{"id":"https://openalex.org/W7131904271","doi":"https://doi.org/10.1109/sii64115.2026.11404617","title":"Spectral-to-Spatial Distillation: Denoising Framework for Real-Time Anomalous Sound Detection","display_name":"Spectral-to-Spatial Distillation: Denoising Framework for Real-Time Anomalous Sound Detection","publication_year":2026,"publication_date":"2026-01-11","ids":{"openalex":"https://openalex.org/W7131904271","doi":"https://doi.org/10.1109/sii64115.2026.11404617"},"language":null,"primary_location":{"id":"doi:10.1109/sii64115.2026.11404617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","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/A5049771306","display_name":"Koki Shoda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Koki Shoda","raw_affiliation_strings":["The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016809618","display_name":"J. Kasahara","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Younes Louhi Kasahara","raw_affiliation_strings":["The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054137505","display_name":"Takuya Igaue","orcid":"https://orcid.org/0000-0002-0182-834X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Igaue","raw_affiliation_strings":["The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109355030","display_name":"S. Kanda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Kanda","raw_affiliation_strings":["The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064103302","display_name":"Hajime Asama","orcid":"https://orcid.org/0000-0002-9482-497X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hajime Asama","raw_affiliation_strings":["The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101460624","display_name":"Qi An","orcid":"https://orcid.org/0000-0002-8909-6234"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Qi An","raw_affiliation_strings":["The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021260328","display_name":"Atsushi Yamashita","orcid":"https://orcid.org/0000-0003-1280-069X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Yamashita","raw_affiliation_strings":["The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo 7-3-1 Hongo,Bunkyo-ku, Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5049771306"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94712046,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"173","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.35899999737739563,"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":0.35899999737739563,"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":0.11010000109672546,"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/T13018","display_name":"Seismology and Earthquake Studies","score":0.10980000346899033,"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/noise-reduction","display_name":"Noise reduction","score":0.6492000222206116},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5891000032424927},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5787000060081482},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5422000288963318},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5394999980926514},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5270000100135803},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5073999762535095},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.4496000111103058},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44269999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336999773979187},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6492000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6087999939918518},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5422000288963318},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5270000100135803},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.40790000557899475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3781000077724457},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3483000099658966},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.3276999890804291},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C121475858","wikidata":"https://www.wikidata.org/wiki/Q2735911","display_name":"Spatial filter","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii64115.2026.11404617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.6147890090942383}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2016043834","https://openalex.org/W2055401280","https://openalex.org/W2412956798","https://openalex.org/W2508393166","https://openalex.org/W2568308529","https://openalex.org/W2889326414","https://openalex.org/W2897802972","https://openalex.org/W2899515918","https://openalex.org/W2964237233","https://openalex.org/W2972401521","https://openalex.org/W2973062255","https://openalex.org/W2997122788","https://openalex.org/W3015199127","https://openalex.org/W3081267827","https://openalex.org/W3097777922","https://openalex.org/W3205567090","https://openalex.org/W3217317857","https://openalex.org/W4223583411","https://openalex.org/W4226442948","https://openalex.org/W4372260310","https://openalex.org/W4385756463","https://openalex.org/W4387603987","https://openalex.org/W4390875033","https://openalex.org/W4391621214","https://openalex.org/W4399939359","https://openalex.org/W4404163273","https://openalex.org/W4405934446"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,64,117],"propose":[4],"spectral-to-spatial":[5],"distillation,":[6],"a":[7,52,76,119,140,197],"novel":[8],"denoising":[9,185],"framework":[10],"for":[11,22,123,161,200],"real-time":[12,192],"anomalous":[13,17],"sound":[14,18],"detection.":[15],"While":[16],"detection":[19,188],"is":[20,27,84,97],"crucial":[21],"industrial":[23,202],"applications,":[24],"its":[25,98],"reliability":[26],"often":[28],"compromised":[29],"by":[30,48,164],"background":[31,46],"noise,":[32,74],"which":[33,68],"can":[34],"lead":[35],"to":[36,100],"false":[37],"positives.":[38],"Our":[39],"proposed":[40],"method":[41,181],"addresses":[42],"the":[43,113,134,145,151,155,166,171,174,183],"issue":[44],"of":[45,93,112,139,173],"noise":[47],"distilling":[49],"knowledge":[50],"from":[51],"general-purpose":[53],"spectral":[54],"filtering":[55,61,82],"network":[56,83],"into":[57],"an":[58],"environment-specific":[59],"spatial":[60,81],"network.":[62],"Specifically,":[63],"generate":[65,102],"distillation":[66,95,125,152,163],"targets,":[67,126],"are":[69],"audio":[70,136],"signals":[71],"with":[72],"reduced":[73],"using":[75,87,105],"pre-trained":[77],"foundation":[78,141],"model.":[79],"A":[80,90],"then":[85],"trained":[86],"these":[88,103,124],"targets.":[89,175],"key":[91],"feature":[92],"our":[94,180],"process":[96],"ability":[99],"automatically":[101],"targets":[104],"only":[106],"one-shot,":[107],"brief,":[108],"noise-free":[109],"reference":[110,156],"signal":[111],"target":[114,153],"sound.":[115],"Furthermore,":[116],"introduce":[118],"new":[120],"quality":[121,172],"metric":[122],"called":[127],"Semantic":[128],"Clarity":[129],"improvement":[130,146],"(SCi).":[131],"By":[132],"leveraging":[133],"semantic":[135,148],"embedding":[137],"capabilities":[138],"model,":[142],"SCi":[143,159],"measures":[144],"in":[147],"similarity":[149],"between":[150],"and":[154,186],"signal.":[157],"This":[158],"allows":[160],"effective":[162],"weighing":[165],"loss":[167],"function":[168],"based":[169],"on":[170],"Experimental":[176],"results":[177],"demonstrate":[178],"that":[179],"achieves":[182],"best":[184],"anomaly":[187],"performance":[189],"while":[190],"maintaining":[191],"processing":[193],"capabilities,":[194],"making":[195],"it":[196],"practical":[198],"solution":[199],"noisy":[201],"environments.":[203]},"counts_by_year":[],"updated_date":"2026-03-01T06:05:34.837733","created_date":"2026-02-28T00:00:00"}