{"id":"https://openalex.org/W4402979272","doi":"https://doi.org/10.1109/icme57554.2024.10687821","title":"Self-Supervised Learning-Based General Fine-tuning Framework For Audio Classification and Event Detection","display_name":"Self-Supervised Learning-Based General Fine-tuning Framework For Audio Classification and Event Detection","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979272","doi":"https://doi.org/10.1109/icme57554.2024.10687821"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687821","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687821","pdf_url":null,"source":null,"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"},"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/A5069599986","display_name":"Yanjie Sun","orcid":"https://orcid.org/0000-0002-2491-2835"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanjie Sun","raw_affiliation_strings":["National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051680867","display_name":"Yong Dou","orcid":"https://orcid.org/0000-0002-1256-8934"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Dou","raw_affiliation_strings":["National University of Defense Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080657827","display_name":"Tian Gao","orcid":"https://orcid.org/0000-0003-0466-1001"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Gao","raw_affiliation_strings":["iFlytek Research,Hefei,China"],"affiliations":[{"raw_affiliation_string":"iFlytek Research,Hefei,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069599986"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18295229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.9605000019073486,"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":0.9605000019073486,"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":0.7541938424110413},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5813144445419312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.574596643447876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5076421499252319},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38863253593444824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38615429401397705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541938424110413},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5813144445419312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574596643447876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5076421499252319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38863253593444824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38615429401397705},{"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/icme57554.2024.10687821","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687821","pdf_url":null,"source":null,"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":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W2033914206"],"abstract_inverted_index":{"Recently,":[0],"self-supervised":[1],"learning":[2,45],"(SSL)":[3],"has":[4,12],"made":[5],"remarkable":[6],"progress":[7],"in":[8,51,138],"signal":[9,53,107],"representation":[10],"and":[11,31,47,94,141],"become":[13],"a":[14,68,78,91],"de":[15],"facto":[16],"solution":[17],"for":[18,121],"different":[19,64],"audio":[20,52,106,115,139],"processing":[21,54,108],"tasks.":[22,55,109,150],"Generally,":[23],"the":[24,28,43,57,85,100,111,119,132],"SSL":[25,86],"consists":[26],"of":[27,60,131],"foundation":[29],"pre-training":[30],"downstream":[32],"fine-tuning":[33,36,69,81],"phases.":[34],"However,":[35],"frameworks":[37],"may":[38],"lack":[39],"universality":[40],"due":[41],"to":[42,102,125],"distinct":[44],"paradigms":[46],"model":[48],"designs":[49],"employed":[50],"Furthermore,":[56],"varying":[58],"degrees":[59],"dataset":[61],"labeling":[62],"across":[63,104,149],"tasks":[65],"challenge":[66],"unifying":[67],"framework.":[70],"To":[71],"address":[72],"these":[73],"issues,":[74],"we":[75],"propose":[76],"vec2task,":[77],"cross-task":[79],"general":[80],"framework":[82,101,112,134],"based":[83],"on":[84],"pre-trained":[87],"model.":[88],"It":[89],"employs":[90,113],"semantic-aware":[92],"module":[93],"an":[95],"alternating":[96],"training":[97],"strategy,":[98],"enabling":[99],"generalize":[103],"various":[105],"Additionally,":[110],"automatic":[114],"augmentation":[116],"strategies,":[117],"eliminating":[118],"requirement":[120],"individually":[122],"tailored":[123],"algorithms":[124],"improve":[126],"task":[127],"performance.":[128],"Experimental":[129],"validations":[130],"vec2task":[133],"outperformed":[135],"previous":[136],"methods":[137],"classification":[140],"event":[142],"detection":[143],"tasks,":[144],"showcasing":[145],"its":[146],"generalization":[147],"ability":[148]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}