{"id":"https://openalex.org/W3015898873","doi":"https://doi.org/10.1109/icassp40776.2020.9053620","title":"SPIDERnet: Attention Network For One-Shot Anomaly Detection In Sounds","display_name":"SPIDERnet: Attention Network For One-Shot Anomaly Detection In Sounds","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015898873","doi":"https://doi.org/10.1109/icassp40776.2020.9053620","mag":"3015898873"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053620","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/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017806490","display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0002-8384-8167"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105367326","display_name":"Shin Murata","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shin Murata","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108799515","display_name":"Shoichiro Saito","orcid":"https://orcid.org/0000-0002-8712-0464"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichiro Saito","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112412633","display_name":"Hisashi Uematsu","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Uematsu","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054467679","display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101503856"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.121,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.8962372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"281","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/T11220","display_name":"Water Systems and Optimization","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7568387985229492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7253891825675964},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.670508623123169},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6279577016830444},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.595696747303009},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5316033363342285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5116196274757385},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5012993812561035},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.48658573627471924},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.48247984051704407},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4625970423221588},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4283284544944763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4067881107330322},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1434555947780609}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7568387985229492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253891825675964},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.670508623123169},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6279577016830444},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.595696747303009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5316033363342285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116196274757385},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5012993812561035},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.48658573627471924},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.48247984051704407},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4625970423221588},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4283284544944763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4067881107330322},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1434555947780609},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/icassp40776.2020.9053620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053620","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1601124178","https://openalex.org/W1982320825","https://openalex.org/W2108287924","https://openalex.org/W2118230268","https://openalex.org/W2119042815","https://openalex.org/W2122646361","https://openalex.org/W2135131618","https://openalex.org/W2292996718","https://openalex.org/W2767052532","https://openalex.org/W2771164042","https://openalex.org/W2785523195","https://openalex.org/W2890235427","https://openalex.org/W2897802972","https://openalex.org/W2899877258","https://openalex.org/W2910068345","https://openalex.org/W2938357656","https://openalex.org/W2938728536","https://openalex.org/W2962845248","https://openalex.org/W2963341924","https://openalex.org/W2963403868","https://openalex.org/W2963568900","https://openalex.org/W2964891022","https://openalex.org/W2972818416","https://openalex.org/W2982294822","https://openalex.org/W2997122788","https://openalex.org/W2997572448","https://openalex.org/W3007328579","https://openalex.org/W3121952123","https://openalex.org/W3123416659","https://openalex.org/W3153872861","https://openalex.org/W4385245566","https://openalex.org/W6631943919","https://openalex.org/W6717697761","https://openalex.org/W6739901393","https://openalex.org/W6747620207","https://openalex.org/W6758101687","https://openalex.org/W7016021835"],"related_works":["https://openalex.org/W2806741695","https://openalex.org/W4290647774","https://openalex.org/W3189286258","https://openalex.org/W3207797160","https://openalex.org/W3210364259","https://openalex.org/W4300558037","https://openalex.org/W2912112202","https://openalex.org/W2667207928","https://openalex.org/W4377864969","https://openalex.org/W3030345572"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,80,98],"similarity":[3,75,105],"function":[4,76],"for":[5,103,113],"one-shot":[6,52],"anomaly":[7,14,24],"detection":[8],"in":[9,27,106],"sounds":[10,68,72],"(ADS)":[11],"called":[12],"SPecific":[13],"IDentifiER":[15],"network":[16],"(SPIDERnet).":[17],"In":[18],"ADS":[19],"systems,":[20],"since":[21],"overlooking":[22],"an":[23,37],"may":[25],"result":[26],"serious":[28],"incidents,":[29],"we":[30],"need":[31],"to":[32],"update":[33],"such":[34,69],"systems":[35],"using":[36],"(often":[38],"only":[39,65],"one)":[40],"overlooked":[41],"anomalous":[42,67,92,133],"sample.":[43],"A":[44,54],"previous":[45,58],"study":[46],"proposed":[47],"the":[48,84],"use":[49],"of":[50,96],"memory-based":[51],"learning.":[53],"problem":[55],"with":[56],"this":[57],"method":[59],"is":[60,77],"that":[61,124],"it":[62],"can":[63],"detect":[64,90],"short":[66],"as":[70],"collision":[71],"because":[73],"its":[74],"based":[78],"on":[79,119],"naive":[81],"mean-squared-error":[82],"between":[83],"input":[85],"and":[86,109,129],"memorized":[87],"spectrogram.":[88],"To":[89],"various":[91,132],"sounds,":[93],"SPIDERnet":[94,125],"consists":[95],"(i)":[97],"neural":[99],"network-based":[100],"feature":[101],"extractor":[102],"measuring":[104],"embedded":[107],"space":[108],"(ii)":[110],"attention":[111],"mechanisms":[112],"absorbing":[114],"time-frequency":[115],"stretching.":[116],"Experimental":[117],"results":[118],"two":[120],"public":[121],"datasets":[122],"indicate":[123],"outperforms":[126],"conventional":[127],"methods":[128],"robustly":[130],"detects":[131],"sounds.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}