{"id":"https://openalex.org/W6893116257","doi":"https://doi.org/10.5281/zenodo.14877415","title":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","display_name":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6893116257","doi":"https://doi.org/10.5281/zenodo.14877415"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877415","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877415","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.14877415","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Alain Riou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alain Riou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Stefan Lattner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Lattner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ga\u00ebtan Hadjeres","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ga\u00ebtan Hadjeres","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Michael Anslow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Anslow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Geoffroy Peeters","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","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":0.916100025177002,"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":0.916100025177002,"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":0.07479999959468842,"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":0.0034000000450760126,"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/encoder","display_name":"Encoder","score":0.5260000228881836},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.45980000495910645},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.366100013256073},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3635999858379364},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3447999954223633},{"id":"https://openalex.org/keywords/compatibility","display_name":"Compatibility (geochemistry)","score":0.34439998865127563},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33180001378059387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6669999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426999926567078},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43320000171661377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38830000162124634},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C2778648169","wikidata":"https://www.wikidata.org/wiki/Q967768","display_name":"Compatibility (geochemistry)","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877415","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877415","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.14877415","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877415","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","id":"https://metadata.un.org/sdg/4","score":0.4529925286769867}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,64,70,115,119,140,148,164,174],"automated":[4],"process":[5],"of":[6,14,66,72,79],"determining":[7],"stem":[8,93,99,150],"compatibility":[9],"by":[10,177],"identifying":[11],"audio":[12],"recordings":[13],"single":[15],"instruments":[16],"that":[17,163,185],"blend":[18],"well":[19],"with":[20],"a":[21,32,40,44,56,73,77,83,98,102,136,152,156],"given":[22,74,103],"musical":[23,190],"context.":[24],"To":[25],"tackle":[26],"this":[27,86],"challenge,":[28],"we":[29],"present":[30],"Stem-JEPA,":[31],"novel":[33],"Joint-Embedding":[34],"Predictive":[35],"Architecture":[36],"(JEPA)":[37],"trained":[38,61],"on":[39,135,139,180],"multi-track":[41],"dataset":[42],"using":[43],"self-supervised":[45],"learning":[46],"approach.":[47],"Our":[48],"model":[49,84,120,179],"comprises":[50],"two":[51],"networks:":[52],"an":[53],"encoder":[54],"and":[55,128,154],"predictor,":[57],"which":[58],"are":[59],"jointly":[60],"to":[62,100,121,125,146],"predict":[63],"embeddings":[65,71,166],"compatible":[67],"stems":[68],"from":[69,151],"context,":[75],"typically":[76],"mix":[78,153],"several":[80,181],"instruments.":[81],"Training":[82],"in":[85,91],"manner":[87],"allows":[88],"its":[89,144],"use":[90],"estimating":[92],"compatibility\u2014retrieving,":[94],"aligning,":[95],"or":[96,111],"generating":[97],"match":[101],"mix\u2014or":[104],"for":[105],"downstream":[106,182],"tasks":[107],"such":[108],"as":[109,114],"genre":[110],"key":[112],"estimation,":[113],"training":[116],"paradigm":[117],"requires":[118],"learn":[122],"information":[123,170],"related":[124],"timbre,":[126],"harmony,":[127],"rhythm.":[129],"We":[130,160],"evaluate":[131,173],"our":[132,178],"model's":[133],"performance":[134],"retrieval":[137],"task":[138],"MUSDB18":[141],"dataset,":[142],"testing":[143],"ability":[145],"find":[147],"missing":[149],"through":[155],"subjective":[157],"user":[158],"study.":[159],"also":[161],"show":[162],"learned":[165,176],"capture":[167,188],"temporal":[168],"alignment":[169],"and,":[171],"finally,":[172],"representations":[175],"tasks,":[183],"highlighting":[184],"they":[186],"effectively":[187],"meaningful":[189],"features.":[191]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}