{"id":"https://openalex.org/W3016059657","doi":"https://doi.org/10.1109/icassp40776.2020.9053459","title":"Duration Robust Weakly Supervised Sound Event Detection","display_name":"Duration Robust Weakly Supervised Sound Event Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016059657","doi":"https://doi.org/10.1109/icassp40776.2020.9053459","mag":"3016059657"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053459","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.03841","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080154283"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.8095,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.9414382,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"315"},"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":0.9976000189781189,"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":0.9891999959945679,"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":0.6959825158119202},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6650140285491943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5290400385856628},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.5252953171730042},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.461870938539505},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4505772888660431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4054149389266968},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08686402440071106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959825158119202},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6650140285491943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5290400385856628},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.5252953171730042},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.461870938539505},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4505772888660431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4054149389266968},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08686402440071106},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053459","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:arXiv.org:1904.03841","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03841","pdf_url":"https://arxiv.org/pdf/1904.03841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.03841","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03841","pdf_url":"https://arxiv.org/pdf/1904.03841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2604490051","https://openalex.org/W2606833507","https://openalex.org/W2758870122","https://openalex.org/W2759176740","https://openalex.org/W2760098415","https://openalex.org/W2884011836","https://openalex.org/W2899771611","https://openalex.org/W2901203584","https://openalex.org/W2958610392","https://openalex.org/W2962924597","https://openalex.org/W2963202769","https://openalex.org/W2963216549","https://openalex.org/W2963460857","https://openalex.org/W2963610932","https://openalex.org/W2963656735","https://openalex.org/W2963919294","https://openalex.org/W2963970792","https://openalex.org/W2977846024","https://openalex.org/W2998304428","https://openalex.org/W3017521796","https://openalex.org/W3123940584","https://openalex.org/W4289329167","https://openalex.org/W6688902765","https://openalex.org/W6735013348","https://openalex.org/W6753516609","https://openalex.org/W6765705499"],"related_works":["https://openalex.org/W1542224353","https://openalex.org/W1661087619","https://openalex.org/W2116854923","https://openalex.org/W2750730210","https://openalex.org/W2236974868","https://openalex.org/W4312766348","https://openalex.org/W4233939244","https://openalex.org/W2730764323","https://openalex.org/W3123806511","https://openalex.org/W1976727107"],"abstract_inverted_index":{"Task":[0],"4":[1],"of":[2,17,50,60],"the":[3,22,47,58,78,99,107,128,132],"DCASE2018":[4],"challenge":[5,23],"demonstrated":[6],"that":[7,29,94],"substantially":[8],"more":[9,65],"research":[10],"is":[11],"needed":[12],"for":[13,95],"a":[14,64,103],"real-world":[15],"application":[16],"sound":[18,118],"event":[19,141],"detection.":[20],"Analyzing":[21],"results":[24],"it":[25],"can":[26],"be":[27],"seen":[28],"most":[30],"successful":[31],"models":[32],"are":[33,81],"biased":[34],"towards":[35,115],"predicting":[36],"long":[37],"(e.g.,":[38],"over":[39],"5s)":[40],"clips.":[41],"This":[42],"work":[43],"aims":[44],"to":[45,140],"investigate":[46],"performance":[48],"impact":[49],"fixed-sized":[51],"window":[52],"median":[53],"filter":[54],"post-processing":[55,69],"and":[56,67,90,131],"advocate":[57],"use":[59],"double":[61],"thresholding":[62],"as":[63,110,112],"robust":[66,139],"predictable":[68],"method.":[70],"Further,":[71],"four":[72],"different":[73],"temporal":[74,100],"subsampling":[75,98],"methods":[76],"within":[77],"CRNN":[79],"framework":[80],"proposed:":[82],"mean-max,":[83],"\u03b1-mean-max,":[84],"L":[85],"<sup":[86],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[87],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">p</sup>":[88],"-norm":[89],"convolutional.":[91],"We":[92],"show":[93],"this":[96],"task":[97],"resolution":[101],"by":[102],"neural":[104],"network":[105],"enhances":[106],"F1":[108,126],"score":[109],"well":[111],"its":[113],"robustness":[114],"short,":[116],"sporadic":[117],"events.":[119],"Our":[120],"best":[121,133],"single":[122],"model":[123,135],"achieves":[124],"30.1%":[125],"on":[127],"evaluation":[129],"set":[130],"fusion":[134],"32.5%,":[136],"while":[137],"being":[138],"length":[142],"variations.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}