{"id":"https://openalex.org/W4372260191","doi":"https://doi.org/10.1109/icassp49357.2023.10096813","title":"Unsupervised Anomaly Detection and Localization of Machine Audio: A Gan-Based Approach","display_name":"Unsupervised Anomaly Detection and Localization of Machine Audio: A Gan-Based Approach","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260191","doi":"https://doi.org/10.1109/icassp49357.2023.10096813"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096813","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/A5032861798","display_name":"Anbai Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Anbai Jiang","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101521826","display_name":"Yufeng Deng","orcid":"https://orcid.org/0000-0003-3975-9922"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Deng","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079233004","display_name":"Pingyi Fan","orcid":"https://orcid.org/0000-0002-0658-6079"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pingyi Fan","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","Tsinghua AI Plus, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua AI Plus, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032861798"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":6.6332,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.97453018,"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":"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":1.0,"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":1.0,"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":0.9945999979972839,"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":0.9936000108718872,"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/discriminator","display_name":"Discriminator","score":0.9257799386978149},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8426859974861145},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.7896016836166382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7718275785446167},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6395887136459351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.607544481754303},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5688429474830627},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5038272738456726},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4780876338481903},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44584572315216064},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4440392255783081},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.4437974691390991},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3946916460990906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36719536781311035},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3176566958427429},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.11825823783874512}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9257799386978149},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8426859974861145},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7896016836166382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718275785446167},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6395887136459351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607544481754303},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5688429474830627},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5038272738456726},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4780876338481903},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44584572315216064},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4440392255783081},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.4437974691390991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3946916460990906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36719536781311035},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3176566958427429},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.11825823783874512},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096813","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":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2599354622","https://openalex.org/W2963045681","https://openalex.org/W2963373786","https://openalex.org/W2963684088","https://openalex.org/W3096831136","https://openalex.org/W4253461361","https://openalex.org/W4254182148","https://openalex.org/W4281719388","https://openalex.org/W4295521014","https://openalex.org/W4320204617","https://openalex.org/W4394662183","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6685352114","https://openalex.org/W6718379498","https://openalex.org/W6735913928","https://openalex.org/W6751917112","https://openalex.org/W6780226713","https://openalex.org/W6838495258","https://openalex.org/W6850002427","https://openalex.org/W6864909175"],"related_works":["https://openalex.org/W3186512740","https://openalex.org/W3040099731","https://openalex.org/W3017266184","https://openalex.org/W4289406342","https://openalex.org/W2896600774","https://openalex.org/W2918377632","https://openalex.org/W3202913553","https://openalex.org/W3194885736","https://openalex.org/W3046391934","https://openalex.org/W4363671829"],"abstract_inverted_index":{"Automatic":[0],"detection":[1,86],"of":[2,14,22,67,90,95],"machine":[3,8,23,107],"anomaly":[4,25,111],"remains":[5],"challenging":[6],"for":[7],"learning.":[9],"We":[10],"believe":[11],"the":[12,20,48,64,73,79,93,102],"capability":[13],"generative":[15],"adversarial":[16],"network":[17],"(GAN)":[18],"suits":[19],"need":[21],"audio":[24],"detection,":[26],"yet":[27],"rarely":[28],"has":[29],"this":[30,37],"been":[31],"investigated":[32],"by":[33],"previous":[34],"work.":[35],"In":[36],"paper,":[38],"we":[39],"propose":[40],"AEGAN-AD,":[41],"a":[42],"totally":[43],"unsupervised":[44],"approach":[45],"in":[46],"which":[47],"generator":[49,80],"(also":[50],"an":[51],"autoencoder)":[52],"is":[53,60,75,114],"trained":[54],"to":[55,77],"reconstruct":[56],"input":[57],"spectrograms.":[58],"It":[59],"pointed":[61],"out":[62],"that":[63],"denoising":[65],"nature":[66],"reconstruction":[68],"deprecates":[69],"its":[70],"capacity.":[71],"Thus,":[72],"discriminator":[74],"redesigned":[76],"aid":[78],"during":[81],"both":[82],"training":[83],"stage":[84],"and":[85],"stage.":[87],"The":[88],"performance":[89],"AEGAN-AD":[91],"on":[92,105],"dataset":[94],"DCASE":[96],"2022":[97],"Challenge":[98],"TASK":[99],"2":[100],"demonstrates":[101],"state-of-the-art":[103],"result":[104],"five":[106],"types.":[108],"A":[109],"novel":[110],"localization":[112],"method":[113],"also":[115],"investigated.":[116],"Source":[117],"code":[118],"available":[119],"at:":[120],"www.github.com/jianganbai/AEGAN-AD":[121]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-27T08:22:11.395708","created_date":"2025-10-10T00:00:00"}