{"id":"https://openalex.org/W4224927669","doi":"https://doi.org/10.1109/icassp43922.2022.9746118","title":"Hybrid Attention-Based Prototypical Networks for Few-Shot Sound Classification","display_name":"Hybrid Attention-Based Prototypical Networks for Few-Shot Sound Classification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224927669","doi":"https://doi.org/10.1109/icassp43922.2022.9746118"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746118","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5100430217","display_name":"You Wang","orcid":"https://orcid.org/0000-0002-6917-2199"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Wang","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,Georgia,USA","School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,Georgia,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033437141","display_name":"David V. Anderson","orcid":"https://orcid.org/0000-0002-8571-4613"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David V. Anderson","raw_affiliation_strings":["Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,Georgia,USA","School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,School of Electrical and Computer Engineering,Atlanta,Georgia,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"651","last_page":"655"},"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":0.9962000250816345,"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":0.9635000228881836,"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":0.8378497958183289},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.8154884576797485},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.628861129283905},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6232445240020752},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6068054437637329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6020190715789795},{"id":"https://openalex.org/keywords/one-shot","display_name":"One shot","score":0.5170541405677795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49471136927604675},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.46265867352485657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.402780681848526},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07169312238693237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378497958183289},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.8154884576797485},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.628861129283905},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6232445240020752},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6068054437637329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6020190715789795},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.5170541405677795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49471136927604675},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.46265867352485657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.402780681848526},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07169312238693237},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746118","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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":23,"referenced_works":["https://openalex.org/W1587069887","https://openalex.org/W2052666245","https://openalex.org/W2113278353","https://openalex.org/W2155893237","https://openalex.org/W2292996718","https://openalex.org/W2566935005","https://openalex.org/W2601450892","https://openalex.org/W2775505379","https://openalex.org/W2791956393","https://openalex.org/W2905471643","https://openalex.org/W2962910554","https://openalex.org/W2962999716","https://openalex.org/W2963341924","https://openalex.org/W2972247414","https://openalex.org/W2973006577","https://openalex.org/W3091905774","https://openalex.org/W3160262112","https://openalex.org/W3162320900","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6747331233","https://openalex.org/W6749158954","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W2497720472","https://openalex.org/W4292659306","https://openalex.org/W4287637665","https://openalex.org/W3044321615","https://openalex.org/W4294892107","https://openalex.org/W2806221744","https://openalex.org/W2326937258","https://openalex.org/W394267150","https://openalex.org/W2988685434","https://openalex.org/W2357748469"],"abstract_inverted_index":{"In":[0,38],"recent":[1],"years,":[2],"prototypical":[3,51,144],"networks":[4,52,145],"have":[5],"been":[6],"widely":[7],"used":[8],"in":[9,24,35,108,115,146],"many":[10],"few-shot":[11,54,117],"learning":[12,18],"scenarios.":[13,149],"However,":[14],"as":[15],"a":[16,43,65,109],"metric-based":[17],"method,":[19],"their":[20],"performance":[21,90],"often":[22],"degrades":[23],"the":[25,97,101,135,142],"presence":[26],"of":[27,62,91],"bad":[28],"or":[29],"noisy":[30],"embedded":[31,81],"features,":[32],"and":[33,47,69,83,100,113,126],"outliers":[34],"support":[36,86],"instances.":[37],"this":[39],"paper,":[40],"we":[41],"introduce":[42],"hybrid":[44,58,136],"attention":[45,59,67,72,76,137],"module":[46,60],"combine":[48],"it":[49],"with":[50],"for":[53],"sound":[55],"classification.":[56],"This":[57],"consists":[61],"two":[63,75],"blocks:":[64],"feature-level":[66],"block,":[68],"an":[70],"instance-level":[71],"block.":[73],"These":[74],"mechanism":[77],"can":[78],"highlight":[79],"key":[80],"features":[82],"emphasize":[84],"crucial":[85],"instances":[87],"respectively.":[88],"The":[89,104,129],"our":[92,139],"model":[93,105,140],"was":[94,106],"evaluated":[95],"using":[96],"ESC-50":[98],"dataset":[99],"noiseESC-50":[102],"dataset.":[103],"trained":[107],"10-way":[110,124,127],"5-shot":[111],"scenario":[112],"tested":[114],"four":[116,148],"cases,":[118],"namely":[119],"5-way":[120,122],"1-shot,":[121,125],"5-shot,":[123],"5-shot.":[128],"results":[130],"demonstrate":[131],"that":[132],"by":[133],"adding":[134],"module,":[138],"outperforms":[141],"baseline":[143],"all":[147]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}