{"id":"https://openalex.org/W4401990901","doi":"https://doi.org/10.1109/taslp.2024.3451983","title":"Sound Activity-Aware Based Cross-Task Collaborative Training for Semi-Supervised Sound Event Detection","display_name":"Sound Activity-Aware Based Cross-Task Collaborative Training for Semi-Supervised Sound Event Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401990901","doi":"https://doi.org/10.1109/taslp.2024.3451983"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3451983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3451983","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":["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/A5053853990","display_name":"Yadong Guan","orcid":"https://orcid.org/0009-0002-6031-9892"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Guan","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0002-6031-9892","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-4297-4300","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057908066","display_name":"Hongwei Song","orcid":"https://orcid.org/0000-0003-1928-8182"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Song","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-1928-8182","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087019132","display_name":"Shiwen Deng","orcid":"https://orcid.org/0000-0001-8964-3165"},"institutions":[{"id":"https://openalex.org/I134052481","display_name":"Harbin Normal University","ror":"https://ror.org/0270y6950","country_code":"CN","type":"education","lineage":["https://openalex.org/I134052481"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwen Deng","raw_affiliation_strings":["School of Mathematical Science, Harbin Normal University, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-8964-3165","affiliations":[{"raw_affiliation_string":"School of Mathematical Science, Harbin Normal University, Harbin, China","institution_ids":["https://openalex.org/I134052481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041058909","display_name":"Guibin Zheng","orcid":"https://orcid.org/0000-0002-4280-5224"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guibin Zheng","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-4280-5224","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846141","display_name":"Tieran Zheng","orcid":"https://orcid.org/0009-0006-5179-0278"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieran Zheng","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0006-5179-0278","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026346396","display_name":"Yongjun He","orcid":"https://orcid.org/0000-0002-5156-651X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun He","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-5156-651X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9708,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87332521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3947","last_page":"3959"},"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":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/sound","display_name":"Sound (geography)","score":0.8169070482254028},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6648933291435242},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6624529957771301},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5503430366516113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5301305651664734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3941264748573303},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18885430693626404},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13923263549804688},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09175023436546326}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.8169070482254028},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6648933291435242},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6624529957771301},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5503430366516113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5301305651664734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3941264748573303},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18885430693626404},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13923263549804688},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09175023436546326},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3451983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3451983","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6374422366","display_name":null,"funder_award_id":"62376071","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2072184010","https://openalex.org/W2591013610","https://openalex.org/W2759976799","https://openalex.org/W2795701516","https://openalex.org/W2936774411","https://openalex.org/W2938357656","https://openalex.org/W2959539607","https://openalex.org/W2963723765","https://openalex.org/W2966415767","https://openalex.org/W3006275583","https://openalex.org/W3015190346","https://openalex.org/W3016195076","https://openalex.org/W3017521796","https://openalex.org/W3034225195","https://openalex.org/W3049446265","https://openalex.org/W3094502228","https://openalex.org/W3097777922","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3160339728","https://openalex.org/W3161447515","https://openalex.org/W3162400960","https://openalex.org/W3164302487","https://openalex.org/W3179917056","https://openalex.org/W3182910640","https://openalex.org/W3199127113","https://openalex.org/W3203468141","https://openalex.org/W4200337780","https://openalex.org/W4205377075","https://openalex.org/W4221149441","https://openalex.org/W4224924117","https://openalex.org/W4224932888","https://openalex.org/W4225706374","https://openalex.org/W4283451606","https://openalex.org/W4296068822","https://openalex.org/W4319586842","https://openalex.org/W4372263379","https://openalex.org/W4375868802","https://openalex.org/W4380551836","https://openalex.org/W4385822570","https://openalex.org/W4390738640","https://openalex.org/W4392904244","https://openalex.org/W4392904573","https://openalex.org/W4392908945"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W4385572368"],"abstract_inverted_index":{"The":[0],"training":[1,28,42,51,123],"of":[2,11,43,116,230],"sound":[3,96,105,159],"event":[4],"detection":[5,100],"(SED)":[6],"models":[7],"remains":[8],"a":[9,44,93,120,146,179],"challenge":[10],"insufficient":[12],"supervision":[13],"due":[14],"to":[15,53,77,133,154,158,168,191],"limited":[16],"frame-wise":[17,67],"labeled":[18],"data.":[19],"Mainstream":[20],"research":[21],"on":[22,223],"this":[23,89],"problem":[24],"has":[25],"adopted":[26],"semi-supervised":[27],"strategies":[29,52],"that":[30,125,183],"generate":[31],"pseudo-labels":[32,195],"for":[33,40],"unlabeled":[34],"data":[35,39],"and":[36,98,110,131,174,196,216],"use":[37],"these":[38,63],"the":[41,58,114,127,135,142,149,162,188,202,206,224,228],"model.":[45,137],"Recent":[46],"works":[47],"further":[48],"introduce":[49,92],"multi-task":[50,147],"impose":[54],"additional":[55,214],"supervision.":[56,87],"However,":[57],"auxiliary":[59],"tasks":[60,144,190],"employed":[61],"in":[62,145],"methods":[64],"either":[65],"lack":[66],"guidance":[68],"or":[69],"exhibit":[70],"unsuitable":[71],"task":[72],"designs.":[73],"Furthermore,":[74],"they":[75],"fail":[76],"exploit":[78],"inter-task":[79],"relationships":[80],"effectively,":[81],"which":[82,102],"can":[83],"serve":[84],"as":[85],"valuable":[86],"In":[88,201],"paper,":[90],"we":[91,118,177],"novel":[94],"task,":[95],"occurrence":[97],"overlap":[99],"(SOD),":[101],"detects":[103],"predefined":[104],"activity":[106],"patterns,":[107],"including":[108],"non-overlapping":[109],"overlapping":[111],"cases.":[112],"On":[113],"basis":[115],"SOD,":[117],"propose":[119,178],"cross-task":[121,163],"collaborative":[122],"framework":[124],"leverages":[126],"relationship":[128],"between":[129,172,187],"SED":[130,136,150,173,208],"SOD":[132],"improve":[134],"Firstly,":[138],"by":[139],"jointly":[140],"optimizing":[141],"two":[143,189],"manner,":[148],"model":[151,209],"is":[152,166,210],"encouraged":[153],"learn":[155],"features":[156],"sensitive":[157],"activity.":[160],"Subsequently,":[161],"consistency":[164],"regularization":[165],"proposed":[167],"promote":[169],"consistent":[170],"predictions":[171,186],"SOD.":[175],"Finally,":[176],"pseudo-label":[180],"selection":[181],"method":[182],"uses":[184],"inconsistent":[185],"identify":[192],"potential":[193],"wrong":[194],"mitigate":[197],"their":[198],"confirmation":[199],"bias.":[200],"inference":[203],"phase,":[204],"only":[205],"trained":[207],"used,":[211],"thus":[212],"no":[213],"computation":[215],"storage":[217],"costs":[218],"are":[219],"incurred.":[220],"Extensive":[221],"experiments":[222],"DESED":[225],"dataset":[226],"demonstrate":[227],"effectiveness":[229],"our":[231],"method.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
