{"id":"https://openalex.org/W4411336667","doi":"https://doi.org/10.1109/lra.2025.3580317","title":"Zero-Shot Denoiser for Enhanced Acoustic Inspection: Mix Signal Separation and Text-Guided Audio Reconstruction","display_name":"Zero-Shot Denoiser for Enhanced Acoustic Inspection: Mix Signal Separation and Text-Guided Audio Reconstruction","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W4411336667","doi":"https://doi.org/10.1109/lra.2025.3580317"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3580317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3580317","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation 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":"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":false,"raw_author_name":"Koki Shoda","raw_affiliation_strings":["Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan","Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0001-7668-8548","affiliations":[{"raw_affiliation_string":"Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051800939","display_name":"Jun Younes Louhi Kasahara","orcid":"https://orcid.org/0000-0002-5924-8858"},"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":["Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan","Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5924-8858","affiliations":[{"raw_affiliation_string":"Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Department of Precision Engineering, Graduate School of Engineering, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056335309","display_name":"Qi An","orcid":"https://orcid.org/0000-0001-7641-2632"},"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":["Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan","Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7641-2632","affiliations":[{"raw_affiliation_string":"Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Japan","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":["Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan","Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1280-069X","affiliations":[{"raw_affiliation_string":"Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Chiba, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Department of Human and Engineered Environmental Studies, Graduate School of Frontier Sciences, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"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":0.10331897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"8","first_page":"7867","last_page":"7874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9876999855041504,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9474999904632568,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/signal","display_name":"SIGNAL (programming language)","score":0.5630642771720886},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5573844313621521},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5346751809120178},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5257773399353027},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5213950276374817},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5059129595756531},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.49896883964538574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4422553777694702},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2359735369682312},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.2260463535785675},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08011108636856079},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.05257567763328552}],"concepts":[{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5630642771720886},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5573844313621521},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5346751809120178},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5257773399353027},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5213950276374817},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5059129595756531},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.49896883964538574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4422553777694702},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2359735369682312},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.2260463535785675},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08011108636856079},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.05257567763328552},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3580317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3580317","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1513311132","https://openalex.org/W2127851351","https://openalex.org/W2151395579","https://openalex.org/W2168273590","https://openalex.org/W2217477878","https://openalex.org/W2304609584","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2418833460","https://openalex.org/W2508393166","https://openalex.org/W2598036111","https://openalex.org/W2774707084","https://openalex.org/W2800059141","https://openalex.org/W2913939497","https://openalex.org/W2946177253","https://openalex.org/W2954049404","https://openalex.org/W2959214850","https://openalex.org/W2972401521","https://openalex.org/W3028356179","https://openalex.org/W3039928442","https://openalex.org/W3042609801","https://openalex.org/W3048055188","https://openalex.org/W3159892859","https://openalex.org/W3163605974","https://openalex.org/W3176445421","https://openalex.org/W3205567090","https://openalex.org/W3217317857","https://openalex.org/W4223583411","https://openalex.org/W4226442948","https://openalex.org/W4372260250","https://openalex.org/W4372260310","https://openalex.org/W4372266927","https://openalex.org/W4372271367","https://openalex.org/W4385245566","https://openalex.org/W4385656233","https://openalex.org/W4386076517","https://openalex.org/W4390875033","https://openalex.org/W4391621214","https://openalex.org/W4401450005","https://openalex.org/W4405180122","https://openalex.org/W4410065572","https://openalex.org/W6611798230","https://openalex.org/W6676179485","https://openalex.org/W6706179695","https://openalex.org/W6745609711","https://openalex.org/W6766838974","https://openalex.org/W6847118160","https://openalex.org/W6869413407","https://openalex.org/W6872850465","https://openalex.org/W6873679058"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Acoustic":[0],"inspection":[1,155],"is":[2,10],"crucial":[3],"for":[4,56,64,95,134,153],"infrastructure":[5],"maintenance,":[6],"but":[7],"its":[8],"effectiveness":[9,130],"often":[11],"hampered":[12],"by":[13],"environmental":[14],"noise.":[15],"Conventional":[16],"denoising":[17,121],"methods":[18],"rely":[19],"on":[20],"prior":[21],"knowledge":[22],"or":[23,45],"training":[24],"data,":[25],"limiting":[26],"their":[27],"practicability.":[28],"This":[29],"paper":[30],"presents":[31],"Zero-Shot":[32],"Denoiser,":[33],"a":[34,109,148],"novel":[35],"approach":[36,133,139],"achieving":[37],"noise":[38,46,150],"reduction":[39,151],"without":[40],"pre-collected":[41],"target":[42,82],"sound":[43],"samples":[44],"knowledge.":[47],"Our":[48,138],"method":[49],"synergistically":[50],"combines":[51],"Blind":[52],"Signal":[53],"Separation":[54],"(BSS)":[55],"unsupervised":[57],"audio":[58,66],"decomposition":[59],"and":[60,73,80,123,146,156],"Artifact-Resilient":[61],"Attention":[62],"(AR-Attention)":[63],"text-guided":[65],"reconstruction.":[67],"AR-Attention":[68],"leverages":[69],"pre-trained":[70],"audio-language":[71,93],"models":[72],"dual":[74],"normalization":[75],"to":[76,116],"mitigate":[77],"BSS":[78,97],"artifacts":[79],"identify":[81],"sounds":[83],"semantically.":[84],"We":[85],"introduce":[86],"pseudo":[87],"Signal-to-Noise":[88],"Ratio,":[89],"derived":[90],"from":[91],"the":[92,129,141],"model,":[94],"automatic":[96],"hyperparameter":[98],"optimization.":[99],"In":[100],"experiments":[101,124],"using":[102],"public":[103],"datasets,":[104],"our":[105,132],"method,":[106],"operating":[107],"in":[108],"true":[110],"zero-shot":[111],"setting,":[112],"achieved":[113],"performance":[114],"comparable":[115],"that":[117],"of":[118,131,143],"state-of-the-art":[119],"supervised":[120],"methods,":[122],"targeting":[125],"hammering":[126],"tests":[127],"confirmed":[128],"real-world":[135],"acoustic":[136,154,158],"inspections.":[137],"overcomes":[140],"limitations":[142],"data-dependent":[144],"techniques":[145],"offers":[147],"versatile":[149],"solution":[152],"broader":[157],"tasks.":[159]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-06-17T00:00:00"}