{"id":"https://openalex.org/W4224947526","doi":"https://doi.org/10.1109/icassp43922.2022.9746789","title":"Exploring Transformer\u2019s Potential on Automatic Piano Transcription","display_name":"Exploring Transformer\u2019s Potential on Automatic Piano Transcription","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224947526","doi":"https://doi.org/10.1109/icassp43922.2022.9746789"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746789","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5003653417","display_name":"Longshen Ou","orcid":"https://orcid.org/0000-0002-1725-8361"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Longshen Ou","raw_affiliation_strings":["National University of Singapore,School of Computing,Singapore","School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,School of Computing,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100949172","display_name":"Ziyi Guo","orcid":"https://orcid.org/0009-0005-5976-5811"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziyi Guo","raw_affiliation_strings":["National University of Singapore,School of Computing,Singapore","School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,School of Computing,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"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,Centre for Digital Music,UK","Centre for Digital Music, Queen Mary University of London, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423435","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0002-0123-1260"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ye Wang","raw_affiliation_strings":["National University of Singapore,School of Computing,Singapore","School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,School of Computing,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003653417"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.7183,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87045814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"776","last_page":"780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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":0.9970999956130981,"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/piano","display_name":"Piano","score":0.7067989110946655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6035432815551758},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5716440081596375},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5534557700157166},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43219467997550964},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.27795371413230896},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2125905156135559},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1281338930130005},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11125725507736206},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08694222569465637},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08278357982635498}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.7067989110946655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6035432815551758},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5716440081596375},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5534557700157166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43219467997550964},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.27795371413230896},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2125905156135559},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1281338930130005},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11125725507736206},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08694222569465637},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08278357982635498},{"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/icassp43922.2022.9746789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746789","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/76838","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/76838","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1586966408","https://openalex.org/W2126252750","https://openalex.org/W2152937398","https://openalex.org/W2158983491","https://openalex.org/W2198584637","https://openalex.org/W2407685581","https://openalex.org/W2566755135","https://openalex.org/W2740907159","https://openalex.org/W2903531107","https://openalex.org/W2906214917","https://openalex.org/W2908510526","https://openalex.org/W2919624000","https://openalex.org/W2938774173","https://openalex.org/W2950547518","https://openalex.org/W2952823162","https://openalex.org/W2964054038","https://openalex.org/W3209419355","https://openalex.org/W4287072584","https://openalex.org/W4293775315","https://openalex.org/W4385245566","https://openalex.org/W6714030504","https://openalex.org/W6731203071","https://openalex.org/W6739901393","https://openalex.org/W6741764173","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6756944834","https://openalex.org/W6757817989","https://openalex.org/W6760601182","https://openalex.org/W6764408361","https://openalex.org/W6798855526"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2316271602","https://openalex.org/W2357375963","https://openalex.org/W607893370","https://openalex.org/W629160228","https://openalex.org/W584653787","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Most":[0],"recent":[1],"research":[2],"about":[3],"automatic":[4],"music":[5,21],"transcription":[6,31],"(AMT)":[7],"uses":[8],"convolutional":[9],"neural":[10,14],"networks":[11,15],"and":[12,82,98],"recurrent":[13],"to":[16,23],"model":[17],"the":[18,35,47,53,56,68,72,79,87,103],"mapping":[19],"from":[20],"signals":[22],"symbolic":[24],"notation.":[25],"Based":[26],"on":[27,71,78,86,95],"a":[28,83,92],"high-resolution":[29],"piano":[30],"system,":[32],"we":[33],"explore":[34],"possibility":[36],"of":[37,55],"incorporating":[38],"another":[39],"powerful":[40],"sequence":[41],"transformation":[42],"tool\u2014the":[43],"Transformer\u2014to":[44],"deal":[45],"with":[46],"AMT":[48,64],"problem.":[49],"We":[50,66,90],"argue":[51],"that":[52],"properties":[54],"Transformer":[57,104],"make":[58],"it":[59],"more":[60],"suitable":[61],"for":[62],"certain":[63],"subtasks.":[65],"confirm":[67],"Transformer\u2019s":[69],"superiority":[70],"velocity":[73],"detection":[74],"task":[75],"by":[76],"experiments":[77],"MAESTRO":[80],"dataset":[81],"cross-dataset":[84],"evaluation":[85],"MAPS":[88],"dataset.":[89],"observe":[91],"performance":[93],"improvement":[94],"both":[96],"frame-level":[97],"note-level":[99],"metrics":[100],"after":[101],"introducing":[102],"network.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
