{"id":"https://openalex.org/W4387969180","doi":"https://doi.org/10.1145/3581783.3612676","title":"IFS-SED: Incremental Few-Shot Sound Event Detection Using Explicit Learning and Calibration","display_name":"IFS-SED: Incremental Few-Shot Sound Event Detection Using Explicit Learning and Calibration","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969180","doi":"https://doi.org/10.1145/3581783.3612676"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612676","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5079794945","display_name":"Ming Feng","orcid":"https://orcid.org/0000-0001-8062-6246"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Feng","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8062-6246","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"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"],"raw_orcid":"https://orcid.org/0000-0001-5997-5169","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/A5020229717","display_name":"Hengxing Cai","orcid":"https://orcid.org/0000-0001-9780-2330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengxing Cai","raw_affiliation_strings":["4Paradigm, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9780-2330","affiliations":[{"raw_affiliation_string":"4Paradigm, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9402","last_page":"9404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.765536904335022},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6054552793502808},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5206343531608582},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.4793999195098877},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44748884439468384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4365389943122864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.436160683631897},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.43553033471107483},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.415355920791626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765536904335022},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6054552793502808},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5206343531608582},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.4793999195098877},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44748884439468384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4365389943122864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436160683631897},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.43553033471107483},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.415355920791626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612676","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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":15,"referenced_works":["https://openalex.org/W2566935005","https://openalex.org/W2759976799","https://openalex.org/W2775794021","https://openalex.org/W2940092410","https://openalex.org/W2954929116","https://openalex.org/W2963504927","https://openalex.org/W2966527417","https://openalex.org/W3034309632","https://openalex.org/W3035342403","https://openalex.org/W3042805811","https://openalex.org/W3100040045","https://openalex.org/W3202568778","https://openalex.org/W4283794303","https://openalex.org/W4367276906","https://openalex.org/W6604190760"],"related_works":["https://openalex.org/W4287067590","https://openalex.org/W3186262193","https://openalex.org/W3192176272","https://openalex.org/W4297634446","https://openalex.org/W4391158518","https://openalex.org/W4381322349","https://openalex.org/W3085307110","https://openalex.org/W3157400488","https://openalex.org/W4382021137","https://openalex.org/W2892655153"],"abstract_inverted_index":{"Sound":[0],"event":[1,64],"detection":[2],"(SED)":[3],"refers":[4],"to":[5,28,37,95,111,120,174],"recognizing":[6],"the":[7,41,50,56,70,83,113,131,134,144,154,166,176],"sound":[8,63,98],"events":[9],"in":[10,31],"a":[11,87,122],"continuous":[12],"audio":[13],"signal,":[14],"which":[15],"has":[16],"drawn":[17],"increasing":[18],"interest":[19],"during":[20,69],"recent":[21],"decades.":[22],"The":[23],"applications":[24],"of":[25,49,115,178],"SED":[26,80],"seem":[27],"be":[29,67,93,151],"evident":[30],"many":[32],"fields,":[33],"ranging":[34],"from":[35],"surveillance":[36],"monitoring":[38],"applications.":[39],"Despite":[40],"sustainable":[42],"efforts":[43],"that":[44],"have":[45],"been":[46],"made,":[47],"most":[48],"previous":[51],"attempts":[52],"are":[53,140],"performed":[54],"on":[55],"closed-set,":[57],"as":[58,86],"only":[59],"fixed":[60],"and":[61,104,118,127,137],"known":[62],"classes":[65],"can":[66,150,159],"employed":[68],"training.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"present":[76],"our":[77,148,179],"incremental":[78],"few-shot":[79],"framework":[81,108,158],"under":[82],"open-set":[84],"settings,":[85],"practical":[88],"machine":[89],"listening":[90],"system":[91,149],"should":[92],"able":[94],"address":[96,112],"unknown":[97],"events.":[99],"Specifically,":[100],"an":[101,162,169],"explicit":[102],"learning":[103,107],"calibration-based":[105],"multi-stage":[106],"is":[109,172],"utilized":[110],"challenges":[114],"catastrophic":[116],"forgetting,":[117],"aim":[119],"achieve":[121],"better":[123],"trade-off":[124],"between":[125],"stability":[126],"plasticity.":[128],"To":[129],"compress":[130],"model":[132,135,145],"efficiently,":[133],"prune":[136],"self-distillation":[138],"paradigm":[139],"combined":[141],"used":[142],"for":[143,153,165],"compression,":[146],"thus":[147],"deployed":[152],"resource-limited":[155],"devices.":[156],"Our":[157],"also":[160],"provide":[161],"uncertain":[163],"estimation":[164],"inference.":[167],"Lastly,":[168],"interactive":[170],"interface":[171],"presented":[173],"demonstrate":[175],"functions":[177],"system.":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}