{"id":"https://openalex.org/W6912078945","doi":"https://doi.org/10.5281/zenodo.14877335","title":"A Method for MIDI Velocity Estimation for Piano Performance by a U-Net With Attention and FiLM","display_name":"A Method for MIDI Velocity Estimation for Piano Performance by a U-Net With Attention and FiLM","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6912078945","doi":"https://doi.org/10.5281/zenodo.14877335"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877335","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877335","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877335","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hyon Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyon Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xavier Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.42424862,"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/T11309","display_name":"Music and Audio Processing","score":0.4359000027179718,"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":0.4359000027179718,"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":0.13809999823570251,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.12359999865293503,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.9503999948501587},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.8708000183105469},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7156000137329102},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5134999752044678},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4300000071525574},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.3434999883174896},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.33660000562667847},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.32580000162124634}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.9503999948501587},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8708000183105469},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7156000137329102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6103000044822693},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5297999978065491},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5134999752044678},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42739999294281006},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3255000114440918},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26570001244544983},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877335","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877335","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877335","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877335","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8184825778007507,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"It":[0,46],"is":[1,47],"a":[2,43,49,64,81,90,96,110],"well":[3],"known":[4],"fact":[5],"that":[6,114],"the":[7,18,22,126,139],"dynamics":[8,30],"in":[9,15,42,52],"piano":[10,40,57],"performance":[11,41],"gives":[12],"significant":[13,36],"effect":[14],"expressiveness.":[16],"Taking":[17],"polyphonic":[19],"nature":[20],"of":[21,75,83,116,142],"instrument":[23],"into":[24],"account,":[25],"analysing":[26],"information":[27],"to":[28,38,77],"form":[29],"for":[31,56,66,70],"each":[32,71],"performed":[33],"note":[34],"has":[35],"meaning":[37],"understand":[39],"quantitative":[44],"way.":[45],"also":[48],"key":[50],"element":[51],"an":[53],"education":[54],"context":[55],"learners.":[58],"In":[59],"this":[60],"study,":[61],"we":[62,112],"developed":[63],"model":[65],"estimating":[67],"MIDI":[68],"velocity":[69],"note,":[72],"as":[73],"one":[74],"indicators":[76],"represent":[78],"loudness,":[79],"with":[80,98],"condition":[82],"score":[84],"assuming":[85],"educational":[86],"use":[87],"case,":[88],"by":[89],"Deep":[91],"Neural":[92],"Network":[93],"(DNN)":[94],"utilizing":[95],"U-Net":[97],"Scaled":[99],"Dot-Product":[100],"Attention":[101,117],"(Attention)":[102],"and":[103,118,124,134],"Feature-wise":[104],"Linear":[105],"Modulation":[106],"(FiLM)":[107],"conditioning.":[108],"As":[109],"result,":[111],"prove":[113],"effectiveness":[115],"FiLM":[119],"conditioning,":[120],"improved":[121],"estimation":[122],"accuracy":[123],"achieved":[125],"best":[127],"result":[128],"among":[129],"previous":[130],"researches":[131],"using":[132],"DNNs":[133],"showed":[135],"its":[136],"robustness":[137],"across":[138],"various":[140],"domain":[141],"test":[143],"data.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}