{"id":"https://openalex.org/W4293370787","doi":"https://doi.org/10.1109/jstsp.2022.3202093","title":"Decorrelating Feature Spaces for Learning General-Purpose Audio Representations","display_name":"Decorrelating Feature Spaces for Learning General-Purpose Audio Representations","publication_year":2022,"publication_date":"2022-08-26","ids":{"openalex":"https://openalex.org/W4293370787","doi":"https://doi.org/10.1109/jstsp.2022.3202093"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3202093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3202093","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5033408639","display_name":"Sreyan Ghosh","orcid":"https://orcid.org/0000-0003-3773-561X"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":["Speech Lab, Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018932560","display_name":"Ashish Seth","orcid":"https://orcid.org/0000-0003-3100-9342"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Seth","raw_affiliation_strings":["Speech Lab, Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0000-0003-3100-9342","affiliations":[{"raw_affiliation_string":"Speech Lab, Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Umesh","raw_affiliation_strings":["Speech Lab, Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, Tamil Nadu, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":1.6243,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82636816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"16","issue":"6","first_page":"1402","last_page":"1414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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/feature","display_name":"Feature (linguistics)","score":0.6593518257141113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5309752225875854},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4126025140285492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2925741970539093},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2606534957885742}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6593518257141113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5309752225875854},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4126025140285492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2925741970539093},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2606534957885742},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2022.3202093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3202093","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2038484192","https://openalex.org/W2146334809","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2726515241","https://openalex.org/W2757910899","https://openalex.org/W2767754137","https://openalex.org/W2797583228","https://openalex.org/W2883595988","https://openalex.org/W2883725317","https://openalex.org/W2896457183","https://openalex.org/W2963087613","https://openalex.org/W2963263347","https://openalex.org/W2982223350","https://openalex.org/W3006926732","https://openalex.org/W3015265920","https://openalex.org/W3016011332","https://openalex.org/W3035524453","https://openalex.org/W3038899388","https://openalex.org/W3041561163","https://openalex.org/W3158919880","https://openalex.org/W3162391496","https://openalex.org/W3171007011","https://openalex.org/W3187822143","https://openalex.org/W3196974791","https://openalex.org/W3197580070","https://openalex.org/W3201143670","https://openalex.org/W3206649123","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W4205689591","https://openalex.org/W4221150524","https://openalex.org/W4225713393","https://openalex.org/W4288024349","https://openalex.org/W4288348042","https://openalex.org/W4295723153","https://openalex.org/W4297808394","https://openalex.org/W6726497184","https://openalex.org/W6736723571","https://openalex.org/W6744513255","https://openalex.org/W6745136726","https://openalex.org/W6746941363","https://openalex.org/W6750665317","https://openalex.org/W6752516136","https://openalex.org/W6761472960","https://openalex.org/W6770196601","https://openalex.org/W6774314701","https://openalex.org/W6779326418","https://openalex.org/W6779997284","https://openalex.org/W6780218876","https://openalex.org/W6780379688","https://openalex.org/W6783591283","https://openalex.org/W6791742336","https://openalex.org/W6798952882","https://openalex.org/W6802796180","https://openalex.org/W6803316188","https://openalex.org/W6809947431","https://openalex.org/W6840487619","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2905271011","https://openalex.org/W2793270624","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579"],"abstract_inverted_index":{"Inspired":[0,65],"by":[1,66],"the":[2,32,67,92,97,108,123,156],"recent":[3],"progress":[4],"in":[5,11,46,104,155],"self-supervised":[6],"learning":[7,30,74,99],"for":[8],"computer":[9],"vision,":[10],"this":[12,96],"paper,":[13],"through":[14,173],"theDeLoRes(Decorrelating":[15],"latent":[16],"spaces":[17],"forLowResource":[18],"audio":[19,28,82,117,130],"representation":[20,29],"learning)":[21],"framework,":[22,100],"we":[23,72,102,115,180],"introduce":[24],"two":[25],"new":[26],"general-purpose":[27],"approaches,":[31],"DeLoRes-S":[33,109],"and":[34,52,110,128,149,164,191,193,198],"DeLoRes-M.":[35,111],"Our":[36],"main":[37],"objective":[38,70],"is":[39,169],"to":[40,77,133,136,161,171],"make":[41,194],"our":[42,113,166,186,196],"network":[43],"learn":[44,116],"representations":[45,118],"a":[47,59],"resource-constrained":[48],"setting":[49],"(both":[50],"data":[51],"compute)":[53],"that":[54,86],"can":[55],"generalize":[56],"well":[57],"across":[58],"diverse":[60],"set":[61],"of":[62,79,125,143,152,177],"downstream":[63],"tasks.":[64],"Barlow":[68],"Twins":[69],"function,":[71],"propose":[73],"embeddings":[75],"invariant":[76],"distortions":[78],"an":[80],"input":[81],"sample":[83],"while":[84],"ensuring":[85],"they":[87],"contain":[88],"non-redundant":[89],"information":[90],"about":[91],"sample.":[93],"We":[94],"call":[95],"DeLoRes":[98],"which":[101],"employ":[103],"different":[105],"fashions":[106],"with":[107,119],"In":[112,159],"experiments,":[114],"less":[120],"than":[121],"half":[122],"number":[124],"model":[126,189],"parameters":[127],"10%":[129],"samples":[131],"compared":[132],"state-of-the-art":[134,138],"algorithms":[135],"achieve":[137],"results":[139,192],"on":[140,146,185],"7":[141],"out":[142,151],"11":[144,153],"tasks":[145,154],"linear":[147],"evaluation":[148],"4":[150],"finetuning":[157],"setup.":[158],"addition":[160],"being":[162],"simple":[163],"intuitive,":[165],"pre-training":[167],"procedure":[168],"amenable":[170],"compute":[172],"its":[174],"inherent":[175],"nature":[176],"construction.":[178],"Furthermore,":[179],"conduct":[181],"extensive":[182],"ablation":[183],"studies":[184],"training":[187],"algorithm,":[188],"architecture,":[190],"all":[195],"code":[197],"pre-trained":[199],"models":[200],"publicly":[201],"available1.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2022-08-28T00:00:00"}