{"id":"https://openalex.org/W4372260106","doi":"https://doi.org/10.1109/icassp49357.2023.10097081","title":"Transformer-Based Bioacoustic Sound Event Detection on Few-Shot Learning Tasks","display_name":"Transformer-Based Bioacoustic Sound Event Detection on Few-Shot Learning Tasks","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260106","doi":"https://doi.org/10.1109/icassp49357.2023.10097081"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5003457871","display_name":"Liwen You","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Liwen You","raw_affiliation_strings":["Amazon.com"],"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071934058","display_name":"Erika Pelaez Coyotl","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erika Pelaez Coyotl","raw_affiliation_strings":["Amazon.com"],"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006401150","display_name":"Suren Gunturu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Suren Gunturu","raw_affiliation_strings":["Amazon.com"],"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113701682","display_name":"Maarten Van Segbroeck","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maarten Van Segbroeck","raw_affiliation_strings":["Amazon.com"],"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003457871"],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":2.8465,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91556613,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7894253730773926},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7683119177818298},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.6454266309738159},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6294225454330444},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5743040442466736},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4982912540435791},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46874526143074036},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43144404888153076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43062758445739746},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4243507385253906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.404117226600647},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3514103889465332}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7894253730773926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683119177818298},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.6454266309738159},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6294225454330444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5743040442466736},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4982912540435791},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46874526143074036},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43144404888153076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43062758445739746},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4243507385253906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.404117226600647},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3514103889465332},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2601450892","https://openalex.org/W2936774411","https://openalex.org/W2994728585","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3167453437","https://openalex.org/W3169320628","https://openalex.org/W3196974791","https://openalex.org/W3207699776","https://openalex.org/W4226051760","https://openalex.org/W6889743928"],"related_works":["https://openalex.org/W2936488316","https://openalex.org/W3091785813","https://openalex.org/W4287776258","https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W4312376745","https://openalex.org/W2913302899","https://openalex.org/W3027997911","https://openalex.org/W2767651786","https://openalex.org/W2144059113"],"abstract_inverted_index":{"Automatic":[0],"detection":[1,43],"of":[2,22,46],"bioacoustic":[3],"sound":[4,42,87,137],"events":[5,18,88,138],"is":[6,27],"crucial":[7],"to":[8,51,57,85,109],"monitor":[9],"wildlife.":[10],"With":[11,114],"a":[12,35,78,110],"tedious":[13],"annotation":[14],"process,":[15],"limited":[16],"labeled":[17],"and":[19,61,82,144],"large":[20],"volume":[21],"recordings,":[23],"few-shot":[24],"learning":[25],"(FSL)":[26],"suitable":[28],"for":[29,41,149],"such":[30],"event":[31],"detections":[32],"based":[33,112],"on":[34,89,104,117],"few":[36],"examples.":[37],"Typical":[38],"FSL":[39,118,150],"frameworks":[40],"make":[44],"use":[45],"Convolutional":[47],"Neural":[48],"Networks":[49],"(CNNs)":[50],"extract":[52],"features.":[53],"However,":[54],"CNNs":[55],"fail":[56],"capture":[58],"long-range":[59],"relationships":[60],"global":[62],"context":[63],"in":[64],"audio":[65,74],"data.":[66],"We":[67],"present":[68],"an":[69],"approach":[70,121,133],"that":[71,98],"combines":[72],"the":[73,90,99,126],"spectrogram":[75],"transformer":[76],"(AST),":[77],"data":[79],"augmentation":[80],"regime":[81],"transductive":[83,115],"inference":[84,116],"detect":[86],"DCASE2022":[91],"(Task":[92],"5)":[93],"dataset.":[94],"Our":[95,132],"results":[96],"show":[97],"AST":[100,128],"model":[101],"performs":[102],"better":[103],"all":[105],"recordings":[106,143],"when":[107],"compared":[108],"CNN":[111],"model.":[113],"tasks,":[119],"our":[120],"has":[122],"6%":[123],"improvement":[124],"over":[125,136],"baseline":[127],"feature":[129],"extraction":[130],"pipeline.":[131],"generalizes":[134],"well":[135],"from":[139],"different":[140],"animal":[141],"species,":[142],"durations,":[145],"suggesting":[146],"its":[147],"effectiveness":[148],"tasks.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}