{"id":"https://openalex.org/W4408353522","doi":"https://doi.org/10.1109/icassp49660.2025.10888814","title":"Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures","display_name":"Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353522","doi":"https://doi.org/10.1109/icassp49660.2025.10888814"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092829399","display_name":"Alain Riou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alain Riou","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com-Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com-Paris,France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094179003","display_name":"Antonin Gagner\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antonin Gagner\u00e9","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com-Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com-Paris,France","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051522702","display_name":"Ga\u00ebtan Hadjeres","orcid":"https://orcid.org/0000-0003-1462-6103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ga\u00ebtan Hadjeres","raw_affiliation_strings":["Sony AI,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI,Zurich,Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113914858","display_name":"Stefan Lattner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131385","display_name":"Sony (France)","ror":"https://ror.org/03cr99w51","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210131385","https://openalex.org/I4210143797"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stefan Lattner","raw_affiliation_strings":["Sony Computer Science Laboratories,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Paris,France","institution_ids":["https://openalex.org/I4210131385"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com-Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com-Paris,France","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03875107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9958000183105469,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6793762445449829},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6776177883148193},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6118805408477783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5986084938049316},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.580074667930603},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.540984034538269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42039230465888977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3842582702636719},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13507956266403198},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07749772071838379},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.06242910027503967},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06162711977958679}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6793762445449829},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6776177883148193},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6118805408477783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5986084938049316},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.580074667930603},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.540984034538269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42039230465888977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3842582702636719},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13507956266403198},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07749772071838379},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.06242910027503967},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06162711977958679},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1978421240","https://openalex.org/W2016885049","https://openalex.org/W2117330939","https://openalex.org/W2133824856","https://openalex.org/W2138621090","https://openalex.org/W2156063659","https://openalex.org/W2572771584","https://openalex.org/W2760103357","https://openalex.org/W3118825798","https://openalex.org/W3162391496","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4372341324","https://openalex.org/W4386076428","https://openalex.org/W4404161706","https://openalex.org/W6713195707","https://openalex.org/W6757817989","https://openalex.org/W6770646036","https://openalex.org/W6774314701","https://openalex.org/W6781319653","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6791537541","https://openalex.org/W6846591948","https://openalex.org/W6855434424","https://openalex.org/W6876063710"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"In":[0,70,90],"this":[1],"paper,":[2],"we":[3,37,72,92],"tackle":[4],"the":[5,96,103,107,114,146],"task":[6],"of":[7,60,67,110],"musical":[8,13],"stem":[9,20,88],"retrieval.":[10,89],"Given":[11],"a":[12,19,39,51,61,68,150],"mix,":[14],"it":[15,122],"consists":[16],"in":[17],"retrieving":[18],"that":[21,27,94,121,155],"would":[22,28],"fit":[23],"with":[24],"it,":[25],"i.e.,":[26],"sound":[29],"pleasant":[30],"if":[31],"played":[32],"together.":[33],"To":[34],"do":[35],"so,":[36],"introduce":[38],"new":[40],"method":[41],"based":[42],"on":[43,79,127,149],"Joint-Embedding":[44],"Predictive":[45],"Architectures,":[46],"where":[47],"an":[48],"encoder":[49,97],"and":[50,63,116,160],"predictor":[52,75],"are":[53],"jointly":[54],"trained":[55],"to":[56,76,85,133],"produce":[57],"latent":[58,65],"representations":[59,66],"context":[62],"predict":[64],"target.":[69],"particular,":[71],"design":[73],"our":[74,83,111],"be":[77],"conditioned":[78],"arbitrary":[80],"instruments,":[81],"enabling":[82],"model":[84,112],"perform":[86],"zero-shot":[87],"addition,":[91],"discover":[93],"pretraining":[95],"using":[98,113],"contrastive":[99],"learning":[100],"drastically":[101],"improves":[102],"model\u2019s":[104],"performance.We":[105],"validate":[106],"retrieval":[108],"performances":[109],"MUSDB18":[115],"MoisesDB":[117],"datasets.":[118],"We":[119,143],"show":[120],"significantly":[123],"out-performs":[124],"previous":[125],"baselines":[126],"both":[128],"datasets,":[129],"showcasing":[130],"its":[131],"ability":[132],"support":[134],"more":[135],"or":[136],"less":[137],"precise":[138],"(and":[139],"possibly":[140],"unseen)":[141],"conditioning.":[142],"also":[144],"evaluate":[145],"learned":[147],"embeddings":[148],"beat":[151],"tracking":[152],"task,":[153],"demonstrating":[154],"they":[156],"retain":[157],"temporal":[158],"structure":[159],"local":[161],"information.":[162]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
