":[100],"Disklavier":[101],"playback.":[102],"Using":[103],"various":[104],"data":[105,143],"augmentation":[106,144],"techniques":[107,145],"when":[108],"with":[110],"original":[112],"re-performed":[114],"versions":[115],"achieve":[121],"state-of-the-art":[122],"note-onset":[123],"accuracy":[124],"88.4":[126],"F1-score":[127],"MAPS":[130],"without":[132],"seeing":[133],"any":[134],"its":[136],"subsequently":[140],"analyze":[141],"series":[148],"ablation":[150],"studies":[151],"better":[153],"understand":[154],"influence":[156],"resulting":[159],"models.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}