{"id":"https://openalex.org/W6911821232","doi":"https://doi.org/10.5281/zenodo.14877387","title":"From Audio Encoders to Piano Judges: Benchmarking Performance Understanding for Solo Piano","display_name":"From Audio Encoders to Piano Judges: Benchmarking Performance Understanding for Solo Piano","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6911821232","doi":"https://doi.org/10.5281/zenodo.14877387"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877387","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877387","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.14877387","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jinhua Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinhua Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Simon Dixon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Dixon","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.8555999994277954,"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":0.8555999994277954,"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":0.07540000230073929,"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":0.023900000378489494,"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/piano","display_name":"Piano","score":0.932200014591217},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8029000163078308},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6046000123023987},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5206000208854675},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41190001368522644},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3806999921798706},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3521000146865845}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.932200014591217},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8029000163078308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.605400025844574},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47600001096725464},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C43091099","wikidata":"https://www.wikidata.org/wiki/Q1067788","display_name":"Through-the-lens metering","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2779685156","wikidata":"https://www.wikidata.org/wiki/Q6942545","display_name":"Musical expression","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2621000111103058},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877387","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877387","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.14877387","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877387","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":[{"score":0.522333562374115,"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":[],"abstract_inverted_index":{"Our":[0,96],"study":[1,127],"investigates":[2],"an":[3],"approach":[4,98],"for":[5,64,136],"understanding":[6,30],"musical":[7],"performances":[8],"through":[9],"the":[10,18,117,141],"lens":[11],"of":[12,20,143],"audio":[13,70],"encoding":[14],"models,":[15],"focusing":[16],"on":[17,128],"domain":[19],"solo":[21],"Western":[22],"classical":[23],"piano":[24,55],"music.":[25],"Compared":[26],"to":[27,85],"composition-level":[28],"attribute":[29],"such":[31],"as":[32,116],"key":[33],"or":[34],"genre,":[35],"we":[36,123],"identify":[37],"a":[38,59,125],"knowledge":[39],"gap":[40],"in":[41,81,92,102,106,111],"performance-level":[42],"music":[43],"understanding,":[44],"and":[45,54,76,109],"address":[46],"three":[47],"critical":[48],"tasks:":[49],"expertise":[50,103,137],"ranking,":[51,104,138],"difficulty":[52,107],"estimation,":[53,108],"technique":[56,112],"detection,":[57,113],"introducing":[58],"comprehensive":[60],"Pianism-Labelling":[61],"Dataset":[62],"(PLD)":[63],"this":[65],"purpose.":[66],"We":[67],"leverage":[68],"pre-trained":[69],"encoders,":[71],"specifically":[72],"Jukebox,":[73],"Audio-MAE,":[74],"MERT,":[75],"DAC,":[77],"demonstrating":[78],"varied":[79],"capabilities":[80],"tackling":[82],"downstream":[83],"tasks,":[84],"explore":[86],"whether":[87],"domain-specific":[88],"fine-tuning":[89],"enhances":[90],"capability":[91],"capturing":[93],"performance":[94],"nuances.":[95],"best":[97],"achieved":[99],"93.6%":[100],"accuracy":[101],"33.7%":[105],"46.7%":[110],"with":[114],"Audio-MAE":[115],"overall":[118],"most":[119],"effective":[120],"encoder.":[121],"Finally,":[122],"conducted":[124],"case":[126],"Chopin":[129],"Piano":[130],"Competition":[131],"data":[132],"using":[133],"trained":[134],"models":[135],"which":[139],"highlights":[140],"challenge":[142],"accurately":[144],"assessing":[145],"top-tier":[146],"performances.":[147]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}