{"id":"https://openalex.org/W4417222068","doi":"https://doi.org/10.1186/s13636-025-00428-z","title":"Sound and music biases in deep music transcription models: a systematic analysis","display_name":"Sound and music biases in deep music transcription models: a systematic analysis","publication_year":2025,"publication_date":"2025-12-11","ids":{"openalex":"https://openalex.org/W4417222068","doi":"https://doi.org/10.1186/s13636-025-00428-z"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00428-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00428-z","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13636-025-00428-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030064907","display_name":"Luk\u00e1\u0161 Samuel Mart\u00e1k","orcid":"https://orcid.org/0000-0003-0723-3010"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Luk\u00e1\u0161\u00a0Samuel Mart\u00e1k","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria","Linz Institute of Technology AI Lab, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria"],"raw_orcid":"https://orcid.org/0000-0003-0723-3010","affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Linz Institute of Technology AI Lab, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112717712","display_name":"Patricia S. Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Patricia Hu","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria","Linz Institute of Technology AI Lab, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Linz Institute of Technology AI Lab, Johannes Kepler University Linz, Altenberger Stra\u00dfe 69, 4040, Linz, Upper Austria, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5030064907"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.6317,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73396138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"2026","issue":"1","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":0.9890000224113464,"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":0.9890000224113464,"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":0.005499999970197678,"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":0.0010999999940395355,"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/polyphony","display_name":"Polyphony","score":0.8051000237464905},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6233000159263611},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.6000000238418579},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.5716000199317932},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5112000107765198},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5065000057220459},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3702999949455261},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3361999988555908},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.3176000118255615}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8051000237464905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044000267982483},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6233000159263611},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.6000000238418579},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5239999890327454},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5112000107765198},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5065000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3864000141620636},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3361999988555908},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C178884764","wikidata":"https://www.wikidata.org/wiki/Q510293","display_name":"Musical acoustics","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C542929976","wikidata":"https://www.wikidata.org/wiki/Q9730","display_name":"Classical music","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C133905733","wikidata":"https://www.wikidata.org/wiki/Q2629238","display_name":"Multifractal system","level":3,"score":0.25429999828338623},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13636-025-00428-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00428-z","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2512.14602","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.14602","pdf_url":"https://arxiv.org/pdf/2512.14602","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:cdcbfb9fefd7413cb2d4f1108d463662","is_oa":true,"landing_page_url":"https://doaj.org/article/cdcbfb9fefd7413cb2d4f1108d463662","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2026, Iss 1, Pp 1-24 (2025)","raw_type":"article"},{"id":"pmh:oai:epub.jku.at/:13855381","is_oa":true,"landing_page_url":"https://epub.jku.at/doi/10.1186/s13636-025-00428-z","pdf_url":null,"source":{"id":"https://openalex.org/S4306401788","display_name":"University Library Linz repository (Johannes Kepler Universitat Linz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121883995","host_organization_name":"Johannes Kepler University of Linz","host_organization_lineage":["https://openalex.org/I121883995"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00428-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00428-z","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4836643065","display_name":null,"funder_award_id":"101019375","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"}],"funders":[{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1902027874","https://openalex.org/W1997948862","https://openalex.org/W1999325521","https://openalex.org/W2070792261","https://openalex.org/W2110007838","https://openalex.org/W2139686198","https://openalex.org/W2144414181","https://openalex.org/W2150319510","https://openalex.org/W2152937398","https://openalex.org/W2198584637","https://openalex.org/W2615019929","https://openalex.org/W3035609550","https://openalex.org/W3094138986","https://openalex.org/W3209419355","https://openalex.org/W3210315957","https://openalex.org/W4300960980","https://openalex.org/W4391640266","https://openalex.org/W4402952717","https://openalex.org/W4408355985"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Music":[1],"Transcription":[2],"(AMT)\u2014the":[3],"task":[4],"of":[5,28,34,114,121,147,163,228,232],"converting":[6],"music":[7,31],"audio":[8],"into":[9],"note":[10],"representations":[11],"\u2014":[12],"has":[13,39],"seen":[14],"rapid":[15],"progress,":[16],"driven":[17],"largely":[18],"by":[19],"deep":[20,238],"learning":[21],"systems.":[22,240],"Due":[23],"to":[24,59,168,173,184],"the":[25,35,83,98,119,127,229,233],"limited":[26],"availability":[27],"richly":[29],"annotated":[30],"datasets,":[32],"much":[33],"progress":[36],"in":[37,73,78,87,214,237],"AMT":[38,124,239],"been":[40],"concentrated":[41],"on":[42,70,126],"classical":[43],"piano":[44],"music,":[45],"and":[46,90,108,134,143,170],"even":[47],"a":[48,158],"few":[49],"very":[50],"specific":[51,151],"datasets.":[52],"Whether":[53],"these":[54,223],"systems":[55,125],"can":[56],"generalize":[57],"effectively":[58],"other":[60],"musical":[61,84,185,219],"contexts":[62],"remains":[63],"an":[64],"open":[65],"question.":[66],"Complementing":[67],"recent":[68],"studies":[69],"distribution":[71,115,152,220],"shifts":[72],"sound":[74],"(e.g.,":[75],"recording":[76],"conditions),":[77],"this":[79,94],"work":[80],"we":[81,96,156,176],"investigate":[82],"dimension\u2014specifically,":[85],"variations":[86],"genre,":[88,105],"dynamics,":[89],"polyphony":[91],"levels.":[92],"To":[93],"end,":[95],"introduce":[97],"MDS":[99,128],"corpus,":[100],"comprising":[101],"three":[102],"distinct":[103],"subsets\u2014(1)":[104],"(2)":[106],"random,":[107],"(3)":[109],"MAEtest\u2014to":[110],"emulate":[111],"different":[112],"axes":[113],"shift.":[116],"We":[117],"evaluate":[118],"performance":[120,137,148,161,216],"several":[122],"state-of-the-art":[123],"corpus":[129,234],"using":[130],"both":[131],"traditional":[132],"information-retrieval":[133],"musically":[135],"informed":[136,191],"metrics.":[138],"Our":[139],"extensive":[140],"evaluation":[141,192],"isolates":[142],"exposes":[144],"varying":[145],"degrees":[146],"degradation":[149],"under":[150,217],"shifts.":[153,221],"In":[154],"particular,":[155],"measure":[157],"note-level":[159],"F1":[160],"drop":[162],"20":[164],"percentage":[165],"points":[166],"due":[167,172],"sound,":[169],"14":[171],"genre.":[174],"Generally,":[175],"find":[177],"that":[178],"dynamics":[179],"estimation":[180],"proves":[181],"more":[182],"vulnerable":[183],"variation":[186],"than":[187],"onset":[188],"prediction.":[189],"Musically":[190],"metrics,":[193],"particularly":[194],"those":[195],"capturing":[196],"harmonic":[197],"structure,":[198],"help":[199],"identify":[200],"potential":[201],"contributing":[202],"factors.":[203],"Furthermore,":[204],"experiments":[205],"with":[206],"randomly":[207],"generated,":[208],"non-musical":[209],"sequences":[210],"reveal":[211],"clear":[212],"limitations":[213],"system":[215],"extreme":[218],"Altogether,":[222],"findings":[224],"offer":[225],"new":[226],"evidence":[227],"persistent":[230],"impact":[231],"bias":[235],"problem":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-12-11T00:00:00"}