{"id":"https://openalex.org/W4392910816","doi":"https://doi.org/10.1109/icassp48485.2024.10447324","title":"Piano Transcription with Harmonic Attention","display_name":"Piano Transcription with Harmonic Attention","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910816","doi":"https://doi.org/10.1109/icassp48485.2024.10447324"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5037018884","display_name":"Ruimin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]},{"id":"https://openalex.org/I4210157617","display_name":"Huazhong University of Science and Technology Hospital","ror":"https://ror.org/05f9vfg11","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210157617"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruimin Wu","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","institution_ids":["https://openalex.org/I4210157617","https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002684652","display_name":"Xianke Wang","orcid":"https://orcid.org/0000-0001-7037-9800"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]},{"id":"https://openalex.org/I4210157617","display_name":"Huazhong University of Science and Technology Hospital","ror":"https://ror.org/05f9vfg11","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210157617"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianke Wang","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","institution_ids":["https://openalex.org/I4210157617","https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379930","display_name":"Yuqing Li","orcid":"https://orcid.org/0000-0001-7493-9297"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]},{"id":"https://openalex.org/I4210157617","display_name":"Huazhong University of Science and Technology Hospital","ror":"https://ror.org/05f9vfg11","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210157617"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Li","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","institution_ids":["https://openalex.org/I4210157617","https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080649483","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-6616-3633"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]},{"id":"https://openalex.org/I4210157617","display_name":"Huazhong University of Science and Technology Hospital","ror":"https://ror.org/05f9vfg11","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210157617"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","institution_ids":["https://openalex.org/I4210157617","https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056643192","display_name":"Wenqing Cheng","orcid":"https://orcid.org/0000-0001-7840-1195"},"institutions":[{"id":"https://openalex.org/I4210157617","display_name":"Huazhong University of Science and Technology Hospital","ror":"https://ror.org/05f9vfg11","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210157617"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqing Cheng","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology,China","institution_ids":["https://openalex.org/I4210157617","https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Electronic Information and Communications Hubei Provincial Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037018884"],"corresponding_institution_ids":["https://openalex.org/I4210157617","https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":1.1206,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74658671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1256","last_page":"1260"},"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":0.998199999332428,"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":0.9969000220298767,"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":0.858574628829956},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6964101195335388},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6870946884155273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6724045872688293},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6083114147186279},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48048320412635803},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4397771954536438},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.4305969476699829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42759838700294495},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3183959424495697},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.24135109782218933},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.192930668592453},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1418614685535431},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13473355770111084}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.858574628829956},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6964101195335388},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6870946884155273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6724045872688293},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6083114147186279},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48048320412635803},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4397771954536438},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.4305969476699829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42759838700294495},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3183959424495697},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.24135109782218933},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.192930668592453},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1418614685535431},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13473355770111084},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2105143211","https://openalex.org/W2152937398","https://openalex.org/W2198584637","https://openalex.org/W2407685581","https://openalex.org/W3043861921","https://openalex.org/W3081424945","https://openalex.org/W3209419355","https://openalex.org/W3212589040","https://openalex.org/W4224947526","https://openalex.org/W4293363567","https://openalex.org/W4321994636","https://openalex.org/W4383988462","https://openalex.org/W4385245566","https://openalex.org/W6714030504","https://openalex.org/W6733936739","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6798855526","https://openalex.org/W6803577363","https://openalex.org/W6846575651"],"related_works":["https://openalex.org/W2587667458","https://openalex.org/W2164070943","https://openalex.org/W1861882962","https://openalex.org/W2163128389","https://openalex.org/W2121926536","https://openalex.org/W1497667432","https://openalex.org/W2390836177","https://openalex.org/W2568904611","https://openalex.org/W1516921425","https://openalex.org/W2983963786"],"abstract_inverted_index":{"Automatic":[0],"Music":[1],"Transcription":[2],"(AMT)":[3],"aims":[4],"to":[5,45,77,136],"convert":[6],"music":[7],"audio":[8],"into":[9],"digital":[10],"sheet":[11],"music.":[12],"Piano":[13],"transcription":[14,106],"is":[15,30,71,134],"a":[16,60,127],"popular":[17],"but":[18],"challenging":[19],"subtask":[20],"of":[21,102,131],"AMT.":[22],"For":[23],"every":[24,97],"piano":[25,57,105],"pitch,":[26],"the":[27,33,37,49,74,79,92,103,112,117,124,137],"harmonic":[28,58,66,75,80,93],"structure":[29,81],"fixed":[31],"in":[32,48],"frequency":[34],"domain,":[35],"while":[36],"Transformer":[38,95],"based":[39],"on":[40,111],"self-attention":[41],"has":[42],"great":[43],"potential":[44],"extract":[46],"features":[47],"long":[50],"sequence.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,90],"propose":[56],"attention,":[59],"mask":[61,69],"self-attention,":[62],"for":[63],"better":[64],"capturing":[65],"features.":[67],"The":[68,108],"matrix":[70],"designed":[72],"with":[73,126],"prior":[76],"pre-modeling":[78],"during":[82],"calculating":[83],"attention":[84],"scores.":[85],"To":[86],"verify":[87],"its":[88],"effectiveness,":[89],"append":[91],"attention-based":[94],"after":[96],"convolutional":[98],"neural":[99],"network":[100],"block":[101],"High-resolution":[104],"system.":[107,139],"evaluation":[109],"results":[110],"MAESTRO":[113],"dataset":[114],"show":[115],"that":[116],"proposed":[118],"model":[119],"achieves":[120],"comprehensive":[121],"improvements":[122],"over":[123],"baseline,":[125],"note":[128],"F1":[129],"score":[130],"97.33%,":[132],"which":[133],"comparable":[135],"state-of-the-art":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
