{"id":"https://openalex.org/W4408353426","doi":"https://doi.org/10.1109/icassp49660.2025.10889194","title":"MTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection","display_name":"MTDA-HSED: Mutual-Assistance Tuning and Dual-Branch Aggregating for Heterogeneous Sound Event Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353426","doi":"https://doi.org/10.1109/icassp49660.2025.10889194"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5100769599","display_name":"Zehao Wang","orcid":"https://orcid.org/0000-0002-7723-1945"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zehao Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071936376","display_name":"Haobo Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobo Yue","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456083","display_name":"Zhicheng Zhang","orcid":"https://orcid.org/0000-0002-5333-1394"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102229312","display_name":"Da Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Mu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030720334","display_name":"Jin Tang","orcid":"https://orcid.org/0000-0001-8375-3590"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Tang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100606496","display_name":"Jianqin Yin","orcid":"https://orcid.org/0000-0002-1595-2499"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqin Yin","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,School of Intelligent Engineering and Automation,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100769599"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05416716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9810000061988831,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9591000080108643,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7105517983436584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6545842885971069},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5431257486343384},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.46724581718444824},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3391638398170471},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2295905351638794}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7105517983436584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6545842885971069},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5431257486343384},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.46724581718444824},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3391638398170471},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2295905351638794},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322866","display_name":"Natural Science Foundation of Hainan Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2936774411","https://openalex.org/W2959539607","https://openalex.org/W3006275583","https://openalex.org/W3015190346","https://openalex.org/W3084086733","https://openalex.org/W3124216180","https://openalex.org/W3178592608","https://openalex.org/W4224920041","https://openalex.org/W4289521424","https://openalex.org/W4312097369","https://openalex.org/W4315926819","https://openalex.org/W4319300717","https://openalex.org/W4372263379","https://openalex.org/W4375839990","https://openalex.org/W4384702789","https://openalex.org/W4385823229","https://openalex.org/W4391028792","https://openalex.org/W4392904244","https://openalex.org/W6733814495","https://openalex.org/W6838701581","https://openalex.org/W6848208918","https://openalex.org/W6858196486","https://openalex.org/W6862412920","https://openalex.org/W6870090694"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2909726438"],"abstract_inverted_index":{"Sound":[0,50],"Event":[1,51],"Detection":[2,52],"(SED)":[3],"plays":[4],"a":[5,38],"vital":[6],"role":[7],"in":[8,24],"comprehending":[9],"and":[10,45,69,109,122,143],"perceiving":[11],"acoustic":[12],"scenes.":[13],"Previous":[14],"methods":[15,132],"have":[16],"demonstrated":[17],"impressive":[18],"capabilities.":[19],"However,":[20],"they":[21],"are":[22],"deficient":[23],"learning":[25],"features":[26],"of":[27,117,136],"complex":[28],"scenes":[29],"from":[30,119],"heterogeneous":[31],"dataset.":[32,103],"In":[33],"this":[34],"paper,":[35],"we":[36],"introduce":[37],"novel":[39],"dual-branch":[40],"architecture":[41,56],"named":[42],"Mutual-Assistance":[43,59],"Tuning":[44],"Dual-Branch":[46,72],"Aggregating":[47],"for":[48],"Heterogeneous":[49],"(MTDA-HSED).":[53],"The":[54,104],"MTDA-HSED":[55],"employs":[57],"the":[58,66,71,78,86,94,101,114,120,123,130,134,141],"Audio":[60],"Adapter":[61],"(M3A)":[62],"to":[63,76,92],"effectively":[64],"tackle":[65,77],"multi-scenario":[67,102],"problem":[68],"uses":[70],"Mid-Fusion":[73],"(DBMF)":[74],"module":[75,106],"multi-granularity":[79],"problem.":[80],"Specifically,":[81],"M3A":[82],"is":[83],"integrated":[84],"into":[85],"BEATs":[87,108,121],"block":[88],"as":[89],"an":[90],"adapter":[91],"improve":[93],"BEATs\u2019":[95],"performance":[96],"by":[97,138],"fine-tuning":[98],"it":[99],"on":[100,140],"DBMF":[105],"connects":[107],"CNN":[110,124],"branches,":[111],"which":[112],"facilitates":[113],"deep":[115],"fusion":[116],"information":[118],"branches.":[125],"Experimental":[126],"results":[127],"show":[128],"that":[129],"proposed":[131],"exceed":[133],"baseline":[135],"mpAUC":[137],"5%":[139],"DESED":[142],"MAESTRO":[144],"Real":[145],"datasets.":[146]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
