{"id":"https://openalex.org/W2407005679","doi":"https://doi.org/10.1109/icassp.2016.7472176","title":"Audio-based multimedia event detection using deep recurrent neural networks","display_name":"Audio-based multimedia event detection using deep recurrent neural networks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2407005679","doi":"https://doi.org/10.1109/icassp.2016.7472176","mag":"2407005679"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100377624","display_name":"Yun Wang","orcid":"https://orcid.org/0000-0002-4749-2984"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113916937","display_name":"Leonardo Neves","orcid":"https://orcid.org/0000-0002-3857-0522"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonardo Neves","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2742","last_page":"2746"},"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":0.998199999332428,"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":0.9970999956130981,"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":0.8579045534133911},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6713691353797913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6004368662834167},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5305303335189819},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4978063106536865},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.49281981587409973},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47868210077285767},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4765879809856415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45614737272262573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39650052785873413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579045534133911},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6713691353797913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6004368662834167},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5305303335189819},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4978063106536865},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.49281981587409973},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47868210077285767},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4765879809856415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45614737272262573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39650052785873413},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1535031652","https://openalex.org/W1559922967","https://openalex.org/W1600745603","https://openalex.org/W1650531274","https://openalex.org/W1899504021","https://openalex.org/W1971129545","https://openalex.org/W2018951638","https://openalex.org/W2036931953","https://openalex.org/W2043194666","https://openalex.org/W2064675550","https://openalex.org/W2075606539","https://openalex.org/W2090777335","https://openalex.org/W2095705004","https://openalex.org/W2131774270","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2396707013","https://openalex.org/W2398456099","https://openalex.org/W2400753342","https://openalex.org/W2402668451","https://openalex.org/W2406257467","https://openalex.org/W2408491073","https://openalex.org/W2963399116","https://openalex.org/W6631636882","https://openalex.org/W6632100227","https://openalex.org/W6633383461","https://openalex.org/W6636898527","https://openalex.org/W6674330103","https://openalex.org/W6712469065","https://openalex.org/W6712880999","https://openalex.org/W6713457403"],"related_works":["https://openalex.org/W1509467138","https://openalex.org/W2206427987","https://openalex.org/W2038078646","https://openalex.org/W2329734087","https://openalex.org/W2267493284","https://openalex.org/W3175075966","https://openalex.org/W2964243145","https://openalex.org/W2328213259","https://openalex.org/W1679636228","https://openalex.org/W2883762569"],"abstract_inverted_index":{"Multimedia":[0],"event":[1,88],"detection":[2],"(MED)":[3],"is":[4,56,145],"the":[5,33,63,75,139],"task":[6],"of":[7,21,134,141],"detecting":[8],"given":[9,87],"events":[10],"(e.g.":[11],"birthday":[12],"party,":[13],"making":[14],"a":[15,18,60,86,91,132,148],"sandwich)":[16],"in":[17,90,171],"large":[19],"collection":[20],"video":[22,92],"clips.":[23],"While":[24],"visual":[25],"features":[26,35],"and":[27,174,180],"automatic":[28],"speech":[29],"recognition":[30],"typically":[31,57],"provide":[32],"best":[34],"for":[36,123,165],"this":[37,110],"task,":[38],"nonspeech":[39],"audio":[40,129],"can":[41],"also":[42],"contribute":[43],"useful":[44],"information,":[45,105],"such":[46],"as":[47,59,147],"crowds":[48],"cheering,":[49],"engine":[50],"noises,":[51],"or":[52,80,106],"animal":[53],"sounds.":[54],"MED":[55],"formulated":[58],"two-stage":[61],"process:":[62],"first":[64],"stage":[65,77],"generates":[66],"clip-level":[67,150,166,175],"feature":[68],"representations,":[69],"often":[70],"by":[71],"aggregating":[72],"frame-level":[73,142,173],"features;":[74],"second":[76],"performs":[78],"binary":[79],"multi-class":[81],"classification":[82],"to":[83,178],"decide":[84],"whether":[85],"occurs":[89],"clip.":[93],"Both":[94],"stages":[95],"are":[96,156],"usually":[97],"performed":[98],"\"statically\",":[99],"i.e.":[100],"using":[101],"only":[102],"local":[103],"temporal":[104,115],"bag-of-words":[107],"models.":[108],"In":[109],"paper,":[111],"we":[112],"introduce":[113],"longer-range":[114],"information":[116],"with":[117],"deep":[118],"recurrent":[119],"neural":[120,182],"networks":[121,164],"(RNNs)":[122],"both":[124,172],"stages.":[125],"We":[126,168],"classify":[127],"each":[128],"frame":[130],"among":[131],"set":[133],"semantic":[135],"units":[136],"called":[137],"\"noisemes\"":[138],"sequence":[140],"confidence":[143,153],"distributions":[144],"used":[146],"variable-length":[149],"representation.":[151],"Such":[152],"vector":[154],"sequences":[155],"then":[157],"fed":[158],"into":[159],"long":[160],"short-term":[161],"memory":[162],"(LSTM)":[163],"classification.":[167],"observe":[169],"improvements":[170],"performance":[176],"compared":[177],"SVM":[179],"feed-forward":[181],"network":[183],"baselines.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}