{"id":"https://openalex.org/W3124216180","doi":"https://doi.org/10.1109/taslp.2021.3054313","title":"Towards Duration Robust Weakly Supervised Sound Event Detection","display_name":"Towards Duration Robust Weakly Supervised Sound Event Detection","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3124216180","doi":"https://doi.org/10.1109/taslp.2021.3054313","mag":"3124216180"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3054313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3054313","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.07687","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":["SEIEE, Shanghai Jiao Tong University - Minhang Campus, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"SEIEE, Shanghai Jiao Tong University - Minhang Campus, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"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":"Mengyue Wu","raw_affiliation_strings":["Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Computer Science, 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":["Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080154283"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":6.4637,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.97476679,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"887","last_page":"900"},"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":0.9988999962806702,"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":0.9894999861717224,"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":0.7335150241851807},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6601210236549377},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6424729824066162},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.6126978397369385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5407254099845886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48842278122901917},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4585352838039398},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.41736355423927307},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.406220018863678},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39227113127708435},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12649139761924744},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.12014281749725342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335150241851807},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6601210236549377},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6424729824066162},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6126978397369385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5407254099845886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48842278122901917},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4585352838039398},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.41736355423927307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.406220018863678},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39227113127708435},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12649139761924744},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.12014281749725342},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3054313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3054313","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2101.07687","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.07687","pdf_url":"https://arxiv.org/pdf/2101.07687","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:2101.07687","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.07687","pdf_url":"https://arxiv.org/pdf/2101.07687","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":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G2643776831","display_name":null,"funder_award_id":"19X100040009","funder_id":"https://openalex.org/F4320322999","funder_display_name":"Shanghai Jiao Tong University"},{"id":"https://openalex.org/G3420185677","display_name":null,"funder_award_id":"61901265","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W54887220","https://openalex.org/W1522301498","https://openalex.org/W2038484192","https://openalex.org/W2110119381","https://openalex.org/W2183341477","https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2594407953","https://openalex.org/W2751116311","https://openalex.org/W2758870122","https://openalex.org/W2759176740","https://openalex.org/W2760098415","https://openalex.org/W2763971240","https://openalex.org/W2771361008","https://openalex.org/W2798158991","https://openalex.org/W2799258971","https://openalex.org/W2799768828","https://openalex.org/W2906926620","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2937959246","https://openalex.org/W2962924597","https://openalex.org/W2963216549","https://openalex.org/W2963369167","https://openalex.org/W2963517948","https://openalex.org/W2963610932","https://openalex.org/W2963656735","https://openalex.org/W2964121744","https://openalex.org/W2964891022","https://openalex.org/W2970971581","https://openalex.org/W2977846024","https://openalex.org/W3015190346","https://openalex.org/W3015295955","https://openalex.org/W3015387077","https://openalex.org/W3016059657","https://openalex.org/W3017521796","https://openalex.org/W3021500721","https://openalex.org/W3094550259","https://openalex.org/W3096625841","https://openalex.org/W3123416659","https://openalex.org/W3123940584","https://openalex.org/W3209073848","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6731878076","https://openalex.org/W6735013348","https://openalex.org/W6745117180","https://openalex.org/W6757817989","https://openalex.org/W6758076146","https://openalex.org/W6766978945","https://openalex.org/W6773464742","https://openalex.org/W6776837456"],"related_works":["https://openalex.org/W2060561905","https://openalex.org/W1417711376","https://openalex.org/W1986883493","https://openalex.org/W2469862403","https://openalex.org/W2166378262","https://openalex.org/W2035891203","https://openalex.org/W2348837382","https://openalex.org/W4379524643","https://openalex.org/W2367807705","https://openalex.org/W4385572368"],"abstract_inverted_index":{"Sound":[0],"event":[1,44,54,96],"detection":[2,55],"(SED)":[3],"is":[4,37,64,179,211,237],"the":[5,9,69,171,182,197,221],"task":[6],"of":[7,13,144,173,176,213],"tagging":[8],"absence":[10],"or":[11],"presence":[12],"audio":[14,23],"events":[15,124],"and":[16,46,158,184,189,199],"their":[17,117],"corresponding":[18],"interval":[19],"within":[20,68,170],"a":[21,112,130,151,166],"given":[22],"clip.":[24],"While":[25],"SED":[26],"can":[27],"be":[28],"done":[29,180],"using":[30],"supervised":[31,218],"machine":[32],"learning,":[33],"where":[34,57],"training":[35],"data":[36,161],"fully":[38,90],"labeled":[39,91],"with":[40,165,241],"access":[41],"to":[42,94,138,216,227],"per":[43],"timestamps":[45],"duration,":[47],"our":[48,177,209,232],"work":[49,128],"focuses":[50,71],"on":[51,72,119,181,196,220],"weakly-supervised":[52],"sound":[53],"(WSSED),":[56],"prior":[58,204],"knowledge":[59],"about":[60],"an":[61],"event's":[62],"duration":[63,97,131,205],"unavailable.":[65],"Recent":[66],"research":[67],"field":[70],"improving":[73],"segmentand":[74,145],"eventlevel":[75],"localization":[76,88,102,107,234],"performance":[77,141,215,235],"for":[78],"specific":[79,82],"datasets":[80,120,201],"regarding":[81],"evaluation":[83],"metrics.":[84],"Specifically,":[85],"well-performing":[86,105],"event-level":[87,146],"requires":[89],"development":[92],"subsets":[93],"obtain":[95],"estimates,":[98],"which":[99,136],"significantly":[100,238],"benefits":[101],"performance.":[103],"Moreover,":[104],"segment-level":[106],"models":[108,219],"output":[109],"predictions":[110],"at":[111],"coarse-scale":[113],"(e.g.,1":[114],"second),":[115],"hindering":[116],"deployment":[118],"containing":[121],"very":[122],"short":[123],"(<;":[125],"1second).":[126],"This":[127,148],"proposes":[129,150],"robust":[132],"CRNN":[133],"(CDur)":[134],"framework,":[135],"aims":[137],"achieve":[139],"competitive":[140],"in":[142],"terms":[143],"localization.":[147],"paper":[149],"new":[152],"post-processing":[153],"strategy":[154],"named":[155],"\u201cTriple":[156],"Threshold\u201d":[157],"investigates":[159],"two":[160],"augmentation":[162],"methods":[163],"along":[164],"label":[167],"smoothing":[168],"method":[169],"scope":[172],"WSSED.":[174],"Evaluation":[175],"model":[178,192,210],"DCASE2017":[183],"2018":[185],"Task":[186],"4":[187],"datasets,":[188],"URBAN-SED.":[190],"Our":[191],"outperforms":[193],"other":[194,242],"approaches":[195],"DCASE2018":[198],"URBAN-SED":[200],"without":[202,230],"requiring":[203],"knowledge.":[206],"In":[207],"particular,":[208],"capable":[212],"similar":[214],"strongly-labeled":[217],"URBANSED":[222],"dataset.":[223],"Lastly,":[224],"ablation":[225],"experiments":[226],"reveal":[228],"that":[229],"post-processing,":[231],"model's":[233],"drop":[236],"lower":[239],"compared":[240],"approaches.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":9}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}