{"id":"https://openalex.org/W3016081131","doi":"https://doi.org/10.1109/icassp40776.2020.9053613","title":"SeCoST:: Sequential Co-Supervision for Large Scale Weakly Labeled Audio Event Detection","display_name":"SeCoST:: Sequential Co-Supervision for Large Scale Weakly Labeled Audio Event Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016081131","doi":"https://doi.org/10.1109/icassp40776.2020.9053613","mag":"3016081131"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.11789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Facebook Reality Labs, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108520440","display_name":"Vamsi Krishna Ithapu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vamsi Krishna Ithapu","raw_affiliation_strings":["Facebook Reality Labs, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080751032"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":0.9143,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73434535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"70","issue":null,"first_page":"666","last_page":"670"},"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":0.9983999729156494,"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":0.9699000120162964,"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":0.7801889181137085},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7141448855400085},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6320785284042358},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6183887124061584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5492576956748962},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5415826439857483},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.45702171325683594},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4519268870353699},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.43432095646858215},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4207383394241333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36147284507751465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33183807134628296},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09435227513313293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801889181137085},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7141448855400085},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6320785284042358},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6183887124061584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5492576956748962},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5415826439857483},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.45702171325683594},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4519268870353699},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.43432095646858215},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4207383394241333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36147284507751465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33183807134628296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09435227513313293},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.11789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11789","pdf_url":"https://arxiv.org/pdf/1910.11789","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.11789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11789","pdf_url":"https://arxiv.org/pdf/1910.11789","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1521843029","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W1825507529","https://openalex.org/W1970578576","https://openalex.org/W1972567154","https://openalex.org/W2086384421","https://openalex.org/W2109244020","https://openalex.org/W2120501001","https://openalex.org/W2122040390","https://openalex.org/W2133564696","https://openalex.org/W2134797427","https://openalex.org/W2294370754","https://openalex.org/W2354870669","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2759976799","https://openalex.org/W2763971240","https://openalex.org/W2788388592","https://openalex.org/W2791956393","https://openalex.org/W2798579254","https://openalex.org/W2799258971","https://openalex.org/W2803023299","https://openalex.org/W2807788374","https://openalex.org/W2899771611","https://openalex.org/W2962910554","https://openalex.org/W2963610932","https://openalex.org/W2963859210","https://openalex.org/W2964121744","https://openalex.org/W2964222566","https://openalex.org/W2964308564","https://openalex.org/W2964891022","https://openalex.org/W2965036688","https://openalex.org/W3103314642","https://openalex.org/W3123416659","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6677850982","https://openalex.org/W6679434410","https://openalex.org/W6679909955","https://openalex.org/W6745117180","https://openalex.org/W6749158954","https://openalex.org/W6750883802","https://openalex.org/W6751751081","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W4388870064","https://openalex.org/W2392921965","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2358755282","https://openalex.org/W2054685365"],"abstract_inverted_index":{"Weakly":[0],"supervised":[1],"learning":[2,18,59,69],"algorithms":[3],"are":[4],"critical":[5],"for":[6,57,86],"scaling":[7],"audio":[8],"event":[9],"detection":[10],"to":[11,35,75],"several":[12],"hundreds":[13],"of":[14,46,89,96,123,129],"sound":[15,24],"categories.":[16],"Such":[17],"models":[19,60],"should":[20],"not":[21],"only":[22],"disambiguate":[23],"events":[25],"efficiently":[26],"with":[27,42,61],"minimal":[28],"class-specific":[29],"annotation":[30],"but":[31],"also":[32],"be":[33],"robust":[34],"label":[36],"noise,":[37],"which":[38],"is":[39],"more":[40],"apparent":[41],"weak":[43,62],"labels":[44],"instead":[45],"strong":[47],"annotations.":[48],"In":[49],"this":[50],"work,":[51],"we":[52],"propose":[53],"a":[54,94,100,119,133],"new":[55],"framework":[56],"designing":[58],"supervision":[63],"by":[64,132],"bridging":[65],"ideas":[66],"from":[67],"sequential":[68],"and":[70],"knowledge":[71,102],"distillation.":[72],"We":[73],"refer":[74],"the":[76,130],"proposed":[77],"methodology":[78],"as":[79],"SeCoST":[80,91,117],"(pronounced":[81],"Sequest)":[82],"\u2014":[83],"Sequential":[84],"Co-supervision":[85],"training":[87],"generations":[88],"Students.":[90],"incrementally":[92],"builds":[93],"cascade":[95],"student-teacher":[97],"pairs":[98],"via":[99],"novel":[101],"transfer":[103],"method.":[104],"Our":[105],"evaluations":[106],"on":[107],"Audioset":[108],"(the":[109],"largest":[110],"weakly":[111],"labeled":[112],"dataset":[113],"available)":[114],"show":[115],"that":[116],"achieves":[118],"mean":[120],"average":[121],"precision":[122],"0.383":[124],"while":[125],"outperforming":[126],"prior":[127],"state":[128],"art":[131],"considerable":[134],"margin.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}