{"id":"https://openalex.org/W4404788072","doi":"https://doi.org/10.1109/taslp.2024.3507568","title":"Towards Efficient and Real-Time Piano Transcription Using Neural Autoregressive Models","display_name":"Towards Efficient and Real-Time Piano Transcription Using Neural Autoregressive Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404788072","doi":"https://doi.org/10.1109/taslp.2024.3507568"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3507568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3507568","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/A5115444778","display_name":"Taegyun Kwon","orcid":"https://orcid.org/0009-0004-8510-872X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Taegyun Kwon","raw_affiliation_strings":["Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055794128","display_name":"Dasaem Jeong","orcid":"https://orcid.org/0009-0002-3655-1181"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dasaem Jeong","raw_affiliation_strings":["Sogang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Sogang University, Seoul, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115444778"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.4017,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82784233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"5106","last_page":"5116"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9945999979972839,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.8194363117218018},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.6993190050125122},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5192318558692932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49066221714019775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23299133777618408},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.21802613139152527},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.11083340644836426}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8194363117218018},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.6993190050125122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5192318558692932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49066221714019775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23299133777618408},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.21802613139152527},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.11083340644836426},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3507568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3507568","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2082290707","https://openalex.org/W2087155953","https://openalex.org/W2096482524","https://openalex.org/W2110007838","https://openalex.org/W2144414181","https://openalex.org/W2162911105","https://openalex.org/W2566755135","https://openalex.org/W2569234605","https://openalex.org/W2753779507","https://openalex.org/W2760103357","https://openalex.org/W2789329504","https://openalex.org/W2906214917","https://openalex.org/W2938774173","https://openalex.org/W2963351448","https://openalex.org/W2973814626","https://openalex.org/W2997591727","https://openalex.org/W3011176162","https://openalex.org/W3095303521","https://openalex.org/W3146994612","https://openalex.org/W3206146520","https://openalex.org/W3209419355","https://openalex.org/W4246193833","https://openalex.org/W6608238415","https://openalex.org/W6637373629","https://openalex.org/W6638826180","https://openalex.org/W6697000175","https://openalex.org/W6714030504","https://openalex.org/W6731203071","https://openalex.org/W6733936739","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6763354517","https://openalex.org/W6764408361","https://openalex.org/W6770469905","https://openalex.org/W6784081880","https://openalex.org/W6784591795","https://openalex.org/W6796569136","https://openalex.org/W6798855526","https://openalex.org/W6803577363","https://openalex.org/W6926129794"],"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/W4362512397","https://openalex.org/W587444722"],"abstract_inverted_index":{"In":[0,128],"recent":[1],"years,":[2],"advancements":[3],"in":[4,20,174],"neural":[5,75],"network":[6],"designs":[7],"and":[8,61,153],"the":[9,21,87,97,102,106,132,154,165],"availability":[10],"of":[11,23,39,44,147],"large-scale":[12],"labeled":[13],"datasets":[14],"have":[15],"led":[16],"to":[17,48,96,100],"significant":[18],"improvements":[19],"accuracy":[22],"piano":[24,51,81],"transcription":[25,52,82],"models.":[26],"However,":[27],"most":[28],"previous":[29],"work":[30,46],"focused":[31],"on":[32,56,105,122,182],"high-performance":[33],"offline":[34],"transcription,":[35],"neglecting":[36],"deliberate":[37],"consideration":[38],"model":[40],"size.":[41],"The":[42],"goal":[43],"this":[45,66],"is":[47],"implement":[49],"real-time":[50,183],"with":[53,135],"a":[54,62,92,117,126],"focus":[55],"achieving":[57,171],"both":[58],"high":[59,151,157,172],"performance":[60,152,173],"lightweight":[63],"model.":[64,83,177],"To":[65],"end,":[67],"we":[68,85,110,130,143,162,179],"propose":[69,144],"novel":[70],"architectures":[71],"for":[72,150,156,170],"convolutional":[73,103],"recurrent":[74],"networks,":[76],"redesigning":[77],"an":[78,136,175],"existing":[79],"autoregressive":[80,133,176],"First,":[84],"extend":[86],"acoustic":[88],"module":[89,99],"by":[90,115],"adding":[91],"frequency-conditioned":[93],"FiLM":[94],"layer":[95],"CNN":[98],"adapt":[101],"filters":[104],"frequency":[107],"axis.":[108],"Second,":[109],"improve":[111],"note-state":[112,123],"sequence":[113],"modeling":[114],"using":[116],"pitchwise":[118],"LSTM":[119],"that":[120,164],"focuses":[121],"transitions":[124],"within":[125],"note.":[127],"addition,":[129],"augment":[131],"connection":[134],"enhanced":[137],"recursive":[138],"context.":[139],"Using":[140],"these":[141],"components,":[142],"two":[145],"types":[146],"models;":[148],"one":[149],"other":[155],"compactness.":[158],"Through":[159],"extensive":[160],"experiments,":[161],"demonstrate":[163],"proposed":[166],"components":[167],"are":[168],"necessary":[169],"Additionally,":[178],"provide":[180],"experiments":[181],"latency.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}