{"id":"https://openalex.org/W2593116425","doi":"https://doi.org/10.1109/icassp.2017.7952261","title":"Audio Set: An ontology and human-labeled dataset for audio events","display_name":"Audio Set: An ontology and human-labeled dataset for audio events","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2593116425","doi":"https://doi.org/10.1109/icassp.2017.7952261","mag":"2593116425"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952261","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/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/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"]}]},{"author_position":"middle","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/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":"middle","author":{"id":"https://openalex.org/A5110435728","display_name":"Robert C. Moore","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":"R. Channing Moore","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/A5059222327","display_name":"Manoj Plakal","orcid":"https://orcid.org/0000-0001-6759-3873"},"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":"Manoj Plakal","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/A5068127101","display_name":"Marvin Ritter","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":"Marvin Ritter","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":3007,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"776","last_page":"780"},"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/T13996","display_name":"Diverse Musicological Studies","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9822999835014343,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8753601908683777},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7566742897033691},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6900683641433716},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.642027735710144},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6284597516059875},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.599646806716919},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4834674000740051},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4352216124534607},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.41763097047805786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38362419605255127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3156595230102539},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2212548851966858},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.07772436738014221}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8753601908683777},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7566742897033691},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6900683641433716},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.642027735710144},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6284597516059875},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.599646806716919},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4834674000740051},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4352216124534607},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.41763097047805786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38362419605255127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3156595230102539},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2212548851966858},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.07772436738014221},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952261","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":25,"referenced_works":["https://openalex.org/W1535031652","https://openalex.org/W2008142581","https://openalex.org/W2032337854","https://openalex.org/W2038484192","https://openalex.org/W2068737686","https://openalex.org/W2074188409","https://openalex.org/W2081580037","https://openalex.org/W2081913879","https://openalex.org/W2086384421","https://openalex.org/W2097117768","https://openalex.org/W2105068979","https://openalex.org/W2117539524","https://openalex.org/W2126422864","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2210407171","https://openalex.org/W2508979362","https://openalex.org/W2526050071","https://openalex.org/W2566935005","https://openalex.org/W4236923591","https://openalex.org/W4319290960","https://openalex.org/W6632100227","https://openalex.org/W6674914833","https://openalex.org/W6675872639","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2970176078","https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2088690926","https://openalex.org/W1526651343","https://openalex.org/W2371215329"],"abstract_inverted_index":{"Audio":[0,44],"event":[1,142],"recognition,":[2],"the":[3,41,57,79,92,137],"human-like":[4],"ability":[5],"to":[6,55,90],"identify":[7],"and":[8,64,81,118,129],"relate":[9],"sounds":[10],"from":[11,32,87],"audio,":[12],"is":[13,123],"a":[14,46,68,124],"nascent":[15],"problem":[16],"in":[17,26,59,98],"machine":[18],"perception.":[19],"Comparable":[20],"problems":[21],"such":[22],"as":[23],"object":[24],"detection":[25],"images":[27],"have":[28],"reaped":[29],"enormous":[30],"benefits":[31],"comprehensive":[33],"datasets":[34],"-":[35],"principally":[36],"ImageNet.":[37],"This":[38],"paper":[39],"describes":[40],"creation":[42],"of":[43,49,73,94,102,126,139],"Set,":[45],"large-scale":[47],"dataset":[48,125],"manually-annotated":[50],"audio":[51,65,75,96,141],"events":[52],"that":[53,131],"endeavors":[54],"bridge":[56],"gap":[58],"data":[60,86],"availability":[61],"between":[62],"image":[63],"research.":[66],"Using":[67],"carefully":[69],"structured":[70],"hierarchical":[71],"ontology":[72],"632":[74],"classes":[76,97],"guided":[77],"by":[78],"literature":[80],"manual":[82],"curation,":[83],"we":[84,133],"collect":[85],"human":[88],"labelers":[89],"probe":[91],"presence":[93],"specific":[95],"10":[99],"second":[100],"segments":[101],"YouTube":[103],"videos.":[104],"Segments":[105],"are":[106],"proposed":[107],"for":[108],"labeling":[109],"using":[110],"searches":[111],"based":[112],"on":[113],"metadata,":[114],"context":[115],"(e.g.,":[116],"links),":[117],"content":[119],"analysis.":[120],"The":[121],"result":[122],"unprecedented":[127],"breadth":[128],"size":[130],"will,":[132],"hope,":[134],"substantially":[135],"stimulate":[136],"development":[138],"high-performance":[140],"recognizers.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":161},{"year":2025,"cited_by_count":465},{"year":2024,"cited_by_count":437},{"year":2023,"cited_by_count":444},{"year":2022,"cited_by_count":388},{"year":2021,"cited_by_count":434},{"year":2020,"cited_by_count":314},{"year":2019,"cited_by_count":216},{"year":2018,"cited_by_count":108},{"year":2017,"cited_by_count":39},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}