{"id":"https://openalex.org/W4416251187","doi":"https://doi.org/10.1109/waspaa66052.2025.11230932","title":"Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning","display_name":"Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251187","doi":"https://doi.org/10.1109/waspaa66052.2025.11230932"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5113780845","display_name":"Julia Wilkins","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Julia Wilkins","raw_affiliation_strings":["New York University,New York,USA"],"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sivan Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sivan Ding","raw_affiliation_strings":["New York University,New York,USA"],"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021235229","display_name":"Magdalena Fuentes","orcid":"https://orcid.org/0000-0003-4506-6639"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Magdalena Fuentes","raw_affiliation_strings":["New York University,New York,USA"],"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Bello","raw_affiliation_strings":["New York University,New York,USA"],"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113780845"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41648312,"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":0.6807000041007996,"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":0.6807000041007996,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1565999984741211,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.02979999966919422,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.6304000020027161},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.586899995803833},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5170999765396118},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45170000195503235},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4146000146865845},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.40369999408721924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763700008392334},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6304000020027161},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5170999765396118},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4219000041484833},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.40369999408721924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.3125},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30300000309944153}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313176","display_name":"Robert Bosch","ror":"https://ror.org/02venad53"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3137857706","https://openalex.org/W3161927506","https://openalex.org/W3162391496","https://openalex.org/W3198608154","https://openalex.org/W4297841853","https://openalex.org/W4375869340","https://openalex.org/W4392902915","https://openalex.org/W4392931767","https://openalex.org/W4404740148","https://openalex.org/W4407748117","https://openalex.org/W4408353036"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,50,89,108],"self-supervised":[3],"learning":[4],"(SSL)":[5],"methods":[6],"offer":[7],"a":[8,51,60,109],"range":[9],"of":[10,87,101,134],"strategies":[11,103,119],"for":[12,22,64],"capturing":[13],"useful":[14],"representations":[15,68,107],"from":[16],"music":[17,66,105,135],"audio":[18,67,106],"without":[19,137],"the":[20,45,98,132],"need":[21],"labeled":[23],"data.":[24],"While":[25],"some":[26],"techniques":[27],"focus":[28],"on":[29,97],"preserving":[30],"comprehensive":[31],"details":[32],"through":[33],"reconstruction,":[34],"others":[35],"favor":[36],"semantic":[37],"structure":[38],"via":[39],"contrastive":[40,71,102,118],"objectives.":[41,74],"Few":[42],"works":[43],"examine":[44],"interaction":[46],"between":[47],"these":[48],"paradigms":[49],"unified":[52],"SSL":[53,62],"framework.":[54],"In":[55],"this":[56,130],"work,":[57],"we":[58],"propose":[59],"multi-view":[61],"framework":[63],"disentangling":[65],"that":[69,114],"combines":[70],"and":[72,84,117],"reconstructive":[73],"The":[75],"architecture":[76],"is":[77],"designed":[78],"to":[79],"promote":[80],"both":[81],"information":[82,139],"fidelity":[83],"structured":[85],"semantics":[86],"factors":[88],"disentangled":[90],"subspaces.":[91],"We":[92,112],"perform":[93],"an":[94],"extensive":[95],"evaluation":[96],"design":[99],"choices":[100],"using":[104],"controlled":[110],"setting.":[111],"find":[113],"while":[115],"reconstruction":[116],"exhibit":[120],"consistent":[121],"trade-offs,":[122],"when":[123],"combined":[124],"effectively,":[125],"they":[126],"complement":[127],"each":[128],"other;":[129],"enables":[131],"disentanglement":[133],"attributes":[136],"compromising":[138],"integrity.":[140]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-11-14T00:00:00"}