{"id":"https://openalex.org/W4372260285","doi":"https://doi.org/10.1109/icassp49357.2023.10097100","title":"Improving Self-Supervised Learning for Audio Representations by Feature Diversity and Decorrelation","display_name":"Improving Self-Supervised Learning for Audio Representations by Feature Diversity and Decorrelation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260285","doi":"https://doi.org/10.1109/icassp49357.2023.10097100"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097100","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5044769639","display_name":"Bac T. Nguyen","orcid":"https://orcid.org/0000-0001-6637-4185"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bac Nguyen","raw_affiliation_strings":["Sony Europe B.V., R&D Center,Stuttgart Laboratory 1,Germany"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V., R&D Center,Stuttgart Laboratory 1,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010554448","display_name":"Stefan Uhlich","orcid":"https://orcid.org/0000-0003-3158-4945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Uhlich","raw_affiliation_strings":["Sony Europe B.V., R&D Center,Stuttgart Laboratory 1,Germany"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V., R&D Center,Stuttgart Laboratory 1,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056623642","display_name":"Fabien Cardinaux","orcid":"https://orcid.org/0000-0003-2921-4873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabien Cardinaux","raw_affiliation_strings":["Sony Europe B.V., R&D Center,Stuttgart Laboratory 1,Germany"],"affiliations":[{"raw_affiliation_string":"Sony Europe B.V., R&D Center,Stuttgart Laboratory 1,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044769639"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2038,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39868545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.7525578141212463},{"id":"https://openalex.org/keywords/decorrelation","display_name":"Decorrelation","score":0.7010493278503418},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6817989945411682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.616389811038971},{"id":"https://openalex.org/keywords/selfie","display_name":"Selfie","score":0.5909972786903381},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5094991326332092},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.44107717275619507},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4279247522354126},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41207122802734375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4081442952156067},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36640244722366333},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2435036301612854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08669060468673706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525578141212463},{"id":"https://openalex.org/C177860922","wikidata":"https://www.wikidata.org/wiki/Q788608","display_name":"Decorrelation","level":2,"score":0.7010493278503418},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6817989945411682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616389811038971},{"id":"https://openalex.org/C2777454149","wikidata":"https://www.wikidata.org/wiki/Q12068677","display_name":"Selfie","level":2,"score":0.5909972786903381},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5094991326332092},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.44107717275619507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4279247522354126},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41207122802734375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4081442952156067},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36640244722366333},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2435036301612854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08669060468673706},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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/icassp49357.2023.10097100","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2030931454","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2133824856","https://openalex.org/W2593116425","https://openalex.org/W2593451766","https://openalex.org/W2726515241","https://openalex.org/W2767754137","https://openalex.org/W2797583228","https://openalex.org/W2972943112","https://openalex.org/W3006926732","https://openalex.org/W3137857706","https://openalex.org/W3159239022","https://openalex.org/W3162391496","https://openalex.org/W3171007011","https://openalex.org/W3206495532","https://openalex.org/W3209059054","https://openalex.org/W4205689591","https://openalex.org/W4225713393","https://openalex.org/W4297808394","https://openalex.org/W4310873011","https://openalex.org/W4311137818","https://openalex.org/W4375839990","https://openalex.org/W6685802191","https://openalex.org/W6736723571","https://openalex.org/W6750665317","https://openalex.org/W6778102432","https://openalex.org/W6779191341","https://openalex.org/W6779326418","https://openalex.org/W6780218876","https://openalex.org/W6780379688","https://openalex.org/W6784011672","https://openalex.org/W6795754764","https://openalex.org/W6802387851","https://openalex.org/W6803360755","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2795495259","https://openalex.org/W1604939135","https://openalex.org/W3028531746","https://openalex.org/W2759481820","https://openalex.org/W2905271011","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579","https://openalex.org/W1872833176","https://openalex.org/W2515319207"],"abstract_inverted_index":{"Self-supervised":[0,59],"learning":[1],"(SSL)":[2],"has":[3],"recently":[4],"shown":[5],"remarkable":[6],"results":[7,120],"in":[8,128],"closing":[9],"the":[10,30,45,72,78,90,98],"gap":[11],"between":[12,92],"supervised":[13],"and":[14,68,87,102,115],"unsupervised":[15],"learning.":[16],"The":[17],"idea":[18,37],"is":[19,95],"to":[20,27],"learn":[21],"robust":[22],"features":[23],"that":[24,77,122],"are":[25,105],"invariant":[26],"distortions":[28],"of":[29],"input":[31],"data.":[32],"Despite":[33],"its":[34,103],"success,":[35],"this":[36,52],"can":[38],"suffer":[39],"from":[40],"a":[41,48,57,82],"collapsing":[42,73],"issue":[43,74],"where":[44],"network":[46],"produces":[47],"constant":[49],"representation.":[50],"To":[51],"end,":[53],"we":[54],"introduce":[55],"SELFIE,":[56],"novel":[58],"Learning":[60],"approach":[61],"for":[62],"audio":[63,109],"representation":[64,79],"via":[65],"Feature":[66],"Diversity":[67],"Decorrelation.":[69],"SELFIE":[70,94,123],"avoids":[71],"by":[75],"ensuring":[76],"(i)":[80],"maintains":[81],"high":[83],"diversity":[84],"among":[85],"embeddings":[86,104],"(ii)":[88],"decorrelates":[89],"dependencies":[91],"dimensions.":[93],"pre-trained":[96],"on":[97,107],"large-scale":[99],"AudioSet":[100],"dataset":[101],"validated":[106],"nine":[108],"downstream":[110],"tasks,":[111],"including":[112],"speech,":[113],"music,":[114],"sound":[116],"event":[117],"recognition.":[118],"Experimental":[119],"show":[121],"outperforms":[124],"existing":[125],"SSL":[126],"methods":[127],"several":[129],"tasks.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}