{"id":"https://openalex.org/W4390738640","doi":"https://doi.org/10.1109/taslp.2024.3352248","title":"Self-Supervised Audio Teacher-Student Transformer for Both Clip-Level and Frame-Level Tasks","display_name":"Self-Supervised Audio Teacher-Student Transformer for Both Clip-Level and Frame-Level Tasks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390738640","doi":"https://doi.org/10.1109/taslp.2024.3352248"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3352248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3352248","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5030279221","display_name":"Xian Wei Li","orcid":"https://orcid.org/0009-0001-5796-8317"},"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":true,"raw_author_name":"Xian Li","raw_affiliation_strings":["Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, China","School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"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":"middle","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nian Shao","raw_affiliation_strings":["Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, China","School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"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":["Institute of Advanced Technology, Westlake Institute for Advanced Study, Hangzhou, China","School of Engineering, Westlake University, Hangzhou, China"],"affiliations":[{"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/A5030279221"],"corresponding_institution_ids":["https://openalex.org/I3133055985"],"apc_list":null,"apc_paid":null,"fwci":8.2926,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.98351619,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"1336","last_page":"1351"},"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":0.9997000098228455,"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":0.996399998664856,"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":0.8082144260406494},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7411282062530518},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6088261604309082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053501725196838},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4686398208141327},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33425235748291016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082144260406494},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7411282062530518},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6088261604309082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053501725196838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4686398208141327},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33425235748291016},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/taslp.2024.3352248","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3352248","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2038484192","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2726515241","https://openalex.org/W2797583228","https://openalex.org/W2896457183","https://openalex.org/W2959539607","https://openalex.org/W2963542740","https://openalex.org/W2973157397","https://openalex.org/W2982223350","https://openalex.org/W2982343573","https://openalex.org/W3006926732","https://openalex.org/W3015190346","https://openalex.org/W3015949486","https://openalex.org/W3041561163","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3137857706","https://openalex.org/W3159481202","https://openalex.org/W3162391496","https://openalex.org/W3162999565","https://openalex.org/W3171007011","https://openalex.org/W3196974791","https://openalex.org/W3201143670","https://openalex.org/W3205475937","https://openalex.org/W3205550549","https://openalex.org/W3205743929","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W4205689591","https://openalex.org/W4225713393","https://openalex.org/W4226165006","https://openalex.org/W4226442948","https://openalex.org/W4246193833","https://openalex.org/W4285483774","https://openalex.org/W4297808394","https://openalex.org/W4297841518","https://openalex.org/W4297841853","https://openalex.org/W4309957268","https://openalex.org/W4310873011","https://openalex.org/W4311137818","https://openalex.org/W4312048190","https://openalex.org/W4313156423","https://openalex.org/W4372341324","https://openalex.org/W4375869340","https://openalex.org/W4385245566","https://openalex.org/W6638523607","https://openalex.org/W6726497184","https://openalex.org/W6736723571","https://openalex.org/W6745136726","https://openalex.org/W6745930336","https://openalex.org/W6750665317","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6784333009","https://openalex.org/W6796761347","https://openalex.org/W6809596386","https://openalex.org/W6809947431","https://openalex.org/W6810007534","https://openalex.org/W6810510949","https://openalex.org/W6840200333","https://openalex.org/W6844194202","https://openalex.org/W6846935845","https://openalex.org/W6848208918"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,10,81],"(SSL)":[2],"has":[3],"emerged":[4],"as":[5],"a":[6,68,74,90,94,102,150],"popular":[7],"approach":[8],"for":[9,38,80,106],"audio":[11,16,25],"representations.":[12],"One":[13],"goal":[14],"of":[15,137],"self-supervised":[17],"pre-training":[18],"is":[19],"to":[20,23,53],"transfer":[21],"knowledge":[22,174],"downstream":[24,49,142],"tasks,":[26,59],"generally":[27],"including":[28],"clip-level":[29,48,56,69,82,139],"and":[30,57,73,83,93,108,116,122,140],"frame-level":[31,34,58,75,84,141,155],"tasks.":[32,50,143],"While":[33],"tasks":[35],"are":[36],"important":[37],"fine-grained":[39],"acoustic":[40],"scene/event":[41],"understanding,":[42],"prior":[43],"studies":[44],"primarily":[45],"evaluate":[46],"on":[47,135,153],"In":[51,160],"order":[52],"tackle":[54],"both":[55],"this":[60],"paper":[61],"proposes":[62],"Audio":[63],"Teacher-Student":[64],"Transformer":[65,91],"(ATST),":[66],"with":[67],"version":[70,76],"(named":[71,77],"ATST-Clip)":[72],"ATST-Frame),":[78],"responsible":[79],"representations,":[85],"respectively.":[86],"Both":[87],"methods":[88],"use":[89],"encoder":[92],"teacher-student":[95],"training":[96],"scheme.":[97],"We":[98],"have":[99],"carefully":[100],"designed":[101],"view":[103],"creation":[104],"strategy":[105],"ATST-Clip":[107,111],"ATST-Frame.":[109],"Specifically,":[110],"uses":[112],"segment-wise":[113],"data":[114,120],"augmentations,":[115],"ATST-Frame":[117,129],"integrates":[118],"frame-wise":[119],"augmentations":[121],"masking.":[123],"Experimental":[124],"results":[125],"show":[126],"that":[127],"our":[128],"model":[130],"obtains":[131],"state-of-the-art":[132],"(SOTA)":[133],"performances":[134],"most":[136],"the":[138,154,162,170],"Especially,":[144],"it":[145],"outperforms":[146],"other":[147],"models":[148,172],"by":[149,168],"large":[151],"margin":[152],"sound":[156],"event":[157],"detection":[158],"task.":[159],"addition,":[161],"performance":[163],"can":[164],"be":[165],"further":[166],"improved":[167],"combining":[169],"two":[171],"through":[173],"distillation.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":6}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}