{"id":"https://openalex.org/W3015622757","doi":"https://doi.org/10.1109/icassp40776.2020.9054712","title":"Metric Learning with Background Noise Class for Few-Shot Detection of Rare Sound Events","display_name":"Metric Learning with Background Noise Class for Few-Shot Detection of Rare Sound Events","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015622757","doi":"https://doi.org/10.1109/icassp40776.2020.9054712","mag":"3015622757"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5051965288","display_name":"Kazuki Shimada","orcid":"https://orcid.org/0000-0001-5389-2346"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kazuki Shimada","raw_affiliation_strings":["Sony Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017785136","display_name":"Yuichiro Koyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuichiro Koyama","raw_affiliation_strings":["Sony Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030351609","display_name":"Akira Inoue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akira Inoue","raw_affiliation_strings":["Sony Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Corporation, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051965288"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0307,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92073733,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"616","last_page":"620"},"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":0.9980000257492065,"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":0.9824000000953674,"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":0.7037139534950256},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6892659664154053},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6741082668304443},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5955966114997864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5598226189613342},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5368568897247314},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.5160674452781677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49293017387390137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4461996555328369},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4418129324913025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35714417695999146},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08881255984306335},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06992959976196289}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7037139534950256},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6892659664154053},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6741082668304443},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5955966114997864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5598226189613342},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5368568897247314},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5160674452781677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49293017387390137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4461996555328369},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4418129324913025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35714417695999146},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08881255984306335},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06992959976196289},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1975517671","https://openalex.org/W2052666245","https://openalex.org/W2097450352","https://openalex.org/W2138621090","https://openalex.org/W2147069236","https://openalex.org/W2194775991","https://openalex.org/W2408239454","https://openalex.org/W2525577390","https://openalex.org/W2566935005","https://openalex.org/W2601450892","https://openalex.org/W2767754137","https://openalex.org/W2775505379","https://openalex.org/W2804233018","https://openalex.org/W2889373351","https://openalex.org/W2889380691","https://openalex.org/W2917294828","https://openalex.org/W2936044260","https://openalex.org/W2938728536","https://openalex.org/W2938798071","https://openalex.org/W2962845248","https://openalex.org/W2962999716","https://openalex.org/W2963341924","https://openalex.org/W2963386851","https://openalex.org/W2963775347","https://openalex.org/W2963977978","https://openalex.org/W2964066126","https://openalex.org/W2964121744","https://openalex.org/W2964287480","https://openalex.org/W2964355201","https://openalex.org/W2972330866","https://openalex.org/W2972764310","https://openalex.org/W2973006577","https://openalex.org/W3091905774","https://openalex.org/W3102534672","https://openalex.org/W4398958419","https://openalex.org/W6631190155","https://openalex.org/W6638791942","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6747331233","https://openalex.org/W6783596713","https://openalex.org/W6869415701"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Few-shot":[0],"learning":[1,91,167],"systems":[2,27],"for":[3,36,96],"sound":[4,51],"event":[5,139],"recognition":[6],"have":[7,28],"gained":[8],"interests":[9],"since":[10],"they":[11],"require":[12],"only":[13,29,59],"a":[14,115,125,134],"few":[15],"examples":[16],"to":[17,19,32,45,75,80,103,181],"adapt":[18],"new":[20],"target":[21,61],"classes":[22,140],"without":[23,168],"fine-tuning.":[24],"However,":[25],"such":[26],"been":[30],"applied":[31],"chunks":[33],"of":[34,49,108,183,194],"sounds":[35],"classification":[37],"or":[38],"verification.":[39],"In":[40],"this":[41,121],"paper,":[42],"we":[43],"aim":[44],"achieve":[46],"few-shot":[47,98,151,175],"detection":[48,152,176],"rare":[50],"events,":[52],"from":[53],"query":[54],"sequence":[55],"that":[56,119,129,161,182],"contain":[57],"not":[58],"the":[60,65,82,97,105,138,142,170,184],"events":[62,67,84],"but":[63],"also":[64,179],"other":[66,83],"and":[68,85,124,141,158],"background":[69,86,93,109,143,171],"noise.":[70,87],"Therefore,":[71],"it":[72],"is":[73,102,178],"required":[74],"prevent":[76],"false":[77],"positive":[78],"reactions":[79],"both":[81],"We":[88],"propose":[89],"metric":[90,166],"with":[92],"noise":[94,110,144,172],"class":[95,145],"detection.":[99],"The":[100,174],"contribution":[101],"present":[104],"explicit":[106],"inclusion":[107],"as":[111],"an":[112],"independent":[113],"class,":[114,123],"suitable":[116],"loss":[117],"function":[118],"emphasizes":[120],"additional":[122],"corresponding":[126],"sampling":[127],"strategy":[128],"assists":[130],"training.":[131],"It":[132],"provides":[133],"feature":[135],"space":[136],"where":[137],"are":[146],"sufficiently":[147],"separated.":[148],"Evaluations":[149],"on":[150],"tasks,":[153],"using":[154],"DCASE":[155,185],"2017":[156,186],"task2":[157,187],"ESC-50,":[159],"show":[160],"our":[162],"proposed":[163],"method":[164],"outperforms":[165],"considering":[169],"class.":[173],"performance":[177],"comparable":[180],"baseline":[188],"system,":[189],"which":[190],"requires":[191],"huge":[192],"amount":[193],"annotated":[195],"audio":[196],"data.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}