{"id":"https://openalex.org/W2595120084","doi":"https://doi.org/10.1109/icassp.2017.7952263","title":"Large-scale audio event discovery in one million YouTube videos","display_name":"Large-scale audio event discovery in one million YouTube videos","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2595120084","doi":"https://doi.org/10.1109/icassp.2017.7952263","mag":"2595120084"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5103622427","display_name":"Aren Jansen","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aren Jansen","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109012430","display_name":"Jort F. Gemmeke","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jort F. Gemmeke","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055458377","display_name":"Daniel P. W. Ellis","orcid":"https://orcid.org/0000-0002-5076-4311"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel P. W. Ellis","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359306","display_name":"Xiaofeng Liu","orcid":"https://orcid.org/0009-0007-6147-7119"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofeng Liu","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075993346","display_name":"Wade Lawrence","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wade Lawrence","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089627238","display_name":"Dylan Freedman","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan Freedman","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"786","last_page":"790"},"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":0.9997000098228455,"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":0.9987000226974487,"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":0.8184915781021118},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7203123569488525},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7043396830558777},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7016687393188477},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5813469290733337},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5806876420974731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5047222375869751},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4486454129219055},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.44498515129089355},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41656115651130676},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.41432344913482666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.331085741519928},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15054532885551453},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1316584050655365},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.11493492126464844},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.08805534243583679}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184915781021118},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7203123569488525},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7043396830558777},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7016687393188477},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5813469290733337},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5806876420974731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5047222375869751},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4486454129219055},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.44498515129089355},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41656115651130676},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.41432344913482666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.331085741519928},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15054532885551453},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1316584050655365},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.11493492126464844},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.08805534243583679},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W182707955","https://openalex.org/W1520721198","https://openalex.org/W1686810756","https://openalex.org/W1923404803","https://openalex.org/W1964442016","https://openalex.org/W2077159900","https://openalex.org/W2086384421","https://openalex.org/W2105068979","https://openalex.org/W2127612600","https://openalex.org/W2129634963","https://openalex.org/W2138615112","https://openalex.org/W2147717514","https://openalex.org/W2154714154","https://openalex.org/W2408491073","https://openalex.org/W2526050071","https://openalex.org/W2963158330","https://openalex.org/W2963547958","https://openalex.org/W6631208077","https://openalex.org/W6675872639","https://openalex.org/W6678951767","https://openalex.org/W6680970901","https://openalex.org/W6714426239"],"related_works":["https://openalex.org/W2112616324","https://openalex.org/W2064012922","https://openalex.org/W2717715803","https://openalex.org/W2056936702","https://openalex.org/W4229926342","https://openalex.org/W2395157499","https://openalex.org/W2106826515","https://openalex.org/W2160665135","https://openalex.org/W2375135037","https://openalex.org/W4200288206"],"abstract_inverted_index":{"Internet":[0],"videos":[1,47],"provide":[2],"a":[3,10,40,57,73,92],"virtually":[4],"boundless":[5],"source":[6],"of":[7,13,35,43,50,76,103,123,151],"audio":[8,37,69,79,106,132],"with":[9],"conspicuous":[11],"lack":[12],"localized":[14],"annotations,":[15],"presenting":[16],"an":[17,28,140],"ideal":[18],"setting":[19],"for":[20,95,143],"unsupervised":[21,96,141],"methods.":[22],"With":[23],"this":[24],"motivation,":[25],"we":[26,99,119],"perform":[27],"unprecedented":[29],"exploration":[30],"into":[31],"the":[32,84,101,104,121,148,152],"large-scale":[33],"discovery":[34],"recurring":[36],"events":[38,80],"in":[39,109],"diverse":[41],"corpus":[42,149],"one":[44],"million":[45],"YouTube":[46],"(45K":[48],"hours":[49],"audio).":[51],"Our":[52],"approach":[53],"is":[54,115,136],"to":[55,62,81,90,129],"apply":[56],"streaming,":[58],"nonparametric":[59],"clustering":[60,86],"algorithm":[61],"both":[63],"spectral":[64],"features":[65],"and":[66,126],"out-of-domain":[67],"neural":[68],"embeddings.":[70],"We":[71],"use":[72],"small":[74],"portion":[75],"manually":[77],"annotated":[78],"quantitatively":[82],"estimate":[83],"intrinsic":[85],"performance.":[87],"In":[88],"addition":[89],"providing":[91],"useful":[93],"mechanism":[94],"active":[97],"learning,":[98,117],"demonstrate":[100],"effectiveness":[102],"discovered":[105,153],"event":[107,154],"clusters":[108],"two":[110],"downstream":[111],"applications.":[112],"The":[113,134],"first":[114],"weakly-supervised":[116],"where":[118],"exploit":[120],"association":[122],"video-level":[124],"metadata":[125],"cluster":[127],"occurrences":[128],"temporally":[130],"localize":[131],"events.":[133],"second":[135],"informative":[137],"activity":[138],"detection,":[139],"method":[142],"semantic":[144],"saliency":[145],"based":[146],"on":[147],"statistics":[150],"clusters.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}