{"id":"https://openalex.org/W6931260264","doi":"https://doi.org/10.5281/zenodo.4285416","title":"Automatic Music Transcription and Instrument Transposition with Differentiable Rendering","display_name":"Automatic Music Transcription and Instrument Transposition with Differentiable Rendering","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W6931260264","doi":"https://doi.org/10.5281/zenodo.4285416"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.4285416","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4285416","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.4285416","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hayato Sumino","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hayato Sumino","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Adrien Bitton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrien Bitton","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lisa Kawai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lisa Kawai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Philippe Esling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philippe Esling","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Tatsuya Harada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tatsuya Harada","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33496537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12703","display_name":"Oil Palm Production and Sustainability","score":0.23800000548362732,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12703","display_name":"Oil Palm Production and Sustainability","score":0.23800000548362732,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10005","display_name":"Ecology and Vegetation Dynamics Studies","score":0.1899999976158142,"subfield":{"id":"https://openalex.org/subfields/2309","display_name":"Nature and Landscape Conservation"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.057999998331069946,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.7836999893188477},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7124000191688538},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6169999837875366},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.47870001196861267},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.4700999855995178},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4343000054359436},{"id":"https://openalex.org/keywords/transposition","display_name":"Transposition (logic)","score":0.3508000075817108}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.7836999893188477},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7124000191688538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7041000127792358},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5508999824523926},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4690000116825104},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C12455157","wikidata":"https://www.wikidata.org/wiki/Q7835331","display_name":"Transposition (logic)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34869998693466187},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.3000999987125397},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.25529998540878296},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.4285416","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4285416","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.4285416","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4285416","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"music":[1],"transcription":[2,87],"aims":[3],"to":[4,70],"extract":[5],"a":[6,10,118],"musical":[7],"score":[8],"from":[9,28,121],"given":[11],"audio":[12,115],"signal.":[13,65,130],"Conventional":[14],"machine":[15],"learning":[16],"frameworks":[17],"usually":[18],"address":[19],"this":[20,38,75,92],"task":[21],"by":[22,113],"relying":[23],"solely":[24,91],"on":[25],"error":[26,78],"back-propagation":[27],"annotated":[29],"MIDI":[30],"data,":[31],"without":[32],"consideration":[33],"for":[34],"acoustic":[35,50,93],"similarities.":[36],"In":[37],"study,":[39],"we":[40],"complement":[41],"the":[42,56,63,80,84,122,128],"onset":[43],"and":[44,59,72,99],"frames":[45],"prediction":[46],"objective":[47],"with":[48,83],"an":[49],"distance,":[51],"through":[52],"differentiable":[53],"rendering":[54],"of":[55,62,117],"estimated":[57],"piano-roll":[58],"approximate":[60],"reconstruction":[61,77],"analyzed":[64],"We":[66],"apply":[67],"our":[68,105],"method":[69,106],"piano":[71],"show":[73],"that":[74],"added":[76],"improves":[79],"performance":[81],"achieved":[82],"usual":[85],"supervised":[86],"loss.":[88],"Moreover,":[89],"using":[90,114],"criterion":[94],"allows":[95],"fully":[96],"unsupervised":[97],"training":[98],"results":[100],"outperforming":[101],"classical":[102],"techniques.":[103],"Finally,":[104],"also":[107],"enables":[108],"performing":[109],"automatic":[110],"instrument":[111,120],"transposition":[112],"samples":[116],"different":[119],"original":[123],"sound":[124],"source":[125],"when":[126],"reconstructing":[127],"input":[129]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
