{"id":"https://openalex.org/W4372266859","doi":"https://doi.org/10.1109/icassp49357.2023.10096245","title":"Improving Weakly Supervised Sound Event Detection with Causal Intervention","display_name":"Improving Weakly Supervised Sound Event Detection with Causal Intervention","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266859","doi":"https://doi.org/10.1109/icassp49357.2023.10096245"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5063679203","display_name":"Yifei Xin","orcid":"https://orcid.org/0000-0001-7792-6352"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifei Xin","raw_affiliation_strings":["Peking University,School of ECE,Shenzhen,China","School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043555011","display_name":"Dongchao Yang","orcid":"https://orcid.org/0000-0002-8905-224X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongchao Yang","raw_affiliation_strings":["Peking University,School of ECE,Shenzhen,China","School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016633964","display_name":"Fan Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Cui","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362605","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-8353-0423"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Corporation,Beijing,China","Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation,Beijing,China","institution_ids":["https://openalex.org/I862669128"]},{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peking University,School of ECE,Shenzhen,China","School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of ECE,Shenzhen,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063679203"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.3927,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53698207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9933000206947327,"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":0.9435999989509583,"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/spurious-relationship","display_name":"Spurious relationship","score":0.8900042772293091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.668765127658844},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6668798923492432},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.655081570148468},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5742772817611694},{"id":"https://openalex.org/keywords/confounding","display_name":"Confounding","score":0.5621882081031799},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.555850088596344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45860064029693604},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.41708946228027344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3861309885978699},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2143867313861847},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20547688007354736}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.8900042772293091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.668765127658844},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6668798923492432},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.655081570148468},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5742772817611694},{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.5621882081031799},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.555850088596344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45860064029693604},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.41708946228027344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3861309885978699},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2143867313861847},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20547688007354736},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096245","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2057212716","https://openalex.org/W2486285194","https://openalex.org/W2771361008","https://openalex.org/W2775505379","https://openalex.org/W2885822952","https://openalex.org/W2912599552","https://openalex.org/W3008739116","https://openalex.org/W3017521796","https://openalex.org/W3049446265","https://openalex.org/W3102714038","https://openalex.org/W3104182862","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3138516171","https://openalex.org/W3207731638","https://openalex.org/W4205306435","https://openalex.org/W4226442948","https://openalex.org/W4287753866","https://openalex.org/W4297841486","https://openalex.org/W6747331233","https://openalex.org/W6774030976","https://openalex.org/W6779600049","https://openalex.org/W6783399553","https://openalex.org/W6784163774","https://openalex.org/W6805622651"],"related_works":["https://openalex.org/W3113091479","https://openalex.org/W2162899405","https://openalex.org/W941090075","https://openalex.org/W2044987316","https://openalex.org/W3134374554","https://openalex.org/W2237480245","https://openalex.org/W2075065631","https://openalex.org/W2519167559","https://openalex.org/W4311248832","https://openalex.org/W4386113923"],"abstract_inverted_index":{"Existing":[0],"weakly":[1],"supervised":[2],"sound":[3,18],"event":[4,128],"detection":[5],"(WSSED)":[6],"work":[7],"has":[8],"not":[9],"explored":[10],"both":[11],"types":[12],"of":[13,69,104,113],"co-occurrences":[14],"simultaneously,":[15],"i.e.,":[16],"some":[17],"events":[19],"often":[20],"co-occur,":[21],"and":[22,40,82,116,143],"their":[23],"occurrences":[24],"are":[25],"usually":[26],"accompanied":[27],"by":[28,107],"specific":[29],"background":[30],"sounds,":[31],"so":[32],"they":[33],"would":[34],"be":[35],"inevitably":[36],"entangled,":[37],"causing":[38],"misclassification":[39],"biased":[41],"localization":[42],"results":[43],"with":[44],"only":[45],"clip-level":[46,83],"supervision.":[47],"To":[48],"tackle":[49],"this":[50],"issue,":[51],"we":[52,90],"first":[53],"establish":[54],"a":[55,92],"structural":[56],"causal":[57,88,93],"model":[58,75],"(SCM)":[59],"to":[60,76,99,121,146],"reveal":[61],"that":[62,72,133],"the":[63,66,74,87,101,119,122,127,138],"context":[64,112],"is":[65],"main":[67],"cause":[68],"co-occurrence":[70,105],"confounders":[71,106],"mislead":[73],"learn":[77],"spurious":[78],"correlations":[79],"between":[80],"frames":[81],"labels.":[84],"Based":[85],"on":[86,140],"analysis,":[89],"propose":[91],"intervention":[94],"(CI)":[95],"method":[96,135],"for":[97,125],"WSSED":[98],"remove":[100],"negative":[102],"impact":[103],"iteratively":[108],"accumulating":[109],"every":[110],"possible":[111],"each":[114],"class":[115],"then":[117],"re-projecting":[118],"contexts":[120],"frame-level":[123],"features":[124],"making":[126],"boundary":[129],"clearer.":[130],"Experiments":[131],"show":[132],"our":[134],"effectively":[136],"improves":[137],"performance":[139],"multiple":[141],"datasets":[142],"can":[144],"generalize":[145],"various":[147],"baseline":[148],"models.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}