{"id":"https://openalex.org/W6892570130","doi":"https://doi.org/10.5281/zenodo.10265419","title":"A Cross-Version Approach to Audio Representation Learning for Orchestral Music","display_name":"A Cross-Version Approach to Audio Representation Learning for Orchestral Music","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6892570130","doi":"https://doi.org/10.5281/zenodo.10265419"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265419","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265419","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.10265419","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Michael Krause","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Krause","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Christof Wei\u00df","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christof Wei\u00df","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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":[]}],"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":0.9832000136375427,"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":0.9832000136375427,"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/T10860","display_name":"Speech and Audio Processing","score":0.004100000020116568,"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":0.002899999963119626,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6547999978065491},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6116999983787537},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5867000222206116},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5006999969482422},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4546000063419342},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4510999917984009},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.36910000443458557},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3596999943256378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7432000041007996},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6547999978065491},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6116999983787537},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5867000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5257999897003174},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40880000591278076},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.36910000443458557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36880001425743103},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3467000126838684},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.28859999775886536},{"id":"https://openalex.org/C118530786","wikidata":"https://www.wikidata.org/wiki/Q1134732","display_name":"Instrumentation (computer programming)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.28790000081062317},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265419","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265419","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.10265419","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265419","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":0.7208357453346252,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1,42,66],"systems":[2,17],"have":[3],"become":[4],"popular":[5],"for":[6,25],"tackling":[7],"a":[8,59,79],"variety":[9],"of":[10,22,78,92,119],"music":[11,43,72,109],"information":[12],"retrieval":[13],"tasks.":[14],"However,":[15],"these":[16],"often":[18],"require":[19],"large":[20],"amounts":[21],"labeled":[23],"data":[24],"supervised":[26],"training,":[27],"which":[28],"can":[29,68,115],"be":[30,69],"very":[31],"costly":[32],"to":[33,63,122],"obtain.":[34],"To":[35],"alleviate":[36],"this":[37,55],"problem,":[38],"recent":[39],"papers":[40],"on":[41,106],"audio":[44,64],"representations":[45],"employ":[46],"alternative":[47],"training":[48],"strategies":[49],"that":[50,67,87,113,124],"utilize":[51],"unannotated":[52],"data.":[53],"In":[54],"paper,":[56],"we":[57],"introduce":[58],"novel":[60],"cross-version":[61,101,128],"approach":[62,102],"representation":[65],"used":[70],"with":[71],"datasets":[73],"containing":[74],"several":[75],"versions":[76,91],"(performances)":[77],"musical":[80,95],"work.":[81],"Our":[82],"method":[83],"exploits":[84],"the":[85,93],"correspondences":[86],"exist":[88],"between":[89],"two":[90],"same":[94],"section.":[96],"We":[97],"evaluate":[98],"our":[99],"proposed":[100],"qualitatively":[103],"and":[104,111],"quantitatively":[105],"complex":[107],"orchestral":[108],"recordings":[110],"show":[112],"it":[114],"better":[116],"capture":[117],"aspects":[118],"instrumentation":[120],"compared":[121],"techniques":[123],"do":[125],"not":[126],"use":[127],"information.":[129]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}