{"id":"https://openalex.org/W4312477075","doi":"https://doi.org/10.1109/mmsp55362.2022.9949191","title":"A Task-Specific Meta-Learning Framework for Few-Shot Sound Event Detection","display_name":"A Task-Specific Meta-Learning Framework for Few-Shot Sound Event Detection","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4312477075","doi":"https://doi.org/10.1109/mmsp55362.2022.9949191"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp55362.2022.9949191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949191","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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/A5100667597","display_name":"Tianyang Zhang","orcid":"https://orcid.org/0000-0001-9542-6685"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]},{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyang Zhang","raw_affiliation_strings":["Chongqing University,Key Laboratory of Optoelectronic Technology and Systems, MOE,Chongqing,China","Key Laboratory of Optoelectronic Technology and Systems, MOE, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing University,Key Laboratory of Optoelectronic Technology and Systems, MOE,Chongqing,China","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I50632499"]},{"raw_affiliation_string":"Key Laboratory of Optoelectronic Technology and Systems, MOE, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026699262","display_name":"Liping Yang","orcid":"https://orcid.org/0000-0001-9194-7248"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]},{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Yang","raw_affiliation_strings":["Chongqing University,Key Laboratory of Optoelectronic Technology and Systems, MOE,Chongqing,China","Key Laboratory of Optoelectronic Technology and Systems, MOE, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing University,Key Laboratory of Optoelectronic Technology and Systems, MOE,Chongqing,China","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I50632499"]},{"raw_affiliation_string":"Key Laboratory of Optoelectronic Technology and Systems, MOE, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083278440","display_name":"Xiaohua Gut","orcid":null},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohua Gut","raw_affiliation_strings":["School of Electrical Engineering, Chongqing University of Science and Technology,Chongqing,China","School of Electrical Engineering, Chongqing University of Science and Technology, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Chongqing University of Science and Technology,Chongqing,China","institution_ids":["https://openalex.org/I168337820"]},{"raw_affiliation_string":"School of Electrical Engineering, Chongqing University of Science and Technology, Chongqing, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409330","display_name":"Yuyang Wang","orcid":"https://orcid.org/0000-0003-0242-8935"},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]},{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Wang","raw_affiliation_strings":["Chongqing University,Key Laboratory of Optoelectronic Technology and Systems, MOE,Chongqing,China","Key Laboratory of Optoelectronic Technology and Systems, MOE, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Chongqing University,Key Laboratory of Optoelectronic Technology and Systems, MOE,Chongqing,China","institution_ids":["https://openalex.org/I158842170","https://openalex.org/I50632499"]},{"raw_affiliation_string":"Key Laboratory of Optoelectronic Technology and Systems, MOE, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100667597"],"corresponding_institution_ids":["https://openalex.org/I158842170","https://openalex.org/I50632499"],"apc_list":null,"apc_paid":null,"fwci":0.3682,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53048973,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9943000078201294,"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":0.9742000102996826,"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":0.7947375774383545},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.7040371298789978},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5852553248405457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.576628565788269},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5749667882919312},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.547846794128418},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5423660278320312},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5297186374664307},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5254912972450256},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45888739824295044},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4574114978313446},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.42960792779922485},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3381078839302063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22476470470428467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7947375774383545},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.7040371298789978},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5852553248405457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.576628565788269},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5749667882919312},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.547846794128418},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5423660278320312},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5297186374664307},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5254912972450256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45888739824295044},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4574114978313446},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.42960792779922485},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3381078839302063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22476470470428467},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/mmsp55362.2022.9949191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949191","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1781043176","display_name":null,"funder_award_id":"61903054","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W2126109423","https://openalex.org/W2127125841","https://openalex.org/W2408239454","https://openalex.org/W2601450892","https://openalex.org/W2723513260","https://openalex.org/W2748560407","https://openalex.org/W2936774411","https://openalex.org/W2963099423","https://openalex.org/W2963341924","https://openalex.org/W3015205011","https://openalex.org/W3015474227","https://openalex.org/W3049446265","https://openalex.org/W3108009835","https://openalex.org/W3176065502","https://openalex.org/W3176341011","https://openalex.org/W3182874523","https://openalex.org/W3207699776","https://openalex.org/W4393830892","https://openalex.org/W6678803179","https://openalex.org/W6717697761","https://openalex.org/W6735236233"],"related_works":["https://openalex.org/W3040691452","https://openalex.org/W4283736627","https://openalex.org/W3208882810","https://openalex.org/W4308755723","https://openalex.org/W2972862903","https://openalex.org/W3099765033","https://openalex.org/W4288419306","https://openalex.org/W2921259037","https://openalex.org/W2970699417","https://openalex.org/W2987302549"],"abstract_inverted_index":{"Meta-learning":[0],"is":[1,39,53,65,204],"extensively":[2],"used":[3,157],"for":[4,16,78,94,107,165],"few-shot":[5,17,95,207,238],"learning.":[6],"Prototypical":[7],"Network":[8],"(ProtoNet)":[9],"has":[10],"been":[11],"proved":[12],"to":[13,56,125,161,171,195],"perform":[14],"well":[15],"sound":[18,96,146,179,239],"event":[19,97,240],"detection.":[20,241],"ProtoNet":[21],"as":[22,158],"a":[23,89,159,189],"meta-learning":[24,91],"method":[25],"consists":[26],"of":[27,63,115,176,198,209,213,231],"two":[28],"stages:":[29],"meta-train":[30,34,113],"and":[31,132,140,151,211,216],"meta-test.":[32],"During":[33,47,117],"stage,":[35,49,119],"an":[36],"embedded":[37,51,68,101,123,163,199],"network":[38,52,69,102,124,164],"trained":[40],"on":[41,192,237],"base-classes":[42],"using":[43,206],"episode":[44],"training":[45],"strategy.":[46],"meta-test":[48,118],"the":[50,67,73,112,120,138,172],"transferred":[54],"directly":[55],"unseen":[57,82],"classes":[58],"during":[59,185],"meta-train.":[60],"This":[61],"style":[62],"transference":[64],"task-agnostic:":[66],"may":[70],"not":[71],"learn":[72,103,126],"optimal":[74],"discrimination":[75,104],"embedding":[76,105,128],"features":[77,106,129],"specific":[79,108,166],"tasks":[80],"including":[81],"classes.":[83],"In":[84,168],"this":[85],"paper,":[86],"we":[87,136],"propose":[88],"task-specific":[90],"framework":[92,121,203],"(TSMLF)":[93],"detection,":[98],"which":[99],"makes":[100],"tasks.":[109,167],"TSMLF":[110,232],"inherits":[111],"process":[114],"ProtoNet.":[116],"enables":[122],"discriminative":[127],"by":[130],"inter-class":[131,139,149],"intra-class":[133,141,153,193],"differences.":[134],"Concretely,":[135],"calculate":[137],"distance":[142,150,154,190,194],"that":[143,228],"support":[144,174],"set":[145,175,188],"samples.":[147],"Maximizing":[148],"minimizing":[152],"(MIMI)":[155],"are":[156,181],"criteria":[160],"fine-tune":[162],"addition,":[169],"due":[170],"small-scaled":[173],"meta-test,":[177],"similar":[178],"samples":[180],"easily":[182],"excessively":[183],"clustered":[184],"fine-tuning.":[186],"We":[187],"constraint":[191],"avoid":[196],"overfitting":[197],"network.":[200],"The":[201],"proposed":[202],"evaluated":[205],"dataset":[208],"Detection":[210],"Classification":[212],"Acoustic":[214],"Scenes":[215],"Events":[217],"challenges":[218],"2022":[219],"(DCASE2022)":[220],"task":[221],"5.":[222],"Extensive":[223],"ablation":[224],"experimental":[225],"results":[226],"validate":[227],"all":[229],"components":[230],"can":[233],"provide":[234],"positive":[235],"effects":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
