{"id":"https://openalex.org/W3207699776","doi":"https://doi.org/10.1109/icassp43922.2022.9746042","title":"A Mutual Learning Framework for Few-Shot Sound Event Detection","display_name":"A Mutual Learning Framework for Few-Shot Sound Event Detection","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207699776","doi":"https://doi.org/10.1109/icassp43922.2022.9746042","mag":"3207699776"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746042","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":"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/A5043555011","display_name":"Dongchao Yang","orcid":"https://orcid.org/0000-0002-8905-224X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongchao Yang","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China","ADSPLAB, School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664824","display_name":"Helin Wang","orcid":"https://orcid.org/0000-0001-6088-0378"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helin Wang","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China","ADSPLAB, School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China","ADSPLAB, School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038853796","display_name":"Zhongjie Ye","orcid":"https://orcid.org/0000-0003-0306-5267"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjie Ye","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,Shenzhen,China","ADSPLAB, School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Center for Vision, Speech and Signal Processing,UK","Center for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Center for Vision, Speech and Signal Processing,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043555011"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.8222,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87724268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"811","last_page":"815"},"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":0.9937999844551086,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7510983943939209},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.7256170511245728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6573188900947571},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6532889604568481},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6395052075386047},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6115999221801758},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6087110638618469},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5556448101997375},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5469681024551392},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5276105403900146},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4578084647655487},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45647743344306946},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44649991393089294},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33113008737564087},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07525116205215454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510983943939209},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.7256170511245728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6573188900947571},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6532889604568481},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6395052075386047},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6115999221801758},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6087110638618469},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5556448101997375},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5469681024551392},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5276105403900146},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4578084647655487},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45647743344306946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44649991393089294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33113008737564087},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07525116205215454},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"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/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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746042","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"},{"id":"pmh:oai:alma.44SUR_INST:11161477850002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2145494108","https://openalex.org/W2187089797","https://openalex.org/W2293363371","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2601450892","https://openalex.org/W2895671740","https://openalex.org/W2962845248","https://openalex.org/W2962999716","https://openalex.org/W2978426779","https://openalex.org/W3015205011","https://openalex.org/W3015474227","https://openalex.org/W3034312118","https://openalex.org/W3034587791","https://openalex.org/W3094550259","https://openalex.org/W3102998533","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3167453437","https://openalex.org/W3208710709","https://openalex.org/W6638523607","https://openalex.org/W6734260513","https://openalex.org/W6735236233","https://openalex.org/W6755766585","https://openalex.org/W6762913911","https://openalex.org/W6785450627","https://openalex.org/W6803564961"],"related_works":["https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2144059113","https://openalex.org/W3003836766","https://openalex.org/W1964120219","https://openalex.org/W2000165426","https://openalex.org/W2385132419","https://openalex.org/W2772780115","https://openalex.org/W2114557664","https://openalex.org/W2546942002"],"abstract_inverted_index":{"Although":[0],"prototypical":[1],"network":[2],"(ProtoNet)":[3],"has":[4],"proved":[5],"to":[6,58,90,97,104,116,121,127],"be":[7,117],"an":[8],"effective":[9],"method":[10,145],"for":[11],"few-shot":[12,166],"sound":[13],"event":[14,168],"detection,":[15],"two":[16],"problems":[17],"still":[18],"exist.":[19],"Firstly,":[20],"the":[21,29,35,40,47,80,99,105,113,123,129,147,152,161,165],"small-scaled":[22],"support":[23],"set":[24],"is":[25,43,50],"insufficient":[26],"so":[27],"that":[28],"class":[30,36,81,92,100,107,125,142],"prototypes":[31,82,93,101,126],"may":[32],"not":[33],"represent":[34],"center":[37,108],"accurately.":[38],"Secondly,":[39],"feature":[41,48,84,114,130,136],"extractor":[42,49,115,137],"task-agnostic":[44],"(or":[45],"class-agnostic):":[46],"trained":[51],"with":[52,72,94],"base-class":[53],"data":[54],"and":[55,83,173,178],"directly":[56],"applied":[57],"unseen-class":[59],"data.":[60],"To":[61,111],"address":[62],"these":[63],"issues,":[64],"we":[65,88,119],"present":[66],"a":[67,134],"novel":[68],"mutual":[69],"learning":[70],"framework":[71],"transductive":[73,95],"learning,":[74],"which":[75,159],"aims":[76],"at":[77],"iteratively":[78],"updating":[79],"extractor.":[85,131],"More":[86],"specifically,":[87],"propose":[89,120],"update":[91],"inference":[96],"make":[98,112],"as":[102,109],"close":[103],"true":[106],"possible.":[110],"task-specific,":[118],"use":[122],"updated":[124],"fine-tune":[128],"After":[132],"that,":[133],"fine-tuned":[135],"further":[138],"helps":[139],"produce":[140],"better":[141],"prototypes.":[143],"Our":[144],"achieves":[146],"F-score":[148],"of":[149,171,175],"38.4%":[150],"on":[151],"DCASE":[153],"2021":[154,181],"Task":[155],"5":[156],"evaluation":[157],"set,":[158],"won":[160],"first":[162],"place":[163],"in":[164],"bioacoustic":[167],"detection":[169],"task":[170],"Detection":[172],"Classification":[174],"Acoustic":[176],"Scenes":[177],"Events":[179],"(DCASE)":[180],"Challenge.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}