{"id":"https://openalex.org/W4313182189","doi":"https://doi.org/10.1109/icfsp55781.2022.9924773","title":"Transcription of Audio to MIDI Using Deep Learning","display_name":"Transcription of Audio to MIDI Using Deep Learning","publication_year":2022,"publication_date":"2022-09-07","ids":{"openalex":"https://openalex.org/W4313182189","doi":"https://doi.org/10.1109/icfsp55781.2022.9924773"},"language":"en","primary_location":{"id":"doi:10.1109/icfsp55781.2022.9924773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfsp55781.2022.9924773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Frontiers of Signal Processing (ICFSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102984797","display_name":"Patrick J. Donnelly","orcid":"https://orcid.org/0000-0003-1033-5931"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick J. Donnelly","raw_affiliation_strings":["Oregon State University,Department of Computer Science,Corvallis,OR,United States","Department of Computer Science, Oregon State University, Corvallis, OR, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University,Department of Computer Science,Corvallis,OR,United States","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Department of Computer Science, Oregon State University, Corvallis, OR, United States","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047833559","display_name":"Victoria Ebert","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victoria Ebert","raw_affiliation_strings":["Oregon State University,Department of Computer Science,Corvallis,OR,United States","Department of Computer Science, Oregon State University, Corvallis, OR, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University,Department of Computer Science,Corvallis,OR,United States","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Department of Computer Science, Oregon State University, Corvallis, OR, United States","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"130","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9977999925613403,"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":0.995199978351593,"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/midi","display_name":"MIDI","score":0.8449743986129761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7660605907440186},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.764477014541626},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6894291639328003},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6469049453735352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6425800919532776},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5576171278953552},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5056633949279785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4367412328720093},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43344321846961975},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11790966987609863}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.8449743986129761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660605907440186},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.764477014541626},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6894291639328003},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6469049453735352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6425800919532776},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5576171278953552},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5056633949279785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4367412328720093},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43344321846961975},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11790966987609863},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.1109/icfsp55781.2022.9924773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfsp55781.2022.9924773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 7th International Conference on Frontiers of Signal Processing (ICFSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4242364395","https://openalex.org/W2153331925","https://openalex.org/W2369521057","https://openalex.org/W2126252750","https://openalex.org/W2340483794","https://openalex.org/W1797486849","https://openalex.org/W2132597408","https://openalex.org/W2584191612"],"abstract_inverted_index":{"We":[0,50],"investigate":[1],"automatic":[2],"transcription":[3,105],"of":[4,42,45,62,73,96],"polyphonic":[5],"piano":[6],"music":[7,104],"with":[8],"recurrent":[9],"neural":[10],"networks":[11],"directly":[12,39,106],"from":[13,47,107],"raw":[14,108],"audio.":[15,109],"Previous":[16],"approaches":[17],"to":[18,102],"this":[19],"task":[20],"rely":[21],"on":[22,40,54],"spectrograms":[23],"or":[24],"other":[25],"features":[26],"extracted":[27],"for":[28],"training,":[29],"which":[30],"requires":[31],"timely":[32],"pre-processing.":[33],"In":[34],"our":[35,52],"approach,":[36],"we":[37],"train":[38],"sequences":[41],"64":[43],"milliseconds":[44],"samples":[46],"the":[48,55,70,74,81,87,94],"waveform.":[49],"evaluate":[51],"models":[53],"MAESTRO":[56],"dataset":[57],"and":[58,64,84],"achieve":[59],"promising":[60],"levels":[61],"pitch":[63],"onset":[65],"accuracy":[66],"but":[67],"difficulty":[68],"detecting":[69],"correct":[71],"offset":[72],"notes.":[75],"Our":[76],"approach":[77],"also":[78],"enables":[79],"learning":[80,100],"note":[82],"pitches":[83],"velocities":[85],"at":[86],"same":[88],"time.":[89],"Together":[90],"these":[91],"results":[92],"demonstrate":[93],"potential":[95],"relatively":[97],"simple":[98],"deep":[99],"architectures":[101],"learn":[103]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}