{"id":"https://openalex.org/W4402979321","doi":"https://doi.org/10.1109/icme57554.2024.10688275","title":"Hierarchical Temporal Attention and Competent Teacher Network for Sound Event Detection","display_name":"Hierarchical Temporal Attention and Competent Teacher Network for Sound Event Detection","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979321","doi":"https://doi.org/10.1109/icme57554.2024.10688275"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688275","doi":"https://doi.org/10.1109/icme57554.2024.10688275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688275","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5034678630","display_name":"Yihang Zhang","orcid":"https://orcid.org/0009-0008-9446-5111","observed_orcids":["https://orcid.org/0009-0008-9446-5111","https://orcid.org/0009-0003-6480-9888","https://orcid.org/0009-0000-3028-900X","https://orcid.org/0009-0002-8759-8609","https://orcid.org/0009-0004-2488-3829","https://orcid.org/0009-0009-1378-563X"]},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihang Zhang","raw_affiliation_strings":["South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604862","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0003-0799-0054","observed_orcids":["https://orcid.org/0000-0003-0799-0054"]},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081355534","display_name":"Shitong Weng","orcid":"https://orcid.org/0000-0002-4751-6050","observed_orcids":["https://orcid.org/0000-0002-4751-6050"]},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shitong Weng","raw_affiliation_strings":["South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112884890","display_name":"Hai Yao Lin","orcid":"https://orcid.org/0009-0000-1822-1002","observed_orcids":["https://orcid.org/0009-0000-1822-1002"]},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Lin","raw_affiliation_strings":["South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430192","display_name":"Liping Chen","orcid":"https://orcid.org/0000-0002-8110-5378","observed_orcids":["https://orcid.org/0000-0002-8110-5378"]},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Chen","raw_affiliation_strings":["South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026517914","display_name":"Shenlong Zheng","orcid":"https://orcid.org/0009-0006-0361-0762","observed_orcids":["https://orcid.org/0009-0006-0361-0762"]},"institutions":[{"id":"https://openalex.org/I101479585","display_name":"South China Agricultural University","ror":"https://ror.org/05v9jqt67","country_code":"CN","type":"education","lineage":["https://openalex.org/I101479585"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenlong Zheng","raw_affiliation_strings":["South China Agricultural University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Agricultural University,Guangzhou,China","institution_ids":["https://openalex.org/I101479585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I101479585"],"apc_list":null,"apc_paid":null,"fwci":0.5727,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63217658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.0,"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":0.0,"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-event-detection","display_name":"sound event detection","score":1.0},{"id":"https://openalex.org/keywords/temporal-localization","display_name":"temporal localization","score":0.5860000252723694},{"id":"https://openalex.org/keywords/weak-labels","display_name":"weak labels","score":0.48500001430511475},{"id":"https://openalex.org/keywords/convolutional-recurrent-neural-network","display_name":"convolutional recurrent neural network","score":0.703000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6784749031066895},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6193707585334778},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5718483328819275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34180688858032227},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18487036228179932},{"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/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/icme57554.2024.10688275","doi":"https://doi.org/10.1109/icme57554.2024.10688275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688275","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2194187530","https://openalex.org/W2408239454","https://openalex.org/W2594627932","https://openalex.org/W2959539607","https://openalex.org/W2979507862","https://openalex.org/W2981733351","https://openalex.org/W2982623348","https://openalex.org/W3016195076","https://openalex.org/W3024686730","https://openalex.org/W3030949748","https://openalex.org/W3091692808","https://openalex.org/W3124216180","https://openalex.org/W3161435013","https://openalex.org/W3204067194","https://openalex.org/W3209572141","https://openalex.org/W3211807332","https://openalex.org/W4200292474","https://openalex.org/W4221149441","https://openalex.org/W4295215087","https://openalex.org/W4304080535"],"related_works":["https://openalex.org/W4312120874","https://openalex.org/W7207758592","https://openalex.org/W4409399598","https://openalex.org/W7163080232","https://openalex.org/W7133491652","https://openalex.org/W4415257473","https://openalex.org/W2972922917","https://openalex.org/W4401542284","https://openalex.org/W7125973849","https://openalex.org/W4403063533"],"abstract_inverted_index":{"Sound":[0],"event":[1,12,51],"detection":[2,67],"identifies":[3],"specific":[4],"auditory":[5],"signal":[6],"occurrences":[7],"to":[8,42,82,88],"recognize":[9],"the":[10,19,58,83,89,105,139],"sound":[11],"class":[13],"and":[14,49,63,78,110,142],"its":[15,32,37],"temporal":[16,47,62],"localization.":[17,53],"While":[18],"Convolutional":[20],"Recurrent":[21],"Neural":[22],"Network":[23,113],"with":[24],"a":[25,98],"mean-teacher":[26],"framework":[27],"shows":[28],"impressive":[29],"SED":[30],"performance,":[31],"effectiveness":[33],"is":[34,71],"hindered":[35],"by":[36],"small":[38],"receptive":[39],"field,":[40],"leading":[41,81,144],"inadequate":[43],"consideration":[44],"of":[45],"global":[46],"information":[48],"imprecise":[50],"boundary":[52],"Moreover,":[54],"existing":[55],"detectors":[56],"overlook":[57],"intricate":[59],"interplay":[60],"between":[61,76],"frequency":[64],"information,":[65],"compromising":[66],"accuracy.":[68],"Simultaneously,":[69],"there":[70],"an":[72,117],"oversight":[73],"in":[74],"interactions":[75],"student":[77],"teacher":[79,84],"models,":[80],"conveying":[85],"inaccurate":[86],"knowledge":[87],"student.":[90],"To":[91],"solve":[92],"these":[93],"challenges,":[94],"this":[95],"paper":[96],"proposes":[97],"novel":[99],"robust":[100],"detector":[101,141],"named":[102],"HTA-CTD,":[103],"incorporating":[104],"Hierarchical":[106],"Temporal":[107],"Attention":[108],"(HTA)":[109],"Competent":[111],"Teacher":[112],"(CTN).":[114],"HTA":[115],"introduces":[116],"adaptive":[118],"temporal-frequency":[119],"feature":[120],"extraction":[121],"method,":[122],"while":[123],"CTN":[124],"minimizes":[125],"reliance":[126],"on":[127,131],"strong":[128],"labels.":[129],"Experiments":[130],"challenging":[132],"benchmarks":[133],"show":[134],"that":[135],"our":[136],"HTA-CTD":[137],"outperforms":[138],"state-of-the-art":[140],"achieves":[143],"performance.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2024-10-01T00:00:00"}
