{"id":"https://openalex.org/W4224919083","doi":"https://doi.org/10.1109/icassp43922.2022.9746947","title":"A Multi-Task Learning Method for Weakly Supervised Sound Event Detection","display_name":"A Multi-Task Learning Method for Weakly Supervised Sound Event Detection","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224919083","doi":"https://doi.org/10.1109/icassp43922.2022.9746947"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746947","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/A5049130665","display_name":"Sichen Liu","orcid":"https://orcid.org/0009-0001-7388-0980"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sichen Liu","raw_affiliation_strings":["Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","University of Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences, Institute of Acoustics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088185643","display_name":"Feiran Yang","orcid":"https://orcid.org/0000-0002-1734-3785"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiran Yang","raw_affiliation_strings":["Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080498990","display_name":"Fang Kang","orcid":"https://orcid.org/0009-0004-3810-0717"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Kang","raw_affiliation_strings":["Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","University of Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences, Institute of Acoustics, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381075","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0003-2807-6130"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Acoustics, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049130665"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.4858,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56405414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8802","last_page":"8806"},"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":0.9995999932289124,"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":0.9926000237464905,"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":0.8086869120597839},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7284373044967651},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6074762344360352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5384691953659058},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5245307087898254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5167555212974548},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4921109080314636},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.41767388582229614},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4116627871990204},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40871551632881165},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33109861612319946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086869120597839},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7284373044967651},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6074762344360352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5384691953659058},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5245307087898254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167555212974548},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4921109080314636},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.41767388582229614},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4116627871990204},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40871551632881165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33109861612319946},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746947","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746947","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":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1522301498","https://openalex.org/W2086384421","https://openalex.org/W2135131618","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2759976799","https://openalex.org/W2770119437","https://openalex.org/W2798158991","https://openalex.org/W2804233018","https://openalex.org/W2963610932","https://openalex.org/W2963723765","https://openalex.org/W2964136284","https://openalex.org/W2964947054","https://openalex.org/W2982537717","https://openalex.org/W2984935418","https://openalex.org/W2985929325","https://openalex.org/W3005741390","https://openalex.org/W3006275583","https://openalex.org/W3015505732","https://openalex.org/W3094550259","https://openalex.org/W3104704316","https://openalex.org/W3121328487","https://openalex.org/W3123940584","https://openalex.org/W3165390575","https://openalex.org/W4205190992","https://openalex.org/W6631190155","https://openalex.org/W6746278845","https://openalex.org/W6773738941"],"related_works":["https://openalex.org/W4385482737","https://openalex.org/W3124278207","https://openalex.org/W3046871516","https://openalex.org/W2948333011","https://openalex.org/W4287694193","https://openalex.org/W4312745891","https://openalex.org/W1942758450","https://openalex.org/W2994972936","https://openalex.org/W2922338626","https://openalex.org/W3088045114"],"abstract_inverted_index":{"In":[0],"weakly":[1],"supervised":[2],"sound":[3,31],"event":[4],"detection":[5],"(SED),":[6],"only":[7],"coarse-grained":[8],"labels":[9],"are":[10],"available,":[11],"and":[12,48,130],"thus":[13],"the":[14,26,45,52,60,66,76,80,89,103,113,121,127],"supervision":[15],"information":[16],"is":[17],"quite":[18],"limited.":[19],"To":[20],"fully":[21],"utilize":[22],"prior":[23,110],"knowledge":[24,111],"of":[25,29,62,82,115],"time-frequency":[27],"masks":[28,64,83],"each":[30],"event,":[32],"we":[33,58],"propose":[34],"a":[35,132],"novel":[36],"multi-task":[37],"learning":[38],"(MTL)":[39],"method":[40,78,123],"that":[41,120],"takes":[42],"SED":[43,136],"as":[44,51,65,84],"main":[46],"task":[47,96,137],"source":[49,94],"separation":[50,95],"auxiliary":[53,93],"task.":[54],"For":[55,73],"active":[56],"events,":[57,75],"minimize":[59],"overlap":[61],"their":[63],"segment":[67],"loss":[68,86],"to":[69,87,102],"learn":[70],"distinguishing":[71],"features.":[72],"inactive":[74],"proposed":[77,122],"measures":[79],"activity":[81],"silent":[85],"reduce":[88,126],"insertion":[90,128],"error.":[91],"The":[92],"calculates":[97],"an":[98],"extra":[99],"penalty":[100],"according":[101],"shared":[104],"masks,":[105],"which":[106],"can":[107,124],"further":[108],"incorporate":[109],"in":[112,135],"form":[114],"regularization":[116],"constraints.":[117],"We":[118],"demonstrated":[119],"effectively":[125],"error":[129],"achieve":[131],"better":[133],"performance":[134],"than":[138],"single-task":[139],"methods.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-26T06:01:38.667478","created_date":"2025-10-10T00:00:00"}