{"id":"https://openalex.org/W4386378247","doi":"https://doi.org/10.3233/jifs-233653","title":"Piano automatic transcription based on transformer","display_name":"Piano automatic transcription based on transformer","publication_year":2023,"publication_date":"2023-09-01","ids":{"openalex":"https://openalex.org/W4386378247","doi":"https://doi.org/10.3233/jifs-233653"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-233653","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-233653","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","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/A5100344808","display_name":"Yuan Wang","orcid":"https://orcid.org/0000-0001-5871-9497"},"institutions":[{"id":"https://openalex.org/I4210128418","display_name":"Nanjing Xiaozhuang University","ror":"https://ror.org/03fnv7n42","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210128418"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Wang","raw_affiliation_strings":["School of Music, NanJing XiaoZhuang University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Music, NanJing XiaoZhuang University, Nanjing, China","institution_ids":["https://openalex.org/I4210128418"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100344808"],"corresponding_institution_ids":["https://openalex.org/I4210128418"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10735524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"5","first_page":"8441","last_page":"8448"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.79178786277771},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.7764862775802612},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7054997682571411},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6088899970054626},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5635548233985901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5360228419303894},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.48836442828178406},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.44678181409835815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4290602207183838},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.416761189699173},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09886705875396729},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09532451629638672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79178786277771},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.7764862775802612},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7054997682571411},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6088899970054626},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5635548233985901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5360228419303894},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.48836442828178406},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.44678181409835815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4290602207183838},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.416761189699173},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09886705875396729},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09532451629638672},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-233653","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-233653","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2001426554","https://openalex.org/W2067922464","https://openalex.org/W2105143211","https://openalex.org/W2107328928","https://openalex.org/W2110007838","https://openalex.org/W2125969424","https://openalex.org/W2590294899","https://openalex.org/W2903739847","https://openalex.org/W3018980093","https://openalex.org/W3046154609","https://openalex.org/W3088265803","https://openalex.org/W3094771832","https://openalex.org/W3209419355","https://openalex.org/W4381186350"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4285232104","https://openalex.org/W2386555541","https://openalex.org/W4242364395","https://openalex.org/W2096042855","https://openalex.org/W2064626218","https://openalex.org/W4301398814","https://openalex.org/W3093121331","https://openalex.org/W2126252750"],"abstract_inverted_index":{"Recent":[0],"years,":[1],"research":[2],"on":[3,35,89,119,141],"automatic":[4,63,158],"music":[5,64,159],"transcription":[6,65,120,145],"has":[7],"made":[8],"significant":[9],"progress":[10],"as":[11],"deep":[12],"learning":[13],"techniques":[14],"have":[15],"been":[16],"validated":[17],"to":[18,39,108,112,131],"demonstrate":[19],"strong":[20],"performance":[21],"in":[22,59],"complex":[23],"data":[24,66],"applications.":[25],"Although":[26],"the":[27,41,53,56,60,73,79,92,97,101,104,114,133,142,149,155],"existing":[28,74],"work":[29,75],"is":[30],"exciting,":[31],"they":[32],"all":[33],"rely":[34],"specific":[36],"domain":[37],"knowledge":[38],"enable":[40],"design":[42,123],"of":[43,62,100,103,116,135,157],"model":[44],"architectures":[45],"and":[46],"training":[47,125],"modes":[48],"for":[49],"different":[50],"tasks.":[51],"At":[52],"same":[54],"time,":[55],"noise":[57,118,130],"generated":[58],"process":[61],"collection":[67],"cannot":[68],"be":[69],"ignored,":[70],"which":[71],"makes":[72],"unsatisfactory.":[76],"To":[77],"address":[78],"issues":[80],"highlighted":[81],"above,":[82],"we":[83,95,122],"propose":[84],"an":[85],"end-to-end":[86],"framework":[87],"based":[88],"Transformer.":[90],"Through":[91],"encoder-decoder":[93],"structure,":[94],"realize":[96],"direct":[98],"conversion":[99],"spectrogram":[102],"collected":[105],"piano":[106,144],"audio":[107],"MIDI":[109],"output.":[110],"Further,":[111],"remove":[113],"impression":[115],"environmental":[117],"quality,":[121],"a":[124],"mechanism":[126],"mixed":[127],"with":[128],"white":[129],"improve":[132,154],"robustness":[134],"our":[136],"proposed":[137,150],"model.":[138],"Our":[139],"experiments":[140],"classic":[143],"datasets":[146],"show":[147],"that":[148],"method":[151],"can":[152],"greatly":[153],"quality":[156],"transcription.":[160]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
