{"id":"https://openalex.org/W4406858688","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848780","title":"Improved Architecture for High-resolution Piano Transcription to Efficiently Capture Acoustic Characteristics of Music Signals","display_name":"Improved Architecture for High-resolution Piano Transcription to Efficiently Capture Acoustic Characteristics of Music Signals","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858688","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848780"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5114425121","display_name":"Jinyi Mi","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jinyi Mi","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734442","display_name":"Se Hoon Kim","orcid":"https://orcid.org/0000-0001-7516-7372"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sehun Kim","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9746000170707703,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9682999849319458,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7472115755081177},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6615712642669678},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6571532487869263},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6198909282684326},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5005829334259033},{"id":"https://openalex.org/keywords/high-resolution","display_name":"High resolution","score":0.49685171246528625},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36547064781188965},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23165124654769897},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08169013261795044},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.06739678978919983},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.06549394130706787}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.7472115755081177},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6615712642669678},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6571532487869263},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6198909282684326},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5005829334259033},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.49685171246528625},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36547064781188965},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23165124654769897},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08169013261795044},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06739678978919983},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.06549394130706787},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W129413713","https://openalex.org/W2076608692","https://openalex.org/W2105143211","https://openalex.org/W2152937398","https://openalex.org/W2183341477","https://openalex.org/W2793617394","https://openalex.org/W2900365452","https://openalex.org/W2902303903","https://openalex.org/W2906214917","https://openalex.org/W2913384670","https://openalex.org/W3081424945","https://openalex.org/W3092879656","https://openalex.org/W3209419355","https://openalex.org/W4225401194","https://openalex.org/W6631190155","https://openalex.org/W6689377339","https://openalex.org/W6714030504","https://openalex.org/W6733936739","https://openalex.org/W6745851314","https://openalex.org/W6746430418","https://openalex.org/W6755182157","https://openalex.org/W6766978945","https://openalex.org/W6784263505","https://openalex.org/W6846575651"],"related_works":["https://openalex.org/W2316271602","https://openalex.org/W2357375963","https://openalex.org/W607893370","https://openalex.org/W629160228","https://openalex.org/W584653787","https://openalex.org/W4362512397","https://openalex.org/W587444722","https://openalex.org/W2022713566","https://openalex.org/W2336023324","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Automatic":[0],"music":[1,19,103],"transcription":[2,46,82,94],"(AMT),":[3],"aiming":[4],"to":[5,54,76,79,96,115,118,164],"convert":[6],"musical":[7,10,119],"signals":[8],"into":[9],"notation,":[11],"is":[12,129,144],"one":[13],"of":[14,36,60,72,102],"the":[15,30,58,70,81,108,112,127,142,165,185],"important":[16],"tasks":[17],"in":[18,45,180],"information":[20],"retrieval.":[21],"Recently,":[22],"previous":[23],"works":[24],"have":[25,123],"applied":[26],"high-resolution":[27,92,166],"labels,":[28],"i.e.,":[29],"continuous":[31],"onset":[32],"and":[33,69,141,183],"offset":[34],"times":[35],"piano":[37,93],"notes,":[38,68],"as":[39,65,111,170],"training":[40],"targets,":[41],"achieving":[42],"substantial":[43],"improvements":[44],"performance.":[47,83],"However,":[48],"there":[49],"still":[50],"remain":[51],"some":[52],"issues":[53],"be":[55,77],"addressed,":[56],"e.g.,":[57],"harmonics":[59],"notes":[61],"are":[62],"sometimes":[63],"recognized":[64],"false":[66],"positive":[67],"size":[71],"AMT":[73,167],"model":[74,95,188],"tends":[75],"larger":[78],"improve":[80],"To":[84],"address":[85],"these":[86],"issues,":[87],"we":[88,106,122],"propose":[89],"an":[90,145],"improved":[91],"well":[97],"capture":[98],"specific":[99],"acoustic":[100],"characteristics":[101],"signals.":[104,120],"First,":[105],"employ":[107],"Constant-Q":[109],"Transform":[110],"input":[113],"representation":[114],"better":[116],"adapt":[117],"Moreover,":[121],"designed":[124],"two":[125],"architectures:":[126],"first":[128],"based":[130],"on":[131,193],"a":[132,152,171],"convolutional":[133],"recurrent":[134],"neural":[135],"network":[136],"(CRNN)":[137],"with":[138,151],"dilated":[139],"convolution,":[140],"second":[143],"encoder-decoder":[146],"architecture":[147],"that":[148],"combines":[149],"CRNN":[150],"non-autoregressive":[153],"Transformer":[154],"decoder.":[155],"We":[156],"conduct":[157],"systematic":[158],"experiments":[159],"for":[160],"our":[161,173],"models.":[162],"Compared":[163],"system":[168],"used":[169],"baseline,":[172],"models":[174],"effectively":[175],"achieve":[176],"1)":[177],"consistent":[178],"improvement":[179],"note-level":[181],"metrics,":[182],"2)":[184],"significant":[186],"smaller":[187],"size,":[189],"which":[190],"shed":[191],"lights":[192],"future":[194],"work.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}