{"id":"https://openalex.org/W7108636939","doi":"https://doi.org/10.5281/zenodo.17811438","title":"Understanding Performance Limitations in Automatic Drum Transcription","display_name":"Understanding Performance Limitations in Automatic Drum Transcription","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108636939","doi":"https://doi.org/10.5281/zenodo.17811438"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811438","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811438","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.17811438","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Philipp Weyers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philipp Weyers","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Christian Uhle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Uhle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Meinard M\u00fcller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meinard M\u00fcller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Matthias Lang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias Lang","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":0.53722123,"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":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9699000120162964,"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":0.9699000120162964,"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":0.01979999989271164,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.002099999925121665,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/drum","display_name":"Drum","score":0.8101999759674072},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.670799970626831},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6524999737739563},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.46950000524520874},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4293000102043152}],"concepts":[{"id":"https://openalex.org/C175845324","wikidata":"https://www.wikidata.org/wiki/Q2738285","display_name":"Drum","level":2,"score":0.8101999759674072},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.670799970626831},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6524999737739563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5564000010490417},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.46950000524520874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.39309999346733093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.26809999346733093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811438","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811438","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.17811438","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811438","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,80],"Automatic":[3],"Drum":[4],"Transcription":[5],"(ADT)":[6],"have":[7],"improved":[8],"overall":[9,170],"transcription":[10,79,130,137,171],"performance.":[11],"However,":[12],"state-of-the-art":[13],"(SOTA)":[14],"models":[15,167],"still":[16],"struggle":[17],"with":[18],"certain":[19],"drum":[20,78,115,129,149],"classes,":[21],"particularly":[22],"toms":[23],"and":[24,26,73,96,109,168],"cymbals,":[25],"the":[27,42,81,87,112,152],"specific":[28],"factors":[29],"limiting":[30,89],"their":[31],"performance":[32,57,101,154],"remain":[33],"unclear.":[34],"This":[35,145],"paper":[36],"addresses":[37],"this":[38],"gap":[39],"by":[40,103],"leveraging":[41],"Separate-Tracks-Annotate-Resynthesize":[43],"Drums":[44],"(STAR":[45],"Drums)":[46],"dataset":[47,51],"to":[48,71,164],"create":[49],"multiple":[50],"versions":[52],"that":[53,147],"systematically":[54],"eliminate":[55],"potential":[56],"constraints.":[58],"We":[59],"conduct":[60],"experiments":[61],"using":[62],"three":[63],"common":[64],"ADT":[65,159],"deep":[66],"neural":[67],"network":[68],"(DNN)":[69],"architectures":[70],"identify":[72],"quantify":[74],"these":[75],"limitations.":[76],"For":[77,128],"presence":[82],"of":[83,131],"melodic":[84,94],"instruments":[85,95],"(DTM),":[86],"primary":[88],"factor":[90],"is":[91,138],"interference":[92],"from":[93,99],"singing.":[97],"Aside":[98],"this,":[100],"improves":[102],"approximately":[104],"five":[105],"percent":[106],"when":[107,140],"training":[108],"testing":[110],"use":[111],"same":[113],"single":[114],"kit,":[116],"only":[117],"strong":[118],"onsets":[119,142],"are":[120,124,143,151],"present,":[121],"or":[122],"notes":[123],"not":[125],"played":[126],"simultaneously.":[127],"drum-only":[132],"recordings":[133],"(DTD),":[134],"nearly":[135],"error-free":[136],"achieved":[139],"simultaneous":[141],"removed.":[144],"confirms":[146],"overlapping":[148],"hits":[150],"main":[153],"constraint.":[155],"By":[156],"identifying":[157],"key":[158],"challenges,":[160],"we":[161],"provide":[162],"insights":[163],"enhance":[165],"SOTA":[166],"improve":[169],"accuracy.":[172]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-05T00:00:00"}