{"id":"https://openalex.org/W2795488127","doi":"https://doi.org/10.21437/interspeech.2018-1120","title":"Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection","display_name":"Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2795488127","doi":"https://doi.org/10.21437/interspeech.2018-1120","mag":"2795488127"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1120","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.09673","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003744098","display_name":"Shao-Yen Tseng","orcid":"https://orcid.org/0000-0003-1795-8330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao-Yen Tseng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618681","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0003-3117-8955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072368204","display_name":"Joseph Szurley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Szurley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110454109","display_name":"Samarjit Das","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samarjit Das","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7216,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66987303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3279","last_page":"3283"},"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":0.9968000054359436,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9689000248908997,"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/computer-science","display_name":"Computer science","score":0.8415056467056274},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.736059844493866},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.732031524181366},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6226899027824402},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6147570013999939},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5595086216926575},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5345994830131531},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4733172655105591},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46194013953208923},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.415089875459671},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3416760563850403},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3306613564491272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415056467056274},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.736059844493866},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.732031524181366},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6226899027824402},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6147570013999939},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595086216926575},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5345994830131531},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4733172655105591},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46194013953208923},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.415089875459671},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3416760563850403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3306613564491272},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-1120","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.09673","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.09673","pdf_url":"https://arxiv.org/pdf/1712.09673","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"mag:2795488127","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1712.09673","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.1712.09673","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1712.09673","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.09673","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.09673","pdf_url":"https://arxiv.org/pdf/1712.09673","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2795488127.pdf","grobid_xml":"https://content.openalex.org/works/W2795488127.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2038484192","https://openalex.org/W2116206474","https://openalex.org/W2354870669","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2614010354"],"related_works":["https://openalex.org/W2778014476","https://openalex.org/W2948510438","https://openalex.org/W2918555356","https://openalex.org/W2964891022","https://openalex.org/W3096841046","https://openalex.org/W2604490051","https://openalex.org/W2751116311","https://openalex.org/W2036931953","https://openalex.org/W2963679447","https://openalex.org/W2949251039","https://openalex.org/W2400753342","https://openalex.org/W3049010479","https://openalex.org/W3034207266","https://openalex.org/W3080294851","https://openalex.org/W2995868231","https://openalex.org/W3081333083","https://openalex.org/W3201539443","https://openalex.org/W2267038056","https://openalex.org/W2894301961","https://openalex.org/W2900292082"],"abstract_inverted_index":{"State-of-the-art":[0],"audio":[1,56,73,99,131,139],"event":[2],"detection":[3],"(AED)":[4],"systems":[5],"rely":[6],"on":[7],"supervised":[8],"learning":[9,41],"using":[10,47,72,81,102],"strongly":[11],"labeled":[12,114],"data.":[13],"However,":[14],"this":[15,33],"dependence":[16],"severely":[17],"limits":[18],"scalability":[19],"to":[20,30,88],"large-scale":[21],"datasets":[22],"where":[23,170],"fine":[24],"resolution":[25],"annotations":[26],"are":[27,173],"too":[28],"expensive":[29],"obtain.":[31],"In":[32],"paper,":[34],"we":[35,123],"propose":[36],"a":[37,60,82,103,109,120,129],"small-footprint":[38],"multiple":[39],"instance":[40],"(MIL)":[42],"framework":[43,54,77,156],"for":[44,168],"multi-class":[45],"AED":[46,163],"weakly":[48,113],"annotated":[49],"labels.":[50],"The":[51],"proposed":[52],"MIL":[53,76,153],"uses":[55],"embeddings":[57,74,140],"extracted":[58,141],"from":[59],"pre-trained":[61],"convolutional":[62,144],"neural":[63,90,145],"network":[64],"as":[65],"input":[66],"features.":[67],"We":[68,92,136],"show":[69,137],"that":[70,138],"by":[71,96,134,142],"the":[75,125,143,149,158,162],"can":[78],"be":[79],"implemented":[80],"simple":[83],"DNN":[84],"with":[85,119],"performance":[86,150],"comparable":[87],"recurrent":[89],"networks.":[91],"evaluate":[93],"our":[94],"approach":[95],"training":[97],"an":[98],"tagging":[100,132],"system":[101,133,164],"subset":[104],"of":[105,112,128,151,161],"AudioSet,":[106],"which":[107],"is":[108,166],"large":[110],"collection":[111],"YouTube":[115],"video":[116],"excerpts.":[117],"Combined":[118],"late-fusion":[121],"approach,":[122],"improve":[124],"F1":[126],"score":[127],"baseline":[130],"17%.":[135],"networks":[146],"significantly":[147],"boost":[148],"all":[152],"models.":[154],"This":[155],"reduces":[157],"model":[159],"complexity":[160],"and":[165],"suitable":[167],"applications":[169],"computational":[171],"resources":[172],"limited.":[174]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}