{"id":"https://openalex.org/W3015205011","doi":"https://doi.org/10.1109/icassp40776.2020.9054708","title":"Few-Shot Sound Event Detection","display_name":"Few-Shot Sound Event Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015205011","doi":"https://doi.org/10.1109/icassp40776.2020.9054708","mag":"3015205011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054708","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":"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/A5100445368","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-3511-0288"},"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":"Yu Wang","raw_affiliation_strings":["Music and Audio Research Laboratory, New York University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"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, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory, New York University, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5586,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98160712,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"85"},"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922999739646912,"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":0.8270957469940186},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6589269042015076},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6116322875022888},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5664619207382202},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.563855767250061},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5555611848831177},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5343804359436035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5321594476699829},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5269637703895569},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4189617931842804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3829382061958313},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0714661180973053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270957469940186},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6589269042015076},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6116322875022888},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5664619207382202},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.563855767250061},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5555611848831177},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5343804359436035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321594476699829},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5269637703895569},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4189617931842804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3829382061958313},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0714661180973053},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054708","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054708","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W821549425","https://openalex.org/W1501987291","https://openalex.org/W1972567154","https://openalex.org/W2038484192","https://openalex.org/W2115733720","https://openalex.org/W2127589108","https://openalex.org/W2145287260","https://openalex.org/W2171590421","https://openalex.org/W2339294230","https://openalex.org/W2341412280","https://openalex.org/W2398456099","https://openalex.org/W2472819217","https://openalex.org/W2591013610","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2753160622","https://openalex.org/W2787705367","https://openalex.org/W2809183397","https://openalex.org/W2912056372","https://openalex.org/W2948974578","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/W3091905774","https://openalex.org/W3209492613","https://openalex.org/W4293412117","https://openalex.org/W4394036604","https://openalex.org/W6681968150","https://openalex.org/W6712469065","https://openalex.org/W6717697761","https://openalex.org/W6720057410","https://openalex.org/W6735236233","https://openalex.org/W6736057607","https://openalex.org/W6743661861","https://openalex.org/W6748326514","https://openalex.org/W6748555532","https://openalex.org/W6758126075","https://openalex.org/W6783596713","https://openalex.org/W6803218319"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2366107444","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134"],"abstract_inverted_index":{"Locating":[0],"perceptually":[1],"similar":[2],"sound":[3,33,137],"events":[4,34],"within":[5],"a":[6,10,72,77],"continuous":[7],"recording":[8],"is":[9,38],"common":[11],"task":[12,117],"for":[13,115],"various":[14],"audio":[15],"applications.":[16],"However,":[17],"current":[18],"tools":[19],"require":[20],"users":[21],"to":[22,25,53,74,85,98,134],"manually":[23],"listen":[24],"and":[26,40,90],"label":[27],"all":[28],"the":[29,32,55,67,116],"locations":[30],"of":[31,35,57,66,80,111,118],"interest,":[36],"which":[37],"tedious":[39],"time-consuming.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,106],"(1)":[46],"adapt":[47],"state-of-the-art":[48],"metric-based":[49],"few-shot":[50,112,131],"learning":[51,113,132],"methods":[52,114],"automate":[54],"detection":[56,100,120,139],"similar-sounding":[58],"events,":[59],"requiring":[60],"only":[61],"one":[62],"or":[63],"few":[64],"examples":[65,82],"target":[68],"event,":[69],"(2)":[70],"develop":[71,92],"method":[73,97],"automatically":[75],"construct":[76],"partial":[78],"set":[79],"labeled":[81],"(negative":[83],"samples)":[84],"reduce":[86],"user":[87],"labeling":[88],"effort,":[89],"(3)":[91],"an":[93,135],"inference-time":[94],"data":[95],"augmentation":[96],"increase":[99],"accuracy.":[101],"To":[102],"validate":[103],"our":[104,126],"approach,":[105],"perform":[107],"extensive":[108],"comparative":[109],"analysis":[110],"keyword":[119],"in":[121],"speech.":[122],"We":[123],"show":[124],"that":[125],"approach":[127],"successfully":[128],"adapts":[129],"closed-set":[130],"approaches":[133],"open-set":[136],"event":[138],"problem.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}