{"id":"https://openalex.org/W4372185032","doi":"https://doi.org/10.1109/icassp49357.2023.10096356","title":"Time-Weighted Frequency Domain Audio Representation with GMM Estimator for Anomalous Sound Detection","display_name":"Time-Weighted Frequency Domain Audio Representation with GMM Estimator for Anomalous Sound Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372185032","doi":"https://doi.org/10.1109/icassp49357.2023.10096356"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096356","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/A5101669069","display_name":"Jian Guan","orcid":"https://orcid.org/0000-0002-5069-240X"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Guan","raw_affiliation_strings":["Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China","Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,Group of Intelligent Signal Processing, College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"Group of Intelligent Signal Processing, College of Computer Science and Technology, Harbin Engineering University, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102446491","display_name":"Youde Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youde Liu","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104012520","display_name":"Qiaoxi Zhu","orcid":"https://orcid.org/0000-0003-3942-0945"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiaoxi Zhu","raw_affiliation_strings":["University of Technology Sydney,Centre for Audio, Acoustics and Vibration,Australia","Centre for Audio, Acoustics and Vibration, University of Technology Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney,Centre for Audio, Acoustics and Vibration,Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"Centre for Audio, Acoustics and Vibration, University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846141","display_name":"Tieran Zheng","orcid":"https://orcid.org/0009-0006-5179-0278"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieran Zheng","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,China","School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Centre for Vision Speech and Signal Processing,UK","Centre for Vision Speech and Signal Processing, University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision Speech and Signal Processing,UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6466654539108276},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.6409938335418701},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6405771970748901},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6188244819641113},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5558164715766907},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5460278391838074},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5349529981613159},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3365320563316345},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.29871946573257446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2560844123363495},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15930694341659546},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14633780717849731},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10589796304702759},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07606819272041321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6466654539108276},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.6409938335418701},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6405771970748901},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6188244819641113},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5558164715766907},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5460278391838074},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5349529981613159},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3365320563316345},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.29871946573257446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2560844123363495},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15930694341659546},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14633780717849731},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10589796304702759},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07606819272041321},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096356","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320025","display_name":"British Council","ror":"https://ror.org/00t3pr326"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2101234009","https://openalex.org/W2148143831","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2306289963","https://openalex.org/W2963163009","https://openalex.org/W3015356122","https://openalex.org/W3162150435","https://openalex.org/W3170230444","https://openalex.org/W3201549834","https://openalex.org/W4221140395","https://openalex.org/W4320204617","https://openalex.org/W6779961064","https://openalex.org/W6784066080","https://openalex.org/W6796250704","https://openalex.org/W6850002427"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4366700029","https://openalex.org/W4285230481","https://openalex.org/W2909726438","https://openalex.org/W4385769873","https://openalex.org/W2067046791","https://openalex.org/W4281634296","https://openalex.org/W4319161863","https://openalex.org/W2371687270","https://openalex.org/W4311888330"],"abstract_inverted_index":{"Although":[0],"deep":[1,132],"learning":[2,133],"is":[3,75,136],"the":[4,40,65,90,137,144],"mainstream":[5],"method":[6,67,125],"in":[7,147],"unsupervised":[8],"anomalous":[9,70],"sound":[10,71],"detection,":[11],"Gaussian":[12],"Mixture":[13],"Model":[14],"(GMM)":[15],"with":[16,27,64,110],"statistical":[17,36,78],"audio":[18],"frequency":[19,37,79],"representation":[20,81],"as":[21,108],"input":[22],"can":[23,83],"achieve":[24],"comparable":[25],"results":[26],"much":[28],"lower":[29],"model":[30],"complexity":[31],"and":[32],"fewer":[33],"parameters.":[34],"Existing":[35],"representations,":[38],"e.g.":[39],"log-Mel":[41],"spectrogram\u2019s":[42],"average":[43],"or":[44],"maximum":[45],"over":[46,95],"time,":[47],"do":[48],"not":[49],"always":[50],"work":[51],"well":[52],"for":[53,69],"different":[54,86],"machines.":[55],"This":[56,97],"paper":[57],"presents":[58],"Time-Weighted":[59],"Frequency":[60],"Domain":[61],"Representation":[62],"(TWFR)":[63],"GMM":[66,99],"(TWFR-GMM)":[68],"detection.":[72],"The":[73],"TWFR":[74],"a":[76,111],"generalized":[77],"domain":[80],"that":[82,123,142],"adapt":[84],"to":[85,101],"machine":[87],"types,":[88],"using":[89],"global":[91],"weighted":[92],"ranking":[93],"pooling":[94],"time-domain.":[96],"allows":[98],"estimator":[100],"recognize":[102],"anomalies,":[103],"even":[104],"under":[105],"domain-shift":[106],"conditions,":[107],"visualized":[109],"Mahalanobis":[112],"distance-based":[113],"metric.":[114],"Experiments":[115],"on":[116],"DCASE":[117,148],"2022":[118,149],"Challenge":[119,150],"Task2":[120],"dataset":[121],"show":[122],"our":[124,140],"has":[126],"better":[127],"detection":[128],"performance":[129],"than":[130],"recent":[131],"methods.":[134],"TWFR-GMM":[135],"core":[138],"of":[139],"submission":[141],"achieved":[143],"3rd":[145],"place":[146],"Task2.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
