{"id":"https://openalex.org/W4400066986","doi":"https://doi.org/10.1145/3663976.3664242","title":"Contrastive Learning with Spectrum Information Augmentation in Abnormal Sound Detection","display_name":"Contrastive Learning with Spectrum Information Augmentation in Abnormal Sound Detection","publication_year":2024,"publication_date":"2024-04-26","ids":{"openalex":"https://openalex.org/W4400066986","doi":"https://doi.org/10.1145/3663976.3664242"},"language":"en","primary_location":{"id":"doi:10.1145/3663976.3664242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663976.3664242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition","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/A5102936720","display_name":"Xinxin Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxin Meng","raw_affiliation_strings":["Information and Communication Company, State Grid Xinjiang Electronic Power Company, China"],"raw_orcid":"https://orcid.org/0009-0005-1898-9157","affiliations":[{"raw_affiliation_string":"Information and Communication Company, State Grid Xinjiang Electronic Power Company, China","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058257664","display_name":"Jiangtao Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangtao Guo","raw_affiliation_strings":["Information and Communication Company, State Grid Xinjiang Electronic Power Company, China"],"raw_orcid":"https://orcid.org/0009-0008-2109-5439","affiliations":[{"raw_affiliation_string":"Information and Communication Company, State Grid Xinjiang Electronic Power Company, China","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081283108","display_name":"Yunxiang Zhang","orcid":"https://orcid.org/0000-0001-5633-7786"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxiang Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang university, China"],"raw_orcid":"https://orcid.org/0000-0001-5633-7786","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang university, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102757710","display_name":"Shun Huang","orcid":"https://orcid.org/0009-0001-3012-7833"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shun Huang","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang university, China"],"raw_orcid":"https://orcid.org/0009-0001-3012-7833","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang university, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10294418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.991599977016449,"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":0.6747159957885742},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5756019949913025},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.4641398787498474},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45657825469970703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38228556513786316},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20808619260787964},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07191956043243408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6747159957885742},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5756019949913025},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.4641398787498474},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45657825469970703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38228556513786316},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20808619260787964},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07191956043243408},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3663976.3664242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3663976.3664242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 2nd Asia Conference on Computer Vision, Image Processing and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2920946673","https://openalex.org/W3015356122","https://openalex.org/W3133542152","https://openalex.org/W3162150435","https://openalex.org/W4221140395","https://openalex.org/W4287272592","https://openalex.org/W4287635833","https://openalex.org/W4372349649"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2909726438","https://openalex.org/W4396696052","https://openalex.org/W2382290278"],"abstract_inverted_index":{"The":[0,16,102],"outlier":[1],"exposure":[2],"method":[3,21,60,95,107,124],"is":[4,22,43],"an":[5],"effective":[6],"approach":[7],"to":[8,24,71,75],"address":[9],"the":[10,26,29,69,76,80,84,89,93,97,120,126],"unsupervised":[11],"anomaly":[12],"sound":[13],"detection":[14],"problem.":[15],"key":[17],"focus":[18],"of":[19,32,79,88,122],"this":[20,115],"how":[23],"make":[25],"model":[27,70],"learn":[28],"distribution":[30],"space":[31],"normal":[33,85],"data.":[34],"Based":[35],"on":[36,96,114,125],"biological":[37],"perception":[38],"and":[39,48],"data":[40,58],"analysis,":[41],"it":[42],"found":[44],"that":[45,105],"anomalous":[46],"audio":[47],"noise":[49],"often":[50],"have":[51],"higher":[52],"frequencies.":[53],"Therefore,":[54],"we":[55],"propose":[56],"a":[57],"augmentation":[59],"for":[61],"high-frequency":[62],"information":[63,78],"in":[64],"contrastive":[65,110],"learning.":[66],"This":[67],"enables":[68],"pay":[72],"more":[73],"attention":[74],"low-frequency":[77],"audio,":[81],"which":[82],"represents":[83],"operational":[86],"mode":[87],"machine.":[90],"We":[91,117],"evaluated":[92,119],"proposed":[94],"DCASE":[98,127],"2020":[99],"Task":[100,129],"2.":[101],"results":[103],"showed":[104],"our":[106,123],"outperformed":[108],"other":[109],"learning":[111],"methods":[112],"used":[113],"dataset.":[116,131],"also":[118],"generalizability":[121],"2022":[128],"2":[130]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}