{"id":"https://openalex.org/W4205236539","doi":"https://doi.org/10.1109/waspaa52581.2021.9632677","title":"Who Calls The Shots? Rethinking Few-Shot Learning for Audio","display_name":"Who Calls The Shots? Rethinking Few-Shot Learning for Audio","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4205236539","doi":"https://doi.org/10.1109/waspaa52581.2021.9632677"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5101494707","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-0707-8727"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045694117","display_name":"Nicholas J. Bryan","orcid":"https://orcid.org/0000-0003-1469-7278"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas J. Bryan","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037548450","display_name":"Justin Salamon","orcid":"https://orcid.org/0000-0001-6345-4593"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Salamon","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056532548","display_name":"Mark Cartwright","orcid":"https://orcid.org/0000-0002-5908-390X"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Cartwright","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ, USA"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Pablo Bello","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101494707"],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":2.1603,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88600655,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9944999814033508,"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":0.9592999815940857,"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":0.8148208856582642},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.585864245891571},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5775246620178223},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47365912795066833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4642072319984436},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46011051535606384},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4359019994735718},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4342253506183624},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4165583550930023},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4106457233428955},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39530402421951294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148208856582642},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.585864245891571},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5775246620178223},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47365912795066833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4642072319984436},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46011051535606384},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4359019994735718},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4342253506183624},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4165583550930023},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4106457233428955},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39530402421951294},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3697821359","display_name":null,"funder_award_id":"1544753","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1972567154","https://openalex.org/W2033875152","https://openalex.org/W2038484192","https://openalex.org/W2101234009","https://openalex.org/W2593116425","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2619697695","https://openalex.org/W2753160622","https://openalex.org/W2771361008","https://openalex.org/W2780407133","https://openalex.org/W2798836702","https://openalex.org/W2939574508","https://openalex.org/W2962845248","https://openalex.org/W2962999716","https://openalex.org/W2963341924","https://openalex.org/W2963741406","https://openalex.org/W2964105864","https://openalex.org/W2973006577","https://openalex.org/W3015205011","https://openalex.org/W3015474227","https://openalex.org/W3015622757","https://openalex.org/W3047059250","https://openalex.org/W3091905774","https://openalex.org/W3094550259","https://openalex.org/W3108975329","https://openalex.org/W3160262112","https://openalex.org/W4205689591","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6675354045","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6736057607","https://openalex.org/W6743661861","https://openalex.org/W6746715687","https://openalex.org/W6758126075","https://openalex.org/W6766978945","https://openalex.org/W6781533946","https://openalex.org/W6783462664","https://openalex.org/W6783596713"],"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":[1,77],"aims":[2],"to":[3,48,64,89,92,110,114,130,138],"train":[4],"models":[5],"that":[6],"can":[7],"recognize":[8],"novel":[9,120],"classes":[10],"given":[11],"just":[12],"a":[13,105],"handful":[14],"of":[15,107,145],"labeled":[16],"examples,":[17],"known":[18],"as":[19,56,84],"the":[20,24,68,90,112,154,174],"support":[21,97,166],"set.":[22],"While":[23],"field":[25],"has":[26],"seen":[27],"notable":[28],"advances":[29],"in":[30,42,52,153],"recent":[31,151],"years,":[32],"they":[33],"have":[34,74],"often":[35,45],"focused":[36],"on":[37,75,141,173],"multi-class":[38],"image":[39,155],"classification.":[40],"Audio,":[41],"contrast,":[43],"is":[44,86,158],"multi-label":[46],"due":[47],"overlapping":[49],"sounds,":[50],"resulting":[51],"unique":[53],"properties":[54,72],"such":[55,70],"polyphony":[57],"and":[58,81,94,123,165,180],"signal-to-noise":[59],"ratios":[60],"(SNR).":[61],"This":[62],"leads":[63],"unanswered":[65],"questions":[66,103,133],"concerning":[67],"impact":[69],"audio":[71],"may":[73],"few-shot":[76,142],"system":[78],"design,":[79],"performance,":[80],"human-computer":[82],"interaction,":[83],"it":[85,171],"typically":[87],"up":[88],"user":[91],"collect":[93],"provide":[95],"inference-time":[96],"set":[98,167],"examples.":[99],"We":[100,117],"address":[101],"these":[102,115,132],"through":[104],"series":[106],"experiments":[108,136],"designed":[109],"elucidate":[111],"answers":[113],"questions.":[116],"introduce":[118],"two":[119],"datasets,":[121],"FSD-MIX-CLIPS":[122],"FSD-MIX-SED,":[124],"whose":[125],"programmatic":[126],"generation":[127],"allows":[128],"us":[129],"explore":[131],"systematically.":[134],"Our":[135,178],"lead":[137],"audio-specific":[139],"insights":[140],"learning,":[143],"some":[144],"which":[146],"are":[147,182],"at":[148,184],"odds":[149],"with":[150],"findings":[152],"domain:":[156],"there":[157],"no":[159],"best":[160],"one-size-":[161],"fits-all":[162],"model,":[163],"method,":[164],"selection":[168],"criterion.":[169],"Rather,":[170],"depends":[172],"expected":[175],"application":[176],"scenario.":[177],"code":[179],"data":[181],"available":[183],"https://github.com/wangyu/rethink-audio-fsl.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}