{"id":"https://openalex.org/W4410322261","doi":"https://doi.org/10.1145/3722150.3722153","title":"Research on Anomaly Sound Detection Methods Based on Large Models","display_name":"Research on Anomaly Sound Detection Methods Based on Large Models","publication_year":2025,"publication_date":"2025-01-16","ids":{"openalex":"https://openalex.org/W4410322261","doi":"https://doi.org/10.1145/3722150.3722153"},"language":"en","primary_location":{"id":"doi:10.1145/3722150.3722153","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3722150.3722153","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3722150.3722153","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Control Engineering and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3722150.3722153","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shuyao Hu","orcid":"https://orcid.org/0009-0009-5940-9947"},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyao Hu","raw_affiliation_strings":["National Computer network Emergency Response technical Team/Coordination Center of China, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5940-9947","affiliations":[{"raw_affiliation_string":"National Computer network Emergency Response technical Team/Coordination Center of China, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049974175","display_name":"Guiyang Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiyang Guo","raw_affiliation_strings":["National Computer network Emergency Response technical Team/Coordination Center of China, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-9230-8754","affiliations":[{"raw_affiliation_string":"National Computer network Emergency Response technical Team/Coordination Center of China, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073512565","display_name":"Jiang Zhuo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087772","display_name":"National Computer Network Emergency Response Technical Team/Coordination Center of Chinar","ror":"https://ror.org/00247dh76","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210087772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Jiang","raw_affiliation_strings":["National Computer network Emergency Response technical Team/Coordination Center of China, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-5796-2245","affiliations":[{"raw_affiliation_string":"National Computer network Emergency Response technical Team/Coordination Center of China, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210087772"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210087772"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09537747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9921000003814697,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9743000268936157,"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/anomaly-detection","display_name":"Anomaly detection","score":0.656091034412384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6075021624565125},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5252856016159058},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.487078458070755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34294945001602173},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21889430284500122},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05492141842842102}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.656091034412384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6075021624565125},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5252856016159058},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.487078458070755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34294945001602173},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21889430284500122},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05492141842842102},{"id":"https://openalex.org/C26873012","wikidata":"https://www.wikidata.org/wiki/Q214781","display_name":"Condensed matter physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3722150.3722153","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3722150.3722153","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3722150.3722153","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Control Engineering and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3722150.3722153","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3722150.3722153","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3722150.3722153","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 9th International Conference on Control Engineering and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410322261.pdf","grobid_xml":"https://content.openalex.org/works/W4410322261.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1972567154","https://openalex.org/W2014706377","https://openalex.org/W2082487636","https://openalex.org/W2155273149","https://openalex.org/W2591013610","https://openalex.org/W4400259231","https://openalex.org/W4400943524","https://openalex.org/W4401615828","https://openalex.org/W4403909032"],"related_works":["https://openalex.org/W2806741695","https://openalex.org/W4290647774","https://openalex.org/W3189286258","https://openalex.org/W3207797160","https://openalex.org/W3210364259","https://openalex.org/W4300558037","https://openalex.org/W2667207928","https://openalex.org/W2912112202","https://openalex.org/W4377864969","https://openalex.org/W3120251014"],"abstract_inverted_index":{"With":[0],"the":[1,11,26,41,58,68,86,97,112,141,167,170,197,200,209],"continuous":[2],"development":[3,42],"of":[4,44,60,99,114,136,161,173,203,211],"industrial":[5],"equipment":[6],"and":[7,20,55,96,108,110,147,152,175,182,190,205,218],"security":[8],"monitoring":[9],"fields,":[10],"demand":[12],"for":[13,221],"intelligent":[14],"anomaly":[15,46,78,126],"detection":[16,47,89,217],"is":[17,34],"increasing":[18],"more":[19],"more.":[21],"Equipment":[22],"abnormal":[23,87,145,179,193,215],"diagnosis":[24],"from":[25,49,132],"acoustic":[27],"perspective,":[28],"as":[29,103,121],"a":[30,133,162],"reliable":[31],"research":[32],"approach,":[33],"widely":[35],"studied.":[36],"This":[37],"article":[38,81],"first":[39],"reviews":[40],"history":[43],"audio":[45,77,137,158],"technology,":[48],"rule-based":[50],"methods":[51,116],"to":[52,57,143],"statistical":[53],"methods,":[54],"then":[56,82],"application":[59,98],"deep":[61,73],"learning":[62,74],"techniques,":[63],"with":[64,117],"special":[65],"focus":[66],"on":[67],"great":[69],"progress":[70],"made":[71],"by":[72],"technology":[75],"in":[76,84,125,178,192,214],"detection.":[79,127],"The":[80],"discusses":[83],"detail":[85],"sound":[88,180,194,216],"techniques":[90],"using":[91,156],"frequency-shift":[92],"Cepstral":[93],"coefficients":[94],"(MFCC)":[95],"compact":[100],"models,":[101,129,207],"such":[102],"Gaussian":[104],"mixture":[105],"models":[106,119,177,186,213],"(GMM),":[107],"compares":[109,169],"analyzes":[111,199],"performance":[113,189],"these":[115],"large":[118,122,176,185,206,212],"(such":[120],"language":[123],"models)":[124],"Large":[128],"which":[130],"learn":[131],"huge":[134],"amount":[135],"data,":[138],"have":[139,148,187],"improved":[140],"ability":[142],"recognize":[144],"sounds,":[146],"shown":[149],"better":[150],"strength":[151],"generalization":[153],"ability.":[154],"Next,":[155],"historical":[157],"playback":[159],"data":[160,164],"specific":[163],"center":[165],"room,":[166],"paper":[168,198],"recognition":[171,201],"effects":[172],"GMM":[174],"detection,":[181],"finds":[183],"that":[184],"higher":[188],"accuracy":[191],"recognition.":[195],"Finally,":[196],"results":[202],"small":[204],"highlighting":[208],"advantages":[210],"possible":[219],"areas":[220],"improvement.":[222]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}