{"id":"https://openalex.org/W3209419355","doi":"https://doi.org/10.1109/taslp.2021.3121991","title":"High-Resolution Piano Transcription With Pedals by Regressing Onset and Offset Times","display_name":"High-Resolution Piano Transcription With Pedals by Regressing Onset and Offset Times","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3209419355","doi":"https://doi.org/10.1109/taslp.2021.3121991","mag":"3209419355"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3121991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3121991","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/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["ByteDance, Shanghai, China, (e-mail: qiuqiangkong@gmail.com)","[ByteDance, Shanghai, China, (e-mail: qiuqiangkong@gmail.com)]"],"affiliations":[{"raw_affiliation_string":"ByteDance, Shanghai, China, (e-mail: qiuqiangkong@gmail.com)","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"[ByteDance, Shanghai, China, (e-mail: qiuqiangkong@gmail.com)]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081720612","display_name":"Bochen Li","orcid":"https://orcid.org/0000-0002-8304-6973"},"institutions":[{"id":"https://openalex.org/I2800240351","display_name":"Mountain View College","ror":"https://ror.org/04fh8an03","country_code":"US","type":"education","lineage":["https://openalex.org/I1291072267","https://openalex.org/I2800240351"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bochen Li","raw_affiliation_strings":["Mountain View, United States, (e-mail: bochenli@bytedance.com)","[Mountain View, United States, (e-mail: bochenli@bytedance.com)]"],"affiliations":[{"raw_affiliation_string":"Mountain View, United States, (e-mail: bochenli@bytedance.com)","institution_ids":["https://openalex.org/I2800240351"]},{"raw_affiliation_string":"[Mountain View, United States, (e-mail: bochenli@bytedance.com)]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104098658","display_name":"Xuchen Song","orcid":null},"institutions":[{"id":"https://openalex.org/I903994226","display_name":"Xuchang University","ror":"https://ror.org/03k174p87","country_code":"CN","type":"education","lineage":["https://openalex.org/I903994226"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuchen Song","raw_affiliation_strings":["Mountain View, United States, (e-mail: xuchen.song@bytedance.com)","[Mountain View, United States, (e-mail: xuchen.song@bytedance.com)]"],"affiliations":[{"raw_affiliation_string":"Mountain View, United States, (e-mail: xuchen.song@bytedance.com)","institution_ids":["https://openalex.org/I903994226"]},{"raw_affiliation_string":"[Mountain View, United States, (e-mail: xuchen.song@bytedance.com)]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101137823","display_name":"Yuan Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Yuan Wan","raw_affiliation_strings":["Shanghai, China, (e-mail: wanyuan.0626@bytedance.com)","[Shanghai, China, (e-mail: wanyuan.0626@bytedance.com)]"],"affiliations":[{"raw_affiliation_string":"Shanghai, China, (e-mail: wanyuan.0626@bytedance.com)","institution_ids":["https://openalex.org/I1292318990"]},{"raw_affiliation_string":"[Shanghai, China, (e-mail: wanyuan.0626@bytedance.com)]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["AI Lab, ByteDance, Mountain View, California, United States, (e-mail: wangyuxuan.11@bytedance.com)","[AI Lab, ByteDance, Mountain View, California, United States, (e-mail: wangyuxuan.11@bytedance.com)]"],"affiliations":[{"raw_affiliation_string":"AI Lab, ByteDance, Mountain View, California, United States, (e-mail: wangyuxuan.11@bytedance.com)","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"[AI Lab, ByteDance, Mountain View, California, United States, (e-mail: wangyuxuan.11@bytedance.com)]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072482416"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":8.0253,"has_fulltext":false,"cited_by_count":80,"citation_normalized_percentile":{"value":0.98302026,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"3707","last_page":"3717"},"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":0.9976999759674072,"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":0.9965000152587891,"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":0.7409565448760986},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.7249220013618469},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.7189490795135498},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6876727938652039},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6217295527458191},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5227406620979309},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.502694845199585},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41016435623168945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3940128684043884},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34787455201148987},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09596052765846252},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09137594699859619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409565448760986},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.7249220013618469},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.7189490795135498},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6876727938652039},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6217295527458191},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5227406620979309},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.502694845199585},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41016435623168945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3940128684043884},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34787455201148987},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09596052765846252},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09137594699859619},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3121991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3121991","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W37699876","https://openalex.org/W189345193","https://openalex.org/W1522301498","https://openalex.org/W1540905550","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1974548373","https://openalex.org/W2042283011","https://openalex.org/W2086127342","https://openalex.org/W2095705004","https://openalex.org/W2096354165","https://openalex.org/W2105143211","https://openalex.org/W2110007838","https://openalex.org/W2113217465","https://openalex.org/W2121148209","https://openalex.org/W2142464052","https://openalex.org/W2144414181","https://openalex.org/W2152937398","https://openalex.org/W2158983491","https://openalex.org/W2160136308","https://openalex.org/W2198584637","https://openalex.org/W2295460171","https://openalex.org/W2296201206","https://openalex.org/W2395696594","https://openalex.org/W2404620398","https://openalex.org/W2407685581","https://openalex.org/W2522399191","https://openalex.org/W2531457347","https://openalex.org/W2773294482","https://openalex.org/W2773636018","https://openalex.org/W2906214917","https://openalex.org/W2913384670","https://openalex.org/W2937941430","https://openalex.org/W2938774173","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W2952823162","https://openalex.org/W2963037989","https://openalex.org/W2975281968","https://openalex.org/W3006528054","https://openalex.org/W3046154609","https://openalex.org/W3094550259","https://openalex.org/W3095303521","https://openalex.org/W4293775315","https://openalex.org/W4295312788","https://openalex.org/W6601523149","https://openalex.org/W6607768639","https://openalex.org/W6631190155","https://openalex.org/W6632295558","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6678022326","https://openalex.org/W6681236507","https://openalex.org/W6697000175","https://openalex.org/W6697237593","https://openalex.org/W6712027155","https://openalex.org/W6712946787","https://openalex.org/W6714030504","https://openalex.org/W6728773792","https://openalex.org/W6733936739","https://openalex.org/W6745851314","https://openalex.org/W6746760656","https://openalex.org/W6746836464","https://openalex.org/W6755182157","https://openalex.org/W6764408361","https://openalex.org/W6766978945","https://openalex.org/W6768334536","https://openalex.org/W6774020473","https://openalex.org/W7052173577"],"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/W587444722","https://openalex.org/W2022713566","https://openalex.org/W4362512397","https://openalex.org/W633023889","https://openalex.org/W2357210383"],"abstract_inverted_index":{"Automatic":[0],"music":[1],"transcription":[2,44,96],"(AMT)":[3],"is":[4,46,54,147,191],"the":[5,43,49,79,129,169,192,197,203],"task":[6],"of":[7,38,57,59,85,93,117,135,166,178,188,208],"transcribing":[8],"audio":[9,86],"recordings":[10],"into":[11],"symbolic":[12],"representations.":[13],"Recently,":[14],"neural":[15],"network":[16],"based":[17],"methods":[18],"have":[19,25,201],"been":[20],"applied":[21],"to":[22,48,63,78,126,149,156],"AMT,":[23],"and":[24,36,66,82,114,132,138,152,175,206],"achieved":[26],"state-of-the-art":[27],"results.":[28],"However,":[29],"many":[30],"previous":[31,73,157,173],"systems":[32,75],"only":[33],"detect":[34],"onset":[35,65,81,113,131,151,164,185],"offset":[37,67,83,115,133,153],"notes":[39,137],"in":[40],"frame-wise,":[41],"so":[42],"resolution":[45],"limited":[47,91],"frame":[50],"hop":[51],"size.":[52],"There":[53],"a":[55,105,183],"lack":[56],"research":[58,92],"using":[60],"different":[61],"strategies":[62],"encode":[64],"targets":[68],"for":[69],"training.":[70],"In":[71,100],"addition,":[72],"AMT":[74,107,145],"are":[76,90],"sensitive":[77],"misaligned":[80,150],"labels":[84,154],"recordings.":[87],"Furthermore,":[88],"there":[89],"sustain":[94],"pedal":[95,139,184],"on":[97,168,196],"large-scale":[98],"datasets.":[99],"this":[101],"article,":[102],"we":[103,122],"propose":[104,123],"high-resolution":[106],"system":[108,146,161,177,181],"trained":[109],"by":[110],"regressing":[111],"precise":[112,130],"times":[116,134],"piano":[118,136],"notes.":[119],"At":[120],"inference,":[121],"an":[124,163],"algorithm":[125],"analytically":[127],"calculate":[128],"events.":[140],"We":[141,200],"show":[142],"that":[143],"our":[144,209],"robust":[148],"compared":[155],"systems.":[158],"Our":[159,180],"proposed":[160],"achieves":[162,182],"F1":[165,186],"96.72%":[167],"MAESTRO":[170,198],"dataset,":[171],"outperforming":[172],"onsets":[174],"frames":[176],"94.80%.":[179],"score":[187],"91.86%,":[189],"which":[190],"first":[193],"benchmark":[194],"result":[195],"dataset.":[199],"released":[202],"source":[204],"code":[205],"checkpoints":[207],"work":[210],"at":[211],"https://github.com/bytedance/piano_transcription.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}