{"id":"https://openalex.org/W4392908945","doi":"https://doi.org/10.1109/icassp48485.2024.10446386","title":"Semi-Supervised Sound Event Detection with Local and Global Consistency Regularization","display_name":"Semi-Supervised Sound Event Detection with Local and Global Consistency Regularization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908945","doi":"https://doi.org/10.1109/icassp48485.2024.10446386"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100346326","display_name":"Yiming Li","orcid":"https://orcid.org/0000-0002-1284-7773"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiming Li","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","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/A5100402345","display_name":"Xiangdong Wang","orcid":"https://orcid.org/0000-0002-4226-3250"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410374","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0003-4524-495X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Beijing,China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600683","display_name":"Rui Tao","orcid":"https://orcid.org/0000-0001-6333-513X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Tao","raw_affiliation_strings":["Toshiba China R&D Center,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Toshiba China R&D Center,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017782552","display_name":"Long Yan","orcid":"https://orcid.org/0000-0002-2815-1332"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long Yan","raw_affiliation_strings":["Toshiba China R&D Center,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Toshiba China R&D Center,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017058806","display_name":"Kazushige Ouchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazushige Ouchi","raw_affiliation_strings":["Toshiba China R&D Center,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Toshiba China R&D Center,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100346326"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":2.2413,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87846014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"275"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9829000234603882,"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":0.9656000137329102,"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/regularization","display_name":"Regularization (linguistics)","score":0.6302701234817505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5681214928627014},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5475878715515137},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.49404314160346985},{"id":"https://openalex.org/keywords/local-consistency","display_name":"Local consistency","score":0.4194619357585907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38695505261421204},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3211407959461212},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07599237561225891}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6302701234817505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5681214928627014},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5475878715515137},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.49404314160346985},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.4194619357585907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38695505261421204},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3211407959461212},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07599237561225891},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.0},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"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/icassp48485.2024.10446386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1983320747","https://openalex.org/W2187089797","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2601450892","https://openalex.org/W2765407302","https://openalex.org/W2936774411","https://openalex.org/W2953070460","https://openalex.org/W2959539607","https://openalex.org/W2992308087","https://openalex.org/W3005680577","https://openalex.org/W3015190346","https://openalex.org/W3160339728","https://openalex.org/W3162391496","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W3203468141","https://openalex.org/W3209458476","https://openalex.org/W4221149441","https://openalex.org/W4225312629","https://openalex.org/W4225313599","https://openalex.org/W4283311932","https://openalex.org/W4296068822","https://openalex.org/W4296069153","https://openalex.org/W4310873011","https://openalex.org/W4372260505","https://openalex.org/W4372263379","https://openalex.org/W4375868802","https://openalex.org/W6603760306","https://openalex.org/W6733814495","https://openalex.org/W6735236233","https://openalex.org/W6745136726","https://openalex.org/W6774314701"],"related_works":["https://openalex.org/W1592998112","https://openalex.org/W1965377399","https://openalex.org/W1510768092","https://openalex.org/W2611003898","https://openalex.org/W4243135923","https://openalex.org/W2540973786","https://openalex.org/W1564991550","https://openalex.org/W2604924028","https://openalex.org/W52378903","https://openalex.org/W2076357653"],"abstract_inverted_index":{"Learning":[0],"meaningful":[1],"frame-wise":[2],"features":[3,86,98],"on":[4,21,56,111],"a":[5,44,105],"partially":[6],"labeled":[7],"dataset":[8,114],"is":[9,64,77,94,141],"crucial":[10],"to":[11,52,66,79,83,96,99],"semi-supervised":[12],"sound":[13],"event":[14],"detection.":[15],"Prior":[16],"works":[17],"either":[18],"maintain":[19],"consistency":[20,76,93],"frame-level":[22,88],"predictions":[23],"or":[24],"seek":[25],"feature-level":[26],"similarity":[27],"among":[28],"neighboring":[29],"frames,":[30],"which":[31],"cannot":[32],"exploit":[33],"the":[34,54,68,74,81,91,112,116,126],"potential":[35],"of":[36,71,118],"unlabeled":[37],"data.":[38],"In":[39],"this":[40],"work,":[41],"we":[42],"design":[43],"Local":[45],"and":[46,59,90],"Global":[47],"Consistency":[48],"(LGC)":[49],"regularization":[50],"scheme":[51],"enhance":[53],"model":[55,82],"both":[57],"label-":[58],"feature-level.":[60],"The":[61,139],"audio":[62],"CutMix":[63],"introduced":[65],"change":[67],"contextual":[69],"information":[70],"clips.":[72],"Then,":[73],"local":[75,85],"adopted":[78],"encourage":[80],"leverage":[84],"for":[87],"predictions,":[89],"global":[92,102],"applied":[95],"force":[97],"align":[100],"with":[101,132],"prototypes":[103],"through":[104],"specially":[106],"designed":[107],"contrastive":[108],"loss.":[109],"Experiments":[110],"DESED":[113],"indicate":[115],"superiority":[117],"LGC,":[119],"surpassing":[120],"its":[121],"respective":[122],"competitors":[123],"largely":[124],"under":[125],"same":[127],"settings.":[128],"Besides,":[129],"combining":[130],"LGC":[131],"existing":[133],"methods":[134],"can":[135],"obtain":[136],"further":[137],"improvements.":[138],"code":[140],"available":[142],"at":[143],"https://github.com/Ming-er/LGC-SED.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}