{"id":"https://openalex.org/W2980322842","doi":"https://doi.org/10.1109/pacrim47961.2019.8985061","title":"Cure Dataset: Ladder Networks for Audio Event Classification","display_name":"Cure Dataset: Ladder Networks for Audio Event Classification","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2980322842","doi":"https://doi.org/10.1109/pacrim47961.2019.8985061","mag":"2980322842"},"language":"en","primary_location":{"id":"doi:10.1109/pacrim47961.2019.8985061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pacrim47961.2019.8985061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.03896","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033701513","display_name":"Harishchandra Dubey","orcid":"https://orcid.org/0000-0003-0476-3884"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harishchandra Dubey","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","[Microsoft Corp., Redmond, WA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Corp., Redmond, WA, USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034420214","display_name":"Dimitra Emmanouilidou","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitra Emmanouilidou","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","Microsoft Research, redmond, WA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, redmond, WA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ivan J. Tashev","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11236229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"1","last_page":"6"},"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":0.9987999796867371,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.972599983215332,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8095738887786865},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6697174310684204},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5821864604949951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5746381282806396},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5693312883377075},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5426239967346191},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5324797630310059},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5223113894462585},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5106201767921448},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.43841278553009033},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.435912549495697},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42681893706321716},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4056335985660553},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.08864372968673706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095738887786865},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6697174310684204},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5821864604949951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5746381282806396},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5693312883377075},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5426239967346191},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5324797630310059},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5223113894462585},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5106201767921448},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.43841278553009033},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.435912549495697},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42681893706321716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4056335985660553},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.08864372968673706},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/pacrim47961.2019.8985061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pacrim47961.2019.8985061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.03896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.03896","pdf_url":"https://arxiv.org/pdf/2001.03896","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2980322842","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2001.03896.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2001.03896","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.03896","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.03896","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.03896","pdf_url":"https://arxiv.org/pdf/2001.03896","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2980322842.pdf","grobid_xml":"https://content.openalex.org/works/W2980322842.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W830076066","https://openalex.org/W1972567154","https://openalex.org/W2033875152","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2103279261","https://openalex.org/W2111072639","https://openalex.org/W2161381512","https://openalex.org/W2174554700","https://openalex.org/W2295001676","https://openalex.org/W2295348761","https://openalex.org/W2354870669","https://openalex.org/W2566935005","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2775505379","https://openalex.org/W2775794021","https://openalex.org/W2885392124","https://openalex.org/W2886877375","https://openalex.org/W2962756039","https://openalex.org/W2962910554","https://openalex.org/W6623329352","https://openalex.org/W6685251022","https://openalex.org/W6697498398","https://openalex.org/W6729831399","https://openalex.org/W6734260513","https://openalex.org/W6747331233","https://openalex.org/W6754161993"],"related_works":["https://openalex.org/W2143944641","https://openalex.org/W3200739883","https://openalex.org/W3090383809","https://openalex.org/W2502508992","https://openalex.org/W2093301770","https://openalex.org/W3130461075","https://openalex.org/W3088843790","https://openalex.org/W2903090425","https://openalex.org/W1978920452","https://openalex.org/W2971668269","https://openalex.org/W2786433859","https://openalex.org/W2908297977","https://openalex.org/W2577998051","https://openalex.org/W2794137263","https://openalex.org/W3049659711","https://openalex.org/W3122272388","https://openalex.org/W2395938203","https://openalex.org/W3201962466","https://openalex.org/W3026539582","https://openalex.org/W2103011222"],"abstract_inverted_index":{"Audio":[0],"event":[1,76],"classification":[2,180],"is":[3,57,113,124],"an":[4],"important":[5],"task":[6],"for":[7,51,90,129],"several":[8],"applications":[9],"such":[10],"as":[11,59,87,126,149],"surveillance,":[12],"audio,":[13],"video":[14],"and":[15,97,143,161,171,178],"multimedia":[16],"retrieval":[17],"etc.":[18],"There":[19],"are":[20],"approximately":[21],"340":[22],"million":[23],"people":[24,52],"with":[25,53,95],"hearing":[26,54],"loss":[27],"who":[28],"can\u2019t":[29],"perceive":[30],"events":[31,48],"happening":[32],"around":[33],"them.":[34],"This":[35],"paper":[36],"establishes":[37],"the":[38,66,80,104,121,136,164],"CURE":[39,131],"dataset":[40],"which":[41],"contains":[42],"curated":[43],"set":[44,156],"of":[45,138,166,176],"specific":[46],"audio":[47,75,88],"most":[49],"relevant":[50],"loss.":[55],"It":[56],"formatted":[58],"5":[60],"sec":[61],"sound":[62],"recordings":[63,108],"derived":[64],"from":[65],"Freesound":[67],"project.":[68],"We":[69,78,93,133],"propose":[70],"a":[71,111,153],"ladder":[72],"network":[73,84,168],"based":[74],"classifier.":[77,151],"adopted":[79,125],"state-of-the-art":[81],"convolutional":[82],"neural":[83],"(CNN)":[85],"embeddings":[86],"features":[89],"this":[91],"task.":[92],"start":[94],"signal":[96],"feature":[98,127],"normalization":[99],"that":[100],"aims":[101],"to":[102],"reduce":[103],"mismatch":[105],"between":[106],"different":[107],"scenarios.":[109],"Initially,":[110],"CNN":[112],"trained":[114],"on":[115],"weakly":[116],"labeled":[117],"Audioset":[118],"data.":[119],"Next,":[120],"pre-trained":[122],"model":[123],"extractor":[128],"proposed":[130],"corpus.":[132],"also":[134],"explore":[135],"performance":[137],"extreme":[139],"learning":[140],"machine":[141,147],"(ELM)":[142],"use":[144],"support":[145],"vector":[146],"(SVM)":[148],"baseline":[150],"As":[152],"second":[154],"evaluation":[155],"we":[157],"incorporate":[158],"ESC-50.":[159],"Results":[160],"discussions":[162],"validate":[163],"superiority":[165],"Ladder":[167],"over":[169],"ELM":[170],"SVM":[172],"classifier":[173],"in":[174],"terms":[175],"robustness":[177],"increased":[179],"accuracy.":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}