{"id":"https://openalex.org/W7080312653","doi":"https://doi.org/10.1109/lsp.2025.3606785","title":"ESTM: An Enhanced Dual-Branch Spectral-Temporal Mamba for Anomalous Sound Detection","display_name":"ESTM: An Enhanced Dual-Branch Spectral-Temporal Mamba for Anomalous Sound Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7080312653","doi":"https://doi.org/10.1109/lsp.2025.3606785"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3606785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3606785","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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":null,"display_name":"Chengyuan Ma","orcid":"https://orcid.org/0009-0000-5393-7030"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Chengyuan Ma","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-5393-7030","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peng Jia","orcid":"https://orcid.org/0000-0002-3124-3924"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Jia","raw_affiliation_strings":["Collaborative Innovation Center for Transport Studies, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-3124-3924","affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center for Transport Studies, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongyue Guo","orcid":"https://orcid.org/0000-0003-1454-4087"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyue Guo","raw_affiliation_strings":["Collaborative Innovation Center for Transport Studies, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-1454-4087","affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center for Transport Studies, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wenming Yang","orcid":"https://orcid.org/0000-0002-2506-1286"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Wenming Yang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2506-1286","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87971592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"3919","last_page":"3923"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.36059999465942383,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.36059999465942383,"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/T13177","display_name":"Geological and Geophysical Studies","score":0.05490000173449516,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13067","display_name":"Geological Modeling and Analysis","score":0.02879999950528145,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8808000087738037},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5033000111579895},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4966999888420105},{"id":"https://openalex.org/keywords/coupling","display_name":"Coupling (piping)","score":0.4771000146865845},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4763000011444092},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4519999921321869},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42969998717308044},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3573000133037567}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8808000087738037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6592000126838684},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47519999742507935},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.46369999647140503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4609000086784363},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3573000133037567},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3305000066757202},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C2992428333","wikidata":"https://www.wikidata.org/wiki/Q11461","display_name":"Sound production","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3606785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3606785","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2114659828","https://openalex.org/W2962834855","https://openalex.org/W2969985801","https://openalex.org/W2982294822","https://openalex.org/W2990621560","https://openalex.org/W2997122788","https://openalex.org/W3015356122","https://openalex.org/W3162150435","https://openalex.org/W4221140395","https://openalex.org/W4372185032","https://openalex.org/W4375868962","https://openalex.org/W4385822679","https://openalex.org/W4386075572","https://openalex.org/W4392903041","https://openalex.org/W4392903605","https://openalex.org/W4392903703","https://openalex.org/W4392903798","https://openalex.org/W4403511013","https://openalex.org/W4406461620","https://openalex.org/W4408355866","https://openalex.org/W4410087476"],"related_works":[],"abstract_inverted_index":{"The":[0],"core":[1],"challenge":[2],"in":[3,11,42],"industrial":[4],"equipment":[5],"anomalous":[6,103,116],"sound":[7],"detection":[8,117],"(ASD)":[9],"lies":[10],"modeling":[12,21,66],"the":[13,106,120,128,131],"time-frequency":[14,64],"coupling":[15,40],"characteristics":[16],"of":[17,130],"acoustic":[18,44],"features.":[19,45],"Existing":[20],"methods":[22],"are":[23],"limited":[24],"by":[25,89],"local":[26],"receptive":[27],"fields,":[28],"making":[29],"it":[30],"difficult":[31],"to":[32,102],"capture":[33],"long-range":[34,74],"temporal":[35],"patterns":[36,104],"and":[37,67,86,94],"cross-band":[38],"dynamic":[39],"effects":[41],"machine":[43],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"a":[51,59],"novel":[52],"framework,":[53],"ESTM,":[54],"which":[55],"is":[56],"based":[57],"on":[58,119],"dual-path":[60],"Mamba":[61],"architecture":[62],"with":[63],"decoupled":[65],"utilizes":[68],"Selective":[69],"State-Space":[70],"Models":[71],"(SSM)":[72],"for":[73],"sequence":[75],"modeling.":[76],"ESTM":[77,114],"extracts":[78],"rich":[79],"feature":[80],"representations":[81],"from":[82],"different":[83],"time":[84],"segments":[85],"frequency":[87],"bands":[88],"fusing":[90],"enhanced":[91],"Mel":[92],"spectrograms":[93],"raw":[95],"audio":[96],"features,":[97],"while":[98],"further":[99,126],"improving":[100],"sensitivity":[101],"through":[105],"TriStat-Gating":[107],"(TSG)":[108],"module.":[109],"Our":[110],"experiments":[111],"demonstrate":[112],"that":[113],"improves":[115],"performance":[118],"DCASE":[121],"2020":[122],"Task":[123],"2":[124],"dataset,":[125],"validating":[127],"effectiveness":[129],"proposed":[132],"method.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}