{"id":"https://openalex.org/W4225317525","doi":"https://doi.org/10.1109/icassp43922.2022.9747472","title":"Federated Self-Supervised Learning for Acoustic Event Classification","display_name":"Federated Self-Supervised Learning for Acoustic Event Classification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225317525","doi":"https://doi.org/10.1109/icassp43922.2022.9747472"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747472","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5027754160","display_name":"Meng Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Feng","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chieh-Chi Kao","raw_affiliation_strings":["Amazon.com Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101986528","display_name":"Qingming Tang","orcid":"https://orcid.org/0000-0002-2670-4917"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Qingming Tang","raw_affiliation_strings":["Amazon.com Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Amazon.com Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091009689","display_name":"Viktor Rozgi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Viktor Rozgic","raw_affiliation_strings":["Amazon.com Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034173999","display_name":"Spyros Matsoukas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Spyros Matsoukas","raw_affiliation_strings":["Amazon.com Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406892","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0001-7578-1970"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon.com Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com Inc","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3994,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90812818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9966999888420105,"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":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808182239532471},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.6442338228225708},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5482974648475647},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5449248552322388},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.533161997795105},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.5150313377380371},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5114630460739136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4812990725040436},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4740733206272125},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4663856029510498},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4309154450893402},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42766258120536804},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42060214281082153},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38304051756858826},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.259235680103302},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20151135325431824},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09646672010421753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808182239532471},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.6442338228225708},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5482974648475647},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5449248552322388},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.533161997795105},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5150313377380371},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5114630460739136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4812990725040436},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4740733206272125},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4663856029510498},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4309154450893402},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42766258120536804},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42060214281082153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38304051756858826},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.259235680103302},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20151135325431824},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09646672010421753},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747472","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1511170870","https://openalex.org/W1533561824","https://openalex.org/W2047484428","https://openalex.org/W2077159900","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2767754137","https://openalex.org/W2775505379","https://openalex.org/W2900120080","https://openalex.org/W2904190483","https://openalex.org/W2963610932","https://openalex.org/W2964066126","https://openalex.org/W2972943112","https://openalex.org/W3006926732","https://openalex.org/W3016011332","https://openalex.org/W3035202887","https://openalex.org/W3043229062","https://openalex.org/W3097714942","https://openalex.org/W3098250197","https://openalex.org/W3158424777","https://openalex.org/W3160719641","https://openalex.org/W3162072286","https://openalex.org/W4220738117","https://openalex.org/W4256604311","https://openalex.org/W4288348042","https://openalex.org/W4318619660","https://openalex.org/W6632323398","https://openalex.org/W6728757088","https://openalex.org/W6747331233","https://openalex.org/W6755988804","https://openalex.org/W6757172675","https://openalex.org/W6794649757","https://openalex.org/W6795234033","https://openalex.org/W6840487619"],"related_works":["https://openalex.org/W34092691","https://openalex.org/W4312414840","https://openalex.org/W2794908468","https://openalex.org/W2531570999","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W4206276646","https://openalex.org/W101422005","https://openalex.org/W192740413","https://openalex.org/W2952937263"],"abstract_inverted_index":{"Standard":[0],"acoustic":[1],"event":[2],"classification":[3],"(AEC)":[4],"solutions":[5],"require":[6,144],"large-scale":[7],"collection":[8,28],"of":[9,43,79,93,101],"data":[10,27,53,109,150],"from":[11,69,133,155],"client":[12],"devices":[13],"for":[14,89],"model":[15,30],"optimization.":[16],"Federated":[17],"learning":[18,84,92,146],"(FL)":[19],"is":[20,153,160],"a":[21],"compelling":[22],"frame-":[23],"work":[24,131,135],"that":[25,139],"decouples":[26],"and":[29,95,148,159],"training":[31],"to":[32,46,58,85,112,123,162],"enhance":[33],"customer":[34,52],"privacy.":[35],"In":[36],"this":[37],"work,":[38],"we":[39,151],"investigate":[40],"the":[41,59,75,86,102,113,117,128,149,165],"feasibility":[42],"applying":[44],"FL":[45,87,137],"improve":[47],"AEC":[48,104],"performance":[49,100],"while":[50,126],"no":[51,63],"can":[54,66],"be":[55,67],"directly":[56],"uploaded":[57],"server.":[60],"We":[61,81],"assume":[62],"pseudo":[64],"labels":[65],"inferred":[68],"on-device":[70,90],"user":[71],"inputs,":[72],"aligning":[73],"with":[74],"typical":[76],"use":[77,152],"cases":[78],"AEC.":[80],"adapt":[82],"self-supervised":[83],"framework":[88],"continual":[91],"representations,":[94],"it":[96],"results":[97],"in":[98,136,138],"improved":[99],"downstream":[103],"classifiers":[105],"with-":[106],"out":[107],"labeled/pseudo-labeled":[108],"available.":[110],"Compared":[111],"baseline":[114],"w/o":[115],"FL,":[116],"proposed":[118],"method":[119],"improves":[120],"precision":[121],"up":[122],"20.3%":[124],"relatively":[125],"maintaining":[127],"recall.":[129],"Our":[130],"differs":[132],"prior":[134],"our":[140,156],"approach":[141],"does":[142],"not":[143],"user-generated":[145],"targets,":[147],"collected":[154],"Beta":[157],"program":[158],"de-identified,":[161],"maximally":[163],"simulate":[164],"production":[166],"settings.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}