{"id":"https://openalex.org/W7124263486","doi":"https://doi.org/10.1145/3748522.3779786","title":"Linear Complexity Self-Supervised Learning for Music Understanding with Random Quantizer","display_name":"Linear Complexity Self-Supervised Learning for Music Understanding with Random Quantizer","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7124263486","doi":"https://doi.org/10.1145/3748522.3779786"},"language":null,"primary_location":{"id":"doi:10.1145/3748522.3779786","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779786","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3748522.3779786","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006082842","display_name":"Petros Vavaroutsos","orcid":"https://orcid.org/0000-0003-1929-5649"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Petros Vavaroutsos","raw_affiliation_strings":["Orfium Research, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orfium Research, Greece","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123157346","display_name":"Theodoros Palamas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Theodoros Palamas","raw_affiliation_strings":["Orfium Research, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orfium Research, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048033327","display_name":"Pantelis Vikatos","orcid":"https://orcid.org/0000-0003-1573-5125"},"institutions":[{"id":"https://openalex.org/I2801361913","display_name":"Athens International Airport","ror":"https://ror.org/031m32a82","country_code":"GR","type":"other","lineage":["https://openalex.org/I2801361913"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Pantelis Vikatos","raw_affiliation_strings":["Orfium Ressearch, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orfium Ressearch, Greece","institution_ids":["https://openalex.org/I2801361913"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006082842"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07497984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1231","last_page":"1233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8654000163078308,"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":0.8654000163078308,"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":0.05130000039935112,"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/T10028","display_name":"Topic Modeling","score":0.007600000128149986,"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/quantization","display_name":"Quantization (signal processing)","score":0.5582000017166138},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5088000297546387},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3799000084400177},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3666999936103821},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.36640000343322754},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3490000069141388},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.34850001335144043},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.30329999327659607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580999732017517},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5582000017166138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131000280380249},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49470001459121704},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3748522.3779786","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779786","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.09603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.09603","pdf_url":"https://arxiv.org/pdf/2601.09603","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"doi:10.1145/3748522.3779786","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748522.3779786","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 41st ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"foundation":[3],"models":[4,26,147],"have":[5],"become":[6],"very":[7],"popular":[8],"due":[9],"to":[10,48,64,109,160],"their":[11],"exceptional":[12],"performance,":[13],"mainly":[14],"in":[15,44,82,107,114],"natural":[16],"language":[17],"(NLP)":[18],"tasks":[19],"where":[20],"they":[21],"were":[22,79],"first":[23,80],"introduced.":[24],"These":[25],"usually":[27],"consist":[28],"of":[29,31,36,57,126,129],"hundreds":[30],"millions,":[32],"or":[33],"even":[34],"billions,":[35],"parameters,":[37],"making":[38],"them":[39],"resource-intensive":[40],"during":[41],"training":[42],"and":[43],"production":[45],"systems,":[46],"leading":[47],"increased":[49],"costs.":[50],"This":[51],"paper":[52],"focuses":[53],"on":[54,97],"the":[55,73,115,154],"reduction":[56],"a":[58,87,103,123,127],"foundation's":[59],"model":[60,155],"size":[61,156],"when":[62,142],"applied":[63,81],"music":[65],"information":[66],"retrieval":[67],"(MIR)":[68],"tasks.":[69,132],"Our":[70,133],"research":[71],"combines":[72],"Branchformer":[74],"architecture":[75,138],"with":[76,86,144],"SummaryMixing,":[77],"which":[78],"speech":[83],"recognition,":[84],"along":[85],"random":[88],"quantization":[89],"process.":[90],"To":[91],"facilitate":[92],"reproducibility,":[93],"we":[94],"conduct":[95],"pre-training":[96],"publicly":[98],"available":[99],"datasets,":[100],"complemented":[101],"by":[102,121],"proprietary":[104],"dataset":[105],"comparable":[106],"scale":[108],"other":[110,145],"private":[111],"datasets":[112],"reported":[113],"literature.":[116],"We":[117],"ensure":[118],"robust":[119],"evaluation":[120],"using":[122],"framework":[124],"consisting":[125],"variety":[128],"downstream":[130],"MIR":[131],"results":[134],"show":[135],"that":[136,148],"our":[137],"achieves":[139],"competitive":[140],"performance":[141],"compared":[143],"state-of-the-art":[146],"use":[149],"multi-head":[150],"self-attention,":[151],"while":[152],"reducing":[153],"from":[157],"8.5%":[158],"up":[159],"12.3%.":[161]},"counts_by_year":[],"updated_date":"2026-06-10T14:10:52.464848","created_date":"2026-01-16T00:00:00"}