{"id":"https://openalex.org/W4392904244","doi":"https://doi.org/10.1109/icassp48485.2024.10446159","title":"Fine-Tune the Pretrained ATST Model for Sound Event Detection","display_name":"Fine-Tune the Pretrained ATST Model for Sound Event Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904244","doi":"https://doi.org/10.1109/icassp48485.2024.10446159"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446159","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/A5101841879","display_name":"Nian Shao","orcid":"https://orcid.org/0000-0002-6260-3005"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nian Shao","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China","School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425999","display_name":"Xian Li","orcid":"https://orcid.org/0000-0001-5714-3940"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Li","raw_affiliation_strings":["School of Engineering, Westlake University,Hangzhou,China","Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, China","School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Westlake University,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100358313","display_name":"Xiaofei Li","orcid":"https://orcid.org/0000-0003-0393-9905"},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Li","raw_affiliation_strings":["School of Engineering, Westlake University,Hangzhou,China","Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, China","School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Westlake University,Hangzhou,China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]},{"raw_affiliation_string":"School of Engineering, Westlake University, Hangzhou, China","institution_ids":["https://openalex.org/I3133055985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101841879"],"corresponding_institution_ids":["https://openalex.org/I3133055985","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":10.1283,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.98929348,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"911","last_page":"915"},"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":0.9988999962806702,"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":0.9930999875068665,"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/computer-science","display_name":"Computer science","score":0.7457037568092346},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7053648233413696},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.563051164150238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5621811747550964},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5227080583572388},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5108253955841064},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4443700313568115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41838937997817993},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12445265054702759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7457037568092346},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7053648233413696},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.563051164150238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5621811747550964},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5227080583572388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5108253955841064},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4443700313568115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41838937997817993},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12445265054702759},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446159","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W2187089797","https://openalex.org/W2593116425","https://openalex.org/W2936774411","https://openalex.org/W2953070460","https://openalex.org/W2959539607","https://openalex.org/W3160339728","https://openalex.org/W3162400960","https://openalex.org/W3162999565","https://openalex.org/W3203468141","https://openalex.org/W3209458476","https://openalex.org/W4221149441","https://openalex.org/W4224920041","https://openalex.org/W4293363567","https://openalex.org/W4296068822","https://openalex.org/W4297841518","https://openalex.org/W4307823382","https://openalex.org/W4372263379","https://openalex.org/W4385245566","https://openalex.org/W4390738640","https://openalex.org/W6733814495","https://openalex.org/W6796761347","https://openalex.org/W6848208918"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W3040691452"],"abstract_inverted_index":{"Sound":[0],"event":[1],"detection":[2],"(SED)":[3],"often":[4],"suffers":[5],"from":[6],"the":[7,15,27,39,55,67,71,90,135,139,144,160],"data":[8],"deficiency":[9],"problem.":[10],"Recent":[11],"SED":[12,91,129,150],"systems":[13],"leverage":[14],"large":[16,145],"pretrained":[17,28,40,56,72],"self-supervised":[18],"learning":[19,98],"(SelfSL)":[20],"models":[21,29,41,57,73],"to":[22,31,89],"mitigate":[23],"such":[24],"restriction,":[25],"where":[26],"help":[30],"produce":[32],"more":[33],"discriminative":[34],"features":[35],"for":[36,74,97,121],"SED.":[37,75],"However,":[38],"are":[42],"regarded":[43],"as":[44],"a":[45,110,118],"frozen":[46],"feature":[47],"extractor":[48],"in":[49],"most":[50],"systems,":[51],"and":[52,104,127,148],"fine-tuning":[53,68,119,143],"of":[54,70,101,112,156],"has":[58],"been":[59],"rarely":[60],"studied.":[61],"In":[62],"this":[63],"work,":[64],"we":[65],"study":[66],"method":[69,120,137],"We":[76,115],"introduce":[77],"frame-level":[78,99],"audio":[79,102],"teacher-student":[80],"transformer":[81],"model":[82],"(ATST-Frame),":[83],"our":[84,149],"newly":[85],"proposed":[86,136],"SelfSL":[87],"model,":[88],"system.":[92],"ATST-Frame":[93,122],"was":[94],"especially":[95],"designed":[96],"representations":[100],"signals":[103],"obtained":[105],"state-of-the-art":[106],"(SOTA)":[107],"performances":[108],"on":[109,159],"series":[111],"downstream":[113],"tasks.":[114],"then":[116],"propose":[117],"using":[123],"both":[124],"(in-domain)":[125],"unlabelled":[126],"labelled":[128],"data.":[130],"Our":[131],"experiments":[132],"show":[133],"that,":[134],"overcomes":[138],"overfitting":[140],"problem":[141],"when":[142],"pre-trained":[146],"network,":[147],"system":[151],"obtains":[152],"new":[153],"SOTA":[154],"results":[155],"0.587/0.812":[157],"PSDS1/PSDS2":[158],"DCASE":[161],"challenge":[162],"task":[163],"4":[164],"dataset.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}