{"id":"https://openalex.org/W3161435013","doi":"https://doi.org/10.1109/icassp39728.2021.9414579","title":"The Benefit of Temporally-Strong Labels in Audio Event Classification","display_name":"The Benefit of Temporally-Strong Labels in Audio Event Classification","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161435013","doi":"https://doi.org/10.1109/icassp39728.2021.9414579","mag":"3161435013"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2105.07031","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014428891","display_name":"Shawn Hershey","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":"Shawn Hershey","raw_affiliation_strings":["Google Research,New York, NY, and Mountain View,CA,USA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,New York, NY, and Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","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 Research,New York, NY, and Mountain View,CA,USA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,New York, NY, and Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025025113","display_name":"Eduardo Fonseca","orcid":"https://orcid.org/0000-0001-9872-3917"},"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":"Eduardo Fonseca","raw_affiliation_strings":["Google Research,New York, NY, and Mountain View,CA,USA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,New York, NY, and Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","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 Research,New York, NY, and Mountain View,CA,USA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,New York, NY, and Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036544739","display_name":"Caroline Liu","orcid":"https://orcid.org/0000-0002-6684-026X"},"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":"Caroline Liu","raw_affiliation_strings":["Google Research,New York, NY, and Mountain View,CA,USA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,New York, NY, and Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","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 Research,New York, NY, and Mountain View,CA,USA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,New York, NY, and Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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 Research,New York, NY, and Mountain View,CA,USA","Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,New York, NY, and Mountain View,CA,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","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":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"370"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9933000206947327,"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":0.6924624443054199},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6763026118278503},{"id":"https://openalex.org/keywords/clips","display_name":"CLIPS","score":0.6615187525749207},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5779364705085754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5556222200393677},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5013132095336914},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.47171539068222046},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4225904941558838},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4104839563369751},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37459540367126465},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33348459005355835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924624443054199},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6763026118278503},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.6615187525749207},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5779364705085754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5556222200393677},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5013132095336914},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.47171539068222046},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4225904941558838},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4104839563369751},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37459540367126465},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33348459005355835},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414579","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.07031","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.07031","pdf_url":"https://arxiv.org/pdf/2105.07031","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:3161435013","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2105.07031","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.2105.07031","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.07031","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":"Preprint"},{"id":"doi:10.17023/h66r-3e78","is_oa":true,"landing_page_url":"https://doi.org/10.17023/h66r-3e78","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.07031","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.07031","pdf_url":"https://arxiv.org/pdf/2105.07031","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":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3161435013.pdf","grobid_xml":"https://content.openalex.org/works/W3161435013.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W92486268","https://openalex.org/W2038484192","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2565911560","https://openalex.org/W2566935005","https://openalex.org/W2577784528","https://openalex.org/W2593116425","https://openalex.org/W2769956639","https://openalex.org/W2771361008","https://openalex.org/W2774116887","https://openalex.org/W2775505379","https://openalex.org/W2775794021","https://openalex.org/W2799258971","https://openalex.org/W2959539607","https://openalex.org/W2962843773","https://openalex.org/W2963859210","https://openalex.org/W2973109987","https://openalex.org/W2982343573","https://openalex.org/W3005033663","https://openalex.org/W3021910945","https://openalex.org/W3094550259","https://openalex.org/W6603835122","https://openalex.org/W6745978776","https://openalex.org/W6747331233"],"related_works":["https://openalex.org/W3162999565","https://openalex.org/W2763971240","https://openalex.org/W3183597915","https://openalex.org/W3040821547","https://openalex.org/W877541198","https://openalex.org/W3108321527","https://openalex.org/W3016038135","https://openalex.org/W2982382559","https://openalex.org/W2055601365","https://openalex.org/W2982610913","https://openalex.org/W3195675201","https://openalex.org/W2912406944","https://openalex.org/W2142189353","https://openalex.org/W3015321085","https://openalex.org/W2809117326","https://openalex.org/W6869908","https://openalex.org/W3046001438","https://openalex.org/W3176463436","https://openalex.org/W3120689745","https://openalex.org/W3000940430"],"abstract_inverted_index":{"To":[0],"reveal":[1],"the":[2,25,51,83,93],"importance":[3],"of":[4,24,37,46,68],"temporal":[5],"precision":[6],"in":[7],"ground":[8],"truth":[9],"audio":[10],"event":[11],"labels,":[12],"we":[13],"collected":[14],"precise":[15],"(\u223c0.1":[16],"sec":[17,59],"resolution)":[18],"\"strong\"":[19],"labels":[20,107],"for":[21],"a":[22,30,41,66,88],"portion":[23],"AudioSet":[26],"dataset.":[27],"We":[28,61],"devised":[29],"temporally-strong":[31],"evaluation":[32,95],"set":[33],"(including":[34],"explicit":[35,98],"negatives":[36,99],"varying":[38],"difficulty)":[39],"and":[40,70],"small":[42],"strong-labeled":[43],"training":[44],"subset":[45],"67k":[47],"clips":[48,55],"(compared":[49],"to":[50,103,113],"original":[52,84],"dataset\u2019s":[53],"1.8M":[54],"labeled":[56],"at":[57],"10":[58],"resolution).":[60],"show":[62],"that":[63],"fine-tuning":[64],"with":[65],"mix":[67],"weak-":[69],"strongly-labeled":[71],"data":[72,96],"can":[73],"substantially":[74],"improve":[75],"classifier":[76],"performance,":[77],"even":[78],"when":[79],"evaluated":[80],"using":[81],"only":[82],"weak":[85],"labels.":[86],"For":[87],"ResNet-50":[89],"architecture,":[90],"d\u2032":[91],"on":[92],"strong":[94],"including":[97],"improves":[100],"from":[101],"1.13":[102],"1.39.":[104],"The":[105],"new":[106],"are":[108],"available":[109],"as":[110],"an":[111],"update":[112],"AudioSet.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}