{"id":"https://openalex.org/W2963610932","doi":"https://doi.org/10.1109/icassp.2019.8682847","title":"A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling","display_name":"A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2963610932","doi":"https://doi.org/10.1109/icassp.2019.8682847","mag":"2963610932"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[{"id":"https://openalex.org/I4210120115","display_name":"Robert Bosch (United States)","ror":"https://ror.org/02venad53","country_code":"US","type":"company","lineage":["https://openalex.org/I4210120115","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I4210127226","display_name":"Robert Bosch (Slovenia)","ror":"https://ror.org/03248dr08","country_code":"SI","type":"company","lineage":["https://openalex.org/I4210127226","https://openalex.org/I889804353"]}],"countries":["SI","US"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Research and Technology Center, Robert Bosch LLC, Pittsburgh, PA, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Technology Center, Robert Bosch LLC, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I4210120115","https://openalex.org/I4210127226"]}]},{"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":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.6443,"has_fulltext":false,"cited_by_count":160,"citation_normalized_percentile":{"value":0.99770671,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"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":0.9908999800682068,"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":0.9606000185012817,"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/pooling","display_name":"Pooling","score":0.9265205264091492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6941309571266174},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6369674801826477},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5588414669036865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5073868632316589},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4899114966392517},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4778677821159363},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.428849995136261},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4155704081058502},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41304636001586914},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4064498543739319},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3751574754714966},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34436267614364624}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9265205264091492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6941309571266174},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6369674801826477},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5588414669036865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5073868632316589},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4899114966392517},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4778677821159363},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.428849995136261},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4155704081058502},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41304636001586914},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4064498543739319},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3751574754714966},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34436267614364624},{"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/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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1846473900","https://openalex.org/W2010792435","https://openalex.org/W2043701535","https://openalex.org/W2154318594","https://openalex.org/W2166010828","https://openalex.org/W2337904331","https://openalex.org/W2341412280","https://openalex.org/W2354870669","https://openalex.org/W2407005679","https://openalex.org/W2408239454","https://openalex.org/W2526050071","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2622742434","https://openalex.org/W2654517624","https://openalex.org/W2775505379","https://openalex.org/W2791956393","https://openalex.org/W2798579254","https://openalex.org/W2799258971","https://openalex.org/W2807788374","https://openalex.org/W2807977755","https://openalex.org/W2899771611","https://openalex.org/W2962910554","https://openalex.org/W2963022469","https://openalex.org/W2963438834","https://openalex.org/W2963679447","https://openalex.org/W2963723765","https://openalex.org/W3103314642","https://openalex.org/W6638667902","https://openalex.org/W6683033130","https://openalex.org/W6684369376","https://openalex.org/W6704028418","https://openalex.org/W6739564277","https://openalex.org/W6747331233","https://openalex.org/W6749158954","https://openalex.org/W6750883802","https://openalex.org/W6756040250","https://openalex.org/W6884739491","https://openalex.org/W6941349294"],"related_works":["https://openalex.org/W3134502938","https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686","https://openalex.org/W2371215329"],"abstract_inverted_index":{"Sound":[0],"event":[1],"detection":[2],"(SED)":[3],"entails":[4],"two":[5],"subtasks:":[6],"recognizing":[7],"what":[8],"types":[9,53],"of":[10,54,67],"sound":[11],"events":[12],"are":[13],"present":[14],"in":[15],"an":[16,42],"audio":[17,113],"stream":[18],"(audio":[19],"tagging),":[20],"and":[21,25,59],"pinpointing":[22],"their":[23,65],"onset":[24],"offset":[26],"times":[27],"(localization).":[28],"In":[29],"the":[30,46,70,77,82,89,92,107,125,130],"popular":[31],"multiple":[32],"instance":[33],"learning":[34],"(MIL)":[35],"framework":[36],"for":[37],"SED":[38],"with":[39,61],"weak":[40],"labeling,":[41],"important":[43],"component":[44],"is":[45,74,106],"pooling":[47,55,72,85,96],"function.":[48],"This":[49],"paper":[50],"compares":[51],"five":[52],"functions":[56],"both":[57],"theoretically":[58],"experimentally,":[60],"special":[62],"focus":[63],"on":[64,116,124],"performance":[66,115,123],"localization.":[68],"Although":[69],"attention":[71],"function":[73,86],"currently":[75],"receiving":[76],"most":[78],"attention,":[79],"we":[80,98],"find":[81],"linear":[83],"softmax":[84],"to":[87,110],"perform":[88],"best":[90],"among":[91],"five.":[93],"Using":[94],"this":[95],"function,":[97],"build":[99],"a":[100],"neural":[101],"network":[102],"called":[103],"TALNet.":[104],"It":[105],"first":[108],"system":[109],"reach":[111],"state-of-the-art":[112],"tagging":[114],"Audio":[117],"Set,":[118],"while":[119],"exhibiting":[120],"strong":[121],"localization":[122],"DCASE":[126],"2017":[127],"challenge":[128],"at":[129],"same":[131],"time.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":28},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":33},{"year":2019,"cited_by_count":11}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}