{"id":"https://openalex.org/W7203908205","doi":"https://doi.org/10.48550/arxiv.2608.19919","title":"Unified Music Identification for Tracks and Versions","display_name":"Unified Music Identification for Tracks and Versions","publication_year":2026,"publication_date":"2026-08-20","ids":{"openalex":"https://openalex.org/W7203908205","doi":"https://doi.org/10.48550/arxiv.2608.19919"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.19919","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.19919","pdf_url":"https://arxiv.org/pdf/2608.19919","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.19919","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081395357","display_name":"R. Oguz Araz","orcid":"https://orcid.org/0000-0002-8456-0990","observed_orcids":["https://orcid.org/0000-0002-8456-0990"]},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Araz, R. Oguz","raw_affiliation_strings":["Music Technology Group , Universitat Pompeu Fabra , Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group , Universitat Pompeu Fabra , Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044197796","display_name":"Joan Serr\u00e0","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Serr\u00e0, Joan","raw_affiliation_strings":["Sony AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I4210143797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140","observed_orcids":["https://orcid.org/0000-0002-6806-6140"]},"institutions":[{"id":"https://openalex.org/I4210143797","display_name":"Sony (Japan)","ror":"https://ror.org/04wzv3n59","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210143797"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mitsufuji, Yuki","raw_affiliation_strings":["Sony AI","Sony Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I4210143797"]},{"raw_affiliation_string":"Sony Group Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345","observed_orcids":["https://orcid.org/0000-0003-1395-2345"]},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Serra, Xavier","raw_affiliation_strings":["Music Technology Group , Universitat Pompeu Fabra , Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group , Universitat Pompeu Fabra , Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004451369","display_name":"Dmitry Bogdanov","orcid":"https://orcid.org/0000-0002-9469-0633","observed_orcids":["https://orcid.org/0000-0002-9469-0633"]},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Bogdanov, Dmitry","raw_affiliation_strings":["Music Technology Group , Universitat Pompeu Fabra , Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group , Universitat Pompeu Fabra , Barcelona","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.0,"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-identification","display_name":"music identification","score":0.7919999957084656},{"id":"https://openalex.org/keywords/track-identification","display_name":"track identification","score":0.9869999885559082},{"id":"https://openalex.org/keywords/audio-retrieval","display_name":"audio retrieval","score":0.6240000128746033},{"id":"https://openalex.org/keywords/audio-degradation","display_name":"audio degradation","score":0.871999979019165},{"id":"https://openalex.org/keywords/signal-manipulation","display_name":"signal manipulation","score":0.7910000085830688}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7281000018119812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232999801635742},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6668000221252441},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5997999906539917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.560699999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5543000102043152},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33980000019073486},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C119247159","wikidata":"https://www.wikidata.org/wiki/Q1366192","display_name":"System identification","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2556999921798706},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.19919","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.19919","pdf_url":"https://arxiv.org/pdf/2608.19919","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.19919","doi":"https://doi.org/10.48550/arxiv.2608.19919","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.19919","pdf_url":null,"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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.19919","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.19919","pdf_url":"https://arxiv.org/pdf/2608.19919","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1010185562","display_name":null,"funder_award_id":"2024 FI-300065","funder_id":"https://openalex.org/F4320334830","funder_display_name":"Ag\u00e8ncia de Gesti\u00f3 d'Ajuts Universitaris i de Recerca"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334830","display_name":"Ag\u00e8ncia de Gesti\u00f3 d'Ajuts Universitaris i de Recerca","ror":"https://ror.org/01n4pqe45"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203908205.pdf","grobid_xml":"https://content.openalex.org/works/W7203908205.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2981672232","https://openalex.org/W7196965963","https://openalex.org/W2101722322","https://openalex.org/W2727839354","https://openalex.org/W6990185709","https://openalex.org/W7165831868","https://openalex.org/W1232391391","https://openalex.org/W2018682249","https://openalex.org/W7140088858","https://openalex.org/W7103888265"],"abstract_inverted_index":{"Given":[0],"a":[1,64,99,108],"music":[2,138],"database,":[3],"track":[4,10,34],"identification":[5,17,139],"(TI)":[6],"retrieves":[7,19],"the":[8,24,121],"exact":[9],"matching":[11],"an":[12],"audio":[13,59],"excerpt,":[14],"whereas":[15],"version":[16],"(VI)":[18],"its":[20,36],"musical":[21],"versions.":[22],"Traditionally,":[23],"two":[25,122],"tasks":[26,104],"have":[27],"been":[28],"addressed":[29],"separately.":[30],"However,":[31],"as":[32],"every":[33],"is":[35,111],"own":[37],"closest":[38],"version,":[39],"we":[40,82,119],"investigate":[41],"whether":[42],"VI":[43,49],"can":[44],"subsume":[45],"TI.":[46],"This":[47],"requires":[48],"systems":[50],"to":[51,54,136],"be":[52],"robust":[53,92],"both":[55,89,94,103],"signal":[56],"manipulation":[57],"and":[58,70,91,105],"degradation.":[60],"We":[61,96,131],"therefore":[62],"propose":[63],"unified":[65,109],"benchmark":[66],"that":[67,84,107,125],"evaluates":[68],"accuracy":[69],"robustness":[71],"on":[72,79,93],"each":[73],"task.":[74],"Comparing":[75],"seven":[76],"existing":[77],"models":[78],"this":[80,134],"benchmark,":[81],"show":[83,106],"none":[85],"of":[86],"them":[87],"are":[88],"accurate":[90],"tasks.":[95,140],"then":[97],"train":[98],"baseline":[100],"model":[101],"targeting":[102],"system":[110],"possible":[112],"with":[113],"10":[114],"s":[115],"TI":[116,129],"queries.":[117],"Lastly,":[118],"characterize":[120],"retrieval":[123],"constraints":[124],"limit":[126],"our":[127],"model's":[128],"performance.":[130],"envision":[132],"extending":[133],"unification":[135],"other":[137]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-22T00:00:00"}