{"id":"https://openalex.org/W4413168959","doi":"https://doi.org/10.1007/s44443-025-00181-5","title":"Revisiting SSL for sound event detection: complementary fusion and adaptive post-processing","display_name":"Revisiting SSL for sound event detection: complementary fusion and adaptive post-processing","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4413168959","doi":"https://doi.org/10.1007/s44443-025-00181-5"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-025-00181-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00181-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00181-5.pdf","source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00181-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091512445","display_name":"Heng Cui","orcid":"https://orcid.org/0000-0001-7916-7353"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanfang Cui","raw_affiliation_strings":["Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Longfei Song","orcid":null},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longfei Song","raw_affiliation_strings":["Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361143","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-3515-7353"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072265807","display_name":"Dongxing Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongxing Xu","raw_affiliation_strings":["Unisound AI Technology Co., Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["Shanghai Normal University, Shanghai, China","Unisound AI Technology Co., Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5056415893"],"corresponding_institution_ids":["https://openalex.org/I21945476"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21997082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"6","first_page":null,"last_page":null},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.5676920413970947},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5566787123680115},{"id":"https://openalex.org/keywords/complex-event-processing","display_name":"Complex event processing","score":0.5060874819755554},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4162728488445282},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37300002574920654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33802270889282227},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21696078777313232},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11517176032066345},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06591138243675232},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.04742249846458435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5676920413970947},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5566787123680115},{"id":"https://openalex.org/C123606473","wikidata":"https://www.wikidata.org/wiki/Q907918","display_name":"Complex event processing","level":3,"score":0.5060874819755554},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4162728488445282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37300002574920654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33802270889282227},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21696078777313232},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11517176032066345},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06591138243675232},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.04742249846458435},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s44443-025-00181-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00181-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00181-5.pdf","source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2505.11889","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11889","pdf_url":"https://arxiv.org/pdf/2505.11889","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"},{"id":"pmh:oai:doaj.org/article:4a86db2b0d774b49964795722bb5fc2d","is_oa":true,"landing_page_url":"https://doaj.org/article/4a86db2b0d774b49964795722bb5fc2d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of King Saud University: Computer and Information Sciences, Vol 37, Iss 6, Pp 1-18 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-025-00181-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00181-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44443-025-00181-5.pdf","source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G514874842","display_name":"\u4f4e\u8d44\u6e90\u6761\u4ef6\u4e0b\u7684\u91cd\u53e3\u97f3\u9c81\u68d2\u6027\u58f0\u5b66\u5efa\u6a21\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62071302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413168959.pdf","grobid_xml":"https://content.openalex.org/works/W4413168959.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2036931953","https://openalex.org/W2112796928","https://openalex.org/W2194187530","https://openalex.org/W2296193698","https://openalex.org/W2322143332","https://openalex.org/W2759176740","https://openalex.org/W2912056372","https://openalex.org/W2959539607","https://openalex.org/W2973049979","https://openalex.org/W3015190346","https://openalex.org/W3094550259","https://openalex.org/W3196645599","https://openalex.org/W3196974791","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3212264559","https://openalex.org/W4210632456","https://openalex.org/W4221149441","https://openalex.org/W4297808394","https://openalex.org/W4313156423","https://openalex.org/W4387350515","https://openalex.org/W4390738640","https://openalex.org/W4391790571","https://openalex.org/W4392904244","https://openalex.org/W4396743044","https://openalex.org/W4402111776","https://openalex.org/W4402112407","https://openalex.org/W4402112469","https://openalex.org/W4402170843","https://openalex.org/W4405710132","https://openalex.org/W4407242217","https://openalex.org/W6600020421","https://openalex.org/W6600704668","https://openalex.org/W6604009900","https://openalex.org/W6725534529"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W1607805252","https://openalex.org/W2397597979","https://openalex.org/W2799235612","https://openalex.org/W1835640443","https://openalex.org/W2072592647","https://openalex.org/W4308672222","https://openalex.org/W413387906"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"models":[3,24],"offer":[4],"powerful":[5],"representations":[6,46],"for":[7,32,117,144,157],"sound":[8,94],"event":[9,95],"detection":[10,108],"(SED),":[11],"yet":[12],"their":[13],"synergistic":[14],"potential":[15],"remains":[16],"underexplored.":[17],"This":[18],"study":[19],"systematically":[20],"evaluates":[21],"state-of-the-art":[22],"SSL":[23,40,52,85,119,127,148],"to":[25,115],"guide":[26],"optimal":[27],"model":[28,41,128],"selection":[29],"and":[30,57,134,146,155],"integration":[31,87],"SED.":[33],"We":[34,89],"propose":[35],"a":[36,92,142],"framework":[37],"combining":[38],"heterogeneous":[39],"(BEATs,":[42],"HuBERT,":[43],"WavLM,":[44],"etc.)":[45],"through":[47],"three":[48],"fusion":[49,72,133],"strategies:":[50],"individual":[51,84],"embedding":[53,86],"integration,":[54],"dual-modal":[55,71],"fusion,":[56],"full":[58],"aggregation.":[59],"Our":[60,139],"experiments":[61],"on":[62],"the":[63],"DCASE":[64],"2023":[65],"Task":[66],"4":[67],"Challenge":[68],"reveal":[69],"that":[70,103,131],"(e.g.,":[73],"CRNN+BEATs+WavLM)":[74],"achieves":[75],"complementary":[76],"performance":[77],"gains,":[78],"while":[79],"CRNN+BEATs":[80],"alone":[81],"attains":[82],"superior":[83],"results.":[88],"further":[90],"introduce":[91],"normalized":[93],"bounding":[96],"boxes":[97],"(nSEBBs),":[98],"an":[99],"adaptive":[100],"post-processing":[101,136],"method":[102],"dynamically":[104],"adjusts":[105],"target":[106],"events":[107],"boundaries,":[109],"improving":[110],"PSDS":[111],"$$_1$$":[112],"by":[113],"up":[114],"4%":[116],"standalone":[118],"models.":[120],"These":[121],"findings":[122],"provide":[123],"important":[124],"insights":[125],"into":[126],"compatibility,":[129],"demonstrating":[130],"task-specific":[132],"dynamic":[135],"enhance":[137],"robustness.":[138],"work":[140],"establishes":[141],"reference":[143],"selecting":[145],"integrating":[147],"architectures":[149],"in":[150],"SED":[151],"systems,":[152],"balancing":[153],"efficiency":[154],"accuracy":[156],"real-world":[158],"deployment.":[159]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
