{"id":"https://openalex.org/W4381244712","doi":"https://doi.org/10.1109/icassp49357.2023.10095398","title":"An Effective Anomalous Sound Detection Method Based on Representation Learning with Simulated Anomalies","display_name":"An Effective Anomalous Sound Detection Method Based on Representation Learning with Simulated Anomalies","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4381244712","doi":"https://doi.org/10.1109/icassp49357.2023.10095398"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095398","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":"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/A5100732644","display_name":"Han Chen","orcid":"https://orcid.org/0000-0002-3000-3152"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Chen","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381751","display_name":"Yan Song","orcid":"https://orcid.org/0000-0001-7050-4368"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002973086","display_name":"Zhu Zhuo","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu Zhuo","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013277301","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0002-4193-311X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341177","display_name":"Yuhong Li","orcid":"https://orcid.org/0009-0009-9185-7133"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Hong Li","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337747","display_name":"Hui Xue","orcid":"https://orcid.org/0000-0002-2093-2839"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xue","raw_affiliation_strings":["Alibaba Group,China","Alibaba Group, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","ICT Cluster, Singapore Institute of Technology, Singapore","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"ICT Cluster, Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.9932000041007996,"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":0.8243988752365112},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.751244306564331},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7115696668624878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6572402715682983},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6171906590461731},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6144394278526306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6071844696998596},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6023366451263428},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5799771547317505},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5581318140029907},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5092405080795288},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.47285011410713196},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4197336733341217},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34042802453041077},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07058987021446228}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8243988752365112},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.751244306564331},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7115696668624878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6572402715682983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6171906590461731},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6144394278526306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6071844696998596},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6023366451263428},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5799771547317505},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5581318140029907},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5092405080795288},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.47285011410713196},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4197336733341217},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34042802453041077},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07058987021446228},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095398","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":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2137130182","https://openalex.org/W2194775991","https://openalex.org/W2765407302","https://openalex.org/W2936774411","https://openalex.org/W2939422005","https://openalex.org/W2951883849","https://openalex.org/W2963163009","https://openalex.org/W3015356122","https://openalex.org/W3034883497","https://openalex.org/W3162150435","https://openalex.org/W3170230444","https://openalex.org/W4224917958","https://openalex.org/W4236333699","https://openalex.org/W4394662183","https://openalex.org/W6757615711","https://openalex.org/W6779961064","https://openalex.org/W6796250704","https://openalex.org/W6864909175"],"related_works":["https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W3107369729","https://openalex.org/W3208297503","https://openalex.org/W3119773509","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611"],"abstract_inverted_index":{"In":[0],"this":[1,87],"paper,":[2],"we":[3,89],"propose":[4,90],"an":[5,144,151],"effective":[6],"anomalous":[7,60],"sound":[8],"detection":[9],"(ASD)":[10],"method":[11],"based":[12,187],"on":[13,169],"representation":[14,105,180],"learning":[15,106,181],"with":[16,182],"simulated":[17,98,129,162,183],"anomalies.":[18,56],"Recently,":[19],"ASD":[20],"systems":[21],"have":[22],"used":[23],"Outlier":[24],"Exposure":[25],"(OE)":[26],"strategy":[27],"to":[28,42,100,154],"achieve":[29],"promising":[30],"performance":[31],"in":[32],"DCASE":[33],"challenges.":[34],"These":[35],"exploit":[36],"deep":[37],"Convolutional":[38],"Neural":[39],"Networks":[40],"(CNNs)":[41],"learn":[43],"discriminative":[44],"representations":[45,77],"by":[46,134],"treating":[47],"the":[48,59,73,102,111,128,136,170,177],"normal":[49,80],"samples":[50,81],"from":[51,79,119,140],"different":[52,141],"classes":[53],"as":[54,150],"pseudo":[55],"However,":[57],"since":[58],"sounds":[61],"occur":[62],"only":[63],"rarely,":[64],"are":[65,69,117],"diversely":[66],"distributed":[67],"and":[68,113,127],"unseen":[70],"during":[71],"training,":[72],"OE":[74,108,157,186],"capability":[75],"of":[76,104,124,138,179],"learned":[78],"may":[82],"be":[83],"limited.":[84],"To":[85],"address":[86],"issue,":[88],"a":[91],"statistics":[92,116,137],"exchange":[93],"(StEx)":[94],"method,":[95],"which":[96,159],"constructs":[97],"anomalies":[99],"improve":[101],"effectiveness":[103,178],"via":[107],"strategy.":[109],"Specifically,":[110],"first":[112],"second":[114],"order":[115],"extracted":[118],"time":[120],"or":[121],"frequency":[122],"axis":[123],"input":[125],"spectrograms,":[126],"anomaly":[130,163,184],"is":[131,148],"then":[132],"obtained":[133],"exchanging":[135],"spectrograms":[139],"classes.":[142],"Furthermore,":[143],"out-of-distribution":[145],"(OOD)":[146],"metric":[147],"introduced":[149],"importance":[152],"measure":[153],"qualitatively":[155],"analyze":[156],"capability,":[158],"enables":[160],"appropriate":[161],"selection":[164],"for":[165,185],"ASD.":[166,188],"Extensive":[167],"experiments":[168],"DCASE2021":[171],"challenge":[172],"task2":[173],"development":[174],"dataset":[175],"verify":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}