{"id":"https://openalex.org/W4408353036","doi":"https://doi.org/10.1109/icassp49660.2025.10890270","title":"Leave-One-EquiVariant: Alleviating Invariance-Related Information Loss in Contrastive Music Representations","display_name":"Leave-One-EquiVariant: Alleviating Invariance-Related Information Loss in Contrastive Music Representations","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353036","doi":"https://doi.org/10.1109/icassp49660.2025.10890270"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890270","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/A5107854683","display_name":"Julien Guinot","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Julien Guinot","raw_affiliation_strings":["Queen Mary University of London,School of EECS,London,U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of EECS,London,U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051960947","display_name":"Elio Quinton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elio Quinton","raw_affiliation_strings":["Universal Music Group,Music & Audio Machine Learning Lab,London,U.K"],"affiliations":[{"raw_affiliation_string":"Universal Music Group,Music & Audio Machine Learning Lab,London,U.K","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032485940","display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gy\u00f6rgy Fazekas","raw_affiliation_strings":["Queen Mary University of London,School of EECS,London,U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of EECS,London,U.K","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107854683"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":4.7229,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93913667,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"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":0.9955000281333923,"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":0.9955000281333923,"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":0.9922999739646912,"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":0.9878000020980835,"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/equivariant-map","display_name":"Equivariant map","score":0.65572190284729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.508321225643158},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4181564152240753},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38079267740249634},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32431459426879883},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.18936848640441895},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.09502473473548889}],"concepts":[{"id":"https://openalex.org/C171036898","wikidata":"https://www.wikidata.org/wiki/Q256355","display_name":"Equivariant map","level":2,"score":0.65572190284729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.508321225643158},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4181564152240753},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38079267740249634},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32431459426879883},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.18936848640441895},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.09502473473548889}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890270","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":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2049321404","https://openalex.org/W2133824856","https://openalex.org/W2156063659","https://openalex.org/W2964051853","https://openalex.org/W3106743555","https://openalex.org/W4220931296","https://openalex.org/W4221161255","https://openalex.org/W4225713393","https://openalex.org/W4284898017","https://openalex.org/W4293518176","https://openalex.org/W4308860482","https://openalex.org/W4312421335","https://openalex.org/W4392902915","https://openalex.org/W4392903209","https://openalex.org/W4408345573","https://openalex.org/W6641088196","https://openalex.org/W6678969435","https://openalex.org/W6714030504","https://openalex.org/W6736723571","https://openalex.org/W6745878906","https://openalex.org/W6763945542","https://openalex.org/W6774314701","https://openalex.org/W6774670964","https://openalex.org/W6777179611","https://openalex.org/W6781834539","https://openalex.org/W6791537541","https://openalex.org/W6803254773","https://openalex.org/W6843552097","https://openalex.org/W6846470732","https://openalex.org/W6849887002","https://openalex.org/W6852985890","https://openalex.org/W6872553043"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W3148895720","https://openalex.org/W2393913406","https://openalex.org/W2356579025","https://openalex.org/W2736697936","https://openalex.org/W3211835374","https://openalex.org/W30258475","https://openalex.org/W1541054761"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1],"has":[2],"proven":[3],"effective":[4],"in":[5,118],"self-supervised":[6,120],"musical":[7,41],"representation":[8,100],"learning,":[9],"particularly":[10],"for":[11,22],"Music":[12],"Information":[13],"Retrieval":[14],"(MIR)":[15],"tasks.":[16],"However,":[17],"reliance":[18],"on":[19,91,127],"augmentation":[20,92,128],"chains":[21],"contrastive":[23],"view":[24],"generation":[25],"and":[26,95,122],"the":[27,48,72],"resulting":[28],"learnt":[29],"invariances":[30],"pose":[31],"challenges":[32],"when":[33],"different":[34],"downstream":[35],"tasks":[36,94],"require":[37],"sensitivity":[38],"to":[39,61,74,86],"certain":[40],"attributes.":[42,130],"To":[43],"address":[44],"this,":[45],"we":[46,103],"propose":[47],"Leave":[49],"One":[50],"EquiVariant":[51],"(LOEV)":[52],"framework,":[53],"which":[54,110],"introduces":[55],"a":[56,105,112,119],"flexible,":[57],"task-adaptive":[58],"approach":[59],"compared":[60],"previous":[62],"work":[63],"by":[64,116],"selectively":[65],"preserving":[66],"information":[67,83],"about":[68],"specific":[69],"augmentations,":[70],"allowing":[71],"model":[73],"maintain":[75],"task-relevant":[76],"equivariances.":[77],"We":[78],"demonstrate":[79],"that":[80],"LOEV":[81],"alleviates":[82],"loss":[84],"related":[85,93,129],"learned":[87],"invariances,":[88],"improving":[89],"performance":[90],"retrieval":[96,125],"without":[97],"sacrificing":[98],"general":[99],"quality.":[101],"Furthermore,":[102],"introduce":[104],"variant":[106],"of":[107],"LOEV,":[108],"LOEV++,":[109],"builds":[111],"disentangled":[113],"latent":[114],"space":[115],"design":[117],"manner,":[121],"enables":[123],"targeted":[124],"based":[126]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}