{"id":"https://openalex.org/W3015792128","doi":"https://doi.org/10.1109/icassp40776.2020.9053073","title":"Task-Aware Mean Teacher Method for Large Scale Weakly Labeled Semi-Supervised Sound Event Detection","display_name":"Task-Aware Mean Teacher Method for Large Scale Weakly Labeled Semi-Supervised Sound Event Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015792128","doi":"https://doi.org/10.1109/icassp40776.2020.9053073","mag":"3015792128"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Task-Aware_Mean_Teacher_Method_for_Large_Scale_Weakly_Labeled_Semi-Supervised_Sound_Event_Detection/24217470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101437836","display_name":"Jie Yan","orcid":"https://orcid.org/0000-0001-9512-322X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yan","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I167056439","display_name":"Medway School of Pharmacy","ror":"https://ror.org/00fa9v295","country_code":"GB","type":"education","lineage":["https://openalex.org/I167056439"]},{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["School of Computing, University of Kent, Medway, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Kent, Medway, UK","institution_ids":["https://openalex.org/I167056439","https://openalex.org/I20581793"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"330"},"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":0.9983000159263611,"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":0.9732999801635742,"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":0.7530955076217651},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6402572393417358},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.592399001121521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5705856084823608},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5093165636062622},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4950930178165436},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45443999767303467},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4494676887989044},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4150873124599457},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3783947229385376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3677307367324829}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7530955076217651},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6402572393417358},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.592399001121521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5705856084823608},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5093165636062622},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4950930178165436},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45443999767303467},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4494676887989044},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4150873124599457},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3783947229385376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3677307367324829},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/24217470","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Task-Aware_Mean_Teacher_Method_for_Large_Scale_Weakly_Labeled_Semi-Supervised_Sound_Event_Detection/24217470","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/24217470","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Task-Aware_Mean_Teacher_Method_for_Large_Scale_Weakly_Labeled_Semi-Supervised_Sound_Event_Detection/24217470","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"Conference contribution"},"sustainable_development_goals":[{"score":0.8700000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W1970578576","https://openalex.org/W2043194666","https://openalex.org/W2147917435","https://openalex.org/W2431080869","https://openalex.org/W2526050071","https://openalex.org/W2530816535","https://openalex.org/W2567070169","https://openalex.org/W2592691248","https://openalex.org/W2604490051","https://openalex.org/W2706729717","https://openalex.org/W2884011836","https://openalex.org/W2890685186","https://openalex.org/W2936774411","https://openalex.org/W2939641110","https://openalex.org/W2951970475","https://openalex.org/W2953070460","https://openalex.org/W2963435192","https://openalex.org/W2963723765","https://openalex.org/W2963970792","https://openalex.org/W2964159205","https://openalex.org/W2982468701","https://openalex.org/W3209458476","https://openalex.org/W4289329167","https://openalex.org/W6717772578","https://openalex.org/W6731370813","https://openalex.org/W6733814495","https://openalex.org/W6739520758","https://openalex.org/W6753516609","https://openalex.org/W6764051988"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2969450769"],"abstract_inverted_index":{"Weakly":[0],"labeled":[1],"semi-supervised":[2,103],"learning":[3,104],"methods":[4],"have":[5],"recently":[6],"drawn":[7],"increasing":[8],"attention":[9],"from":[10,159],"the":[11,21,24,42,67,83,96,111,114,123,134,139,147,153,165,176,180,183,191],"research":[12],"community":[13],"for":[14,82,95],"sound":[15,33],"event":[16,34],"detection":[17,35],"tasks.":[18],"Due":[19],"to":[20,31,65,109,132],"weakness":[22],"of":[23,113,138,167,175,182],"labelling,":[25],"neural":[26,59],"networks":[27],"are":[28],"often":[29],"designed":[30,81,94],"perform":[32],"(SED)":[36],"and":[37,69,155],"audio":[38],"tagging":[39],"(AT)":[40],"at":[41],"same":[43],"time.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"a":[50,56,74,87,130,168],"task-aware":[51],"mean":[52,100],"teacher":[53,101,131],"method":[54,105],"using":[55],"convolutional":[57],"recurrent":[58],"network":[60],"(CRNN)":[61],"with":[62,76,89],"multi-branch":[63],"structure":[64],"solve":[66],"SED":[68,97,141,148,156],"AT":[70,84,116,125,136,154],"tasks":[71],"differently.":[72],"Specifically,":[73],"branch":[75,88,117,126],"coarse-level":[77,115,124],"temporal":[78,91],"resolution":[79,92],"is":[80,93,106,127,162],"task,":[85],"while":[86],"fine-level":[90,140],"task.":[98],"The":[99],"based":[102],"first":[107],"adopted":[108],"improve":[110,152],"performance":[112],"by":[118],"exploiting":[119],"unlabeled":[120],"data.":[121],"Then":[122],"introduced":[128],"as":[129],"guide":[133],"aggregated":[135],"output":[137],"branch,":[142],"yielding":[143],"an":[144],"improvement":[145],"in":[146,164],"performance.":[149],"To":[150],"further":[151],"performance,":[157],"information":[158],"multiple":[160],"layers":[161],"exploited":[163],"form":[166],"multi-resolution":[169],"feature.":[170],"Experimental":[171],"results":[172],"on":[173],"Task4":[174],"DCASE2018":[177],"challenge":[178],"demonstrate":[179],"superiority":[181],"proposed":[184],"method,":[185],"achieving":[186],"37.7%":[187],"F1-score,":[188],"which":[189],"outperforms":[190],"winning":[192],"system's":[193],"32.4%.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}