{"id":"https://openalex.org/W4387870682","doi":"https://doi.org/10.1109/mlsp55844.2023.10285985","title":"A U-Net Based Architecture for Automatic Music Transcription","display_name":"A U-Net Based Architecture for Automatic Music Transcription","publication_year":2023,"publication_date":"2023-09-17","ids":{"openalex":"https://openalex.org/W4387870682","doi":"https://doi.org/10.1109/mlsp55844.2023.10285985"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55844.2023.10285985","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp55844.2023.10285985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5067809229","display_name":"Michele Scarpiniti","orcid":"https://orcid.org/0000-0002-3164-6256"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Michele Scarpiniti","raw_affiliation_strings":["Sapienza University of Rome via Eudossiana 18,Department of Information Engineering, Electronics and Telecommunications (DIET),Rome,Italy,00184"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome via Eudossiana 18,Department of Information Engineering, Electronics and Telecommunications (DIET),Rome,Italy,00184","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093111517","display_name":"Edoardo Sigismondi","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Edoardo Sigismondi","raw_affiliation_strings":["Sapienza University of Rome via Eudossiana 18,Department of Information Engineering, Electronics and Telecommunications (DIET),Rome,Italy,00184"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome via Eudossiana 18,Department of Information Engineering, Electronics and Telecommunications (DIET),Rome,Italy,00184","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019647783","display_name":"Danilo Comminiello","orcid":"https://orcid.org/0000-0003-4067-4504"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Comminiello","raw_affiliation_strings":["Sapienza University of Rome via Eudossiana 18,Department of Information Engineering, Electronics and Telecommunications (DIET),Rome,Italy,00184"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome via Eudossiana 18,Department of Information Engineering, Electronics and Telecommunications (DIET),Rome,Italy,00184","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039283820","display_name":"Aurelio Uncini","orcid":"https://orcid.org/0000-0002-5793-0917"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Aurelio Uncini","raw_affiliation_strings":["Sapienza University of Rome via Eudossiana 18,Department of Information Engineering, Electronics and Telecommunications (DIET),Rome,Italy,00184"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome via Eudossiana 18,Department of Information Engineering, Electronics and Telecommunications (DIET),Rome,Italy,00184","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067809229"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1429734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9922999739646912,"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":0.9864000082015991,"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":0.7811485528945923},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6882448196411133},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6648319363594055},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6267044544219971},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.6075528860092163},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5999629497528076},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5622861385345459},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5303932428359985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4905985891819},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4509276747703552},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.42606061697006226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811485528945923},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6882448196411133},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6648319363594055},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6267044544219971},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.6075528860092163},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5999629497528076},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5622861385345459},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5303932428359985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4905985891819},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4509276747703552},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.42606061697006226},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":2,"locations":[{"id":"doi:10.1109/mlsp55844.2023.10285985","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp55844.2023.10285985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1692643","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1692643","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W89231944","https://openalex.org/W2096482524","https://openalex.org/W2104298926","https://openalex.org/W2105143211","https://openalex.org/W2105343238","https://openalex.org/W2110007838","https://openalex.org/W2120809168","https://openalex.org/W2121148209","https://openalex.org/W2144414181","https://openalex.org/W2198584637","https://openalex.org/W2295460171","https://openalex.org/W2497836768","https://openalex.org/W2938774173","https://openalex.org/W2939988664","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W3095303521","https://openalex.org/W3160787318","https://openalex.org/W3206146520","https://openalex.org/W4293775315","https://openalex.org/W6603626069","https://openalex.org/W6678022326","https://openalex.org/W6697000175","https://openalex.org/W6733936739","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6930559537"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4242364395","https://openalex.org/W2386555541","https://openalex.org/W3042962886","https://openalex.org/W2920621887","https://openalex.org/W2187442448","https://openalex.org/W2126252750","https://openalex.org/W1797486849","https://openalex.org/W2584191612"],"abstract_inverted_index":{"Automatic":[0],"Music":[1],"Transcription":[2],"(AMT)":[3],"is":[4,27],"a":[5,53,92],"complex":[6],"matter":[7],"involving":[8],"several":[9],"researchers.":[10],"Recently,":[11],"due":[12],"to":[13,65,95],"the":[14,63,87,98,109,115,118,122],"powerful":[15],"Deep":[16],"Learning":[17],"techniques,":[18],"many":[19],"effective":[20],"solutions":[21],"have":[22],"been":[23],"proposed.":[24],"However,":[25],"there":[26],"still":[28],"room":[29],"for":[30],"improvement.":[31],"To":[32],"this":[33,36],"purpose,":[34],"in":[35,101],"paper,":[37],"we":[38],"propose":[39],"an":[40],"architecture":[41],"based":[42],"on":[43,108],"two":[44],"U-Net":[45],"models":[46],"exploiting":[47],"Convolutional":[48],"Neural":[49],"Networks":[50],"(CNNs)":[51],"and":[52,76,121],"Bidirectional":[54],"Long-Short":[55],"Term":[56],"Memory":[57],"(BiLSTM)":[58],"unit,":[59],"aiming":[60],"at":[61],"improving":[62],"wave":[64],"MIDI":[66],"transcription":[67],"performance.":[68],"This":[69],"couple":[70],"of":[71,117],"U-Nets":[72],"act":[73],"as":[74],"onset":[75],"offset":[77],"detectors,":[78],"respectively,":[79],"whose":[80],"information":[81],"are":[82],"jointly":[83],"used":[84],"along":[85],"with":[86],"input":[88],"mel":[89],"spectrogram":[90],"into":[91],"third":[93],"model":[94],"find":[96],"all":[97],"active":[99],"notes":[100],"each":[102],"time-frame.":[103],"Some":[104],"numerical":[105],"results,":[106],"obtained":[107],"well":[110],"known":[111],"MAPS":[112],"dataset,":[113],"show":[114],"effectiveness":[116],"proposed":[119],"idea":[120],"advantages":[123],"over":[124],"similar":[125],"state-of-the-art":[126],"approaches.":[127]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}