{"id":"https://openalex.org/W3034207266","doi":"https://doi.org/10.1109/taslp.2020.3001683","title":"Adaptive Distance-Based Pooling in Convolutional Neural Networks for Audio Event Classification","display_name":"Adaptive Distance-Based Pooling in Convolutional Neural Networks for Audio Event Classification","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3034207266","doi":"https://doi.org/10.1109/taslp.2020.3001683","mag":"3034207266"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3001683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3001683","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/10550/101191","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041615273","display_name":"Irene Mart\u00edn-Morat\u00f3","orcid":"https://orcid.org/0000-0002-2115-0193"},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Irene Martin-Morato","raw_affiliation_strings":["Departament d\u2019Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain","Departament d'Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departament d\u2019Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain","institution_ids":["https://openalex.org/I16097986"]},{"raw_affiliation_string":"Departament d'Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089104482","display_name":"M\u00e1ximo Cobos","orcid":"https://orcid.org/0000-0001-7318-3192"},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Maximo Cobos","raw_affiliation_strings":["Departament d\u2019Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain","Departament d'Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departament d\u2019Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain","institution_ids":["https://openalex.org/I16097986"]},{"raw_affiliation_string":"Departament d'Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain","institution_ids":["https://openalex.org/I16097986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067408837","display_name":"Francesc J. Ferri","orcid":"https://orcid.org/0000-0002-1543-3568"},"institutions":[{"id":"https://openalex.org/I16097986","display_name":"Universitat de Val\u00e8ncia","ror":"https://ror.org/043nxc105","country_code":"ES","type":"education","lineage":["https://openalex.org/I16097986"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francesc. J Ferri","raw_affiliation_strings":["Departament d\u2019Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain","Departament d'Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departament d\u2019Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain","institution_ids":["https://openalex.org/I16097986"]},{"raw_affiliation_string":"Departament d'Inform\u00e0tica, Universitat de Val\u00e8ncia, Burjassot, Spain","institution_ids":["https://openalex.org/I16097986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16097986"],"apc_list":null,"apc_paid":null,"fwci":1.2165,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79159872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"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":0.9986000061035156,"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":0.9807000160217285,"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":0.8354412913322449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7569568753242493},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6736186742782593},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6267514824867249},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6258162260055542},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6075130701065063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5601965188980103},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5162094235420227},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.49686291813850403},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.4901066720485687},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4778304100036621},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.47413894534111023},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3818510174751282},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3363012671470642},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11112761497497559}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8354412913322449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569568753242493},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6736186742782593},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6267514824867249},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258162260055542},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6075130701065063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5601965188980103},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5162094235420227},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.49686291813850403},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.4901066720485687},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4778304100036621},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.47413894534111023},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3818510174751282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3363012671470642},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11112761497497559},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2020.3001683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3001683","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:roderic.uv.es:10550/101191","is_oa":true,"landing_page_url":"https://hdl.handle.net/10550/101191","pdf_url":null,"source":{"id":"https://openalex.org/S4306400245","display_name":"Repository of Digital Objects for Teaching Research and Culture (University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I16097986","host_organization_name":"Universitat de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I16097986"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mart\u00edn Morat\u00f3, Irene Cobos Serrano, M\u00e1ximo Ferri Rabasa, Francesc Josep 2020 Adaptive Distance-Based Pooling in Convolutional Neural Networks for Audio Event Classification Ieee-Acm Transactions On Audio Speech And Language Processing 28 6 1925 1935","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:roderic.uv.es:10550/101191","is_oa":true,"landing_page_url":"https://hdl.handle.net/10550/101191","pdf_url":null,"source":{"id":"https://openalex.org/S4306400245","display_name":"Repository of Digital Objects for Teaching Research and Culture (University of Valencia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I16097986","host_organization_name":"Universitat de Val\u00e8ncia","host_organization_lineage":["https://openalex.org/I16097986"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mart\u00edn Morat\u00f3, Irene Cobos Serrano, M\u00e1ximo Ferri Rabasa, Francesc Josep 2020 Adaptive Distance-Based Pooling in Convolutional Neural Networks for Audio Event Classification Ieee-Acm Transactions On Audio Speech And Language Processing 28 6 1925 1935","raw_type":"journal article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G106482465","display_name":null,"funder_award_id":"TIN2014-59641-C2-1-P","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G1379709309","display_name":null,"funder_award_id":"RTI2018-097045-B-C21","funder_id":"https://openalex.org/F4320315062","funder_display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades"},{"id":"https://openalex.org/G2653881781","display_name":null,"funder_award_id":"BIA2016-76957-C3-1-R","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G4182827893","display_name":null,"funder_award_id":"FPU14/06329","funder_id":"https://openalex.org/F4320321764","funder_display_name":"Ministerio de Educaci\u00f3n, Cultura y Deporte"}],"funders":[{"id":"https://openalex.org/F4320315062","display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","ror":null},{"id":"https://openalex.org/F4320321764","display_name":"Ministerio de Educaci\u00f3n, Cultura y Deporte","ror":"https://ror.org/03nc27g21"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1522301498","https://openalex.org/W1972567154","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2059652044","https://openalex.org/W2064675550","https://openalex.org/W2076608692","https://openalex.org/W2163605009","https://openalex.org/W2165698076","https://openalex.org/W2169284845","https://openalex.org/W2354870669","https://openalex.org/W2398826216","https://openalex.org/W2408093180","https://openalex.org/W2471278348","https://openalex.org/W2509065397","https://openalex.org/W2549826128","https://openalex.org/W2565911560","https://openalex.org/W2593116425","https://openalex.org/W2593451766","https://openalex.org/W2618530766","https://openalex.org/W2619697695","https://openalex.org/W2771361008","https://openalex.org/W2772293448","https://openalex.org/W2773767104","https://openalex.org/W2775019026","https://openalex.org/W2775794021","https://openalex.org/W2798579254","https://openalex.org/W2799258971","https://openalex.org/W2799768828","https://openalex.org/W2888469011","https://openalex.org/W2889495646","https://openalex.org/W2919559219","https://openalex.org/W2955149661","https://openalex.org/W2962756039","https://openalex.org/W2963022469","https://openalex.org/W2963158330","https://openalex.org/W2963517948","https://openalex.org/W2963859210","https://openalex.org/W2963911037","https://openalex.org/W2964121744","https://openalex.org/W2964891022","https://openalex.org/W3027937556","https://openalex.org/W3098357269","https://openalex.org/W3103314642","https://openalex.org/W3123416659","https://openalex.org/W6631190155","https://openalex.org/W6638444622","https://openalex.org/W6729831399","https://openalex.org/W6746683323","https://openalex.org/W6765607314"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W4401096132","https://openalex.org/W2965782936"],"abstract_inverted_index":{"In":[0,92],"the":[1,13,21,52,70,73,117,122,141,156],"last":[2],"years,":[3],"deep":[4],"convolutional":[5,118],"neural":[6],"networks":[7],"have":[8],"become":[9],"a":[10,97,129,135],"standard":[11],"for":[12],"development":[14],"of":[15,34,72,100,108,116],"state-of-the-art":[16],"audio":[17,109],"classification":[18],"systems,":[19],"taking":[20],"lead":[22],"over":[23,56,148],"traditional":[24],"approaches":[25],"based":[26],"on":[27,140],"feature":[28,119,143],"engineering.":[29],"While":[30],"they":[31],"are":[32,54],"capable":[33],"achieving":[35],"human":[36],"performance":[37,153],"under":[38],"certain":[39],"scenarios,":[40],"it":[41],"has":[42],"been":[43],"shown":[44],"that":[45,133,167],"their":[46],"accuracy":[47],"is":[48,159],"severely":[49],"degraded":[50],"when":[51,155],"systems":[53,166],"tested":[55],"noisy":[57],"or":[58],"weakly":[59,179],"segmented":[60],"events.":[61],"Although":[62],"better":[63,169],"generalization":[64],"could":[65],"be":[66],"obtained":[67],"by":[68,77,111],"increasing":[69],"size":[71],"training":[74,90],"dataset,":[75],"e.g.":[76],"applying":[78,112],"data":[79],"augmentation":[80],"techniques,":[81],"this":[82,93],"also":[83],"leads":[84],"to":[85,161,170],"longer":[86],"and":[87,174],"more":[88,176],"complex":[89],"procedures.":[91],"article,":[94],"we":[95],"propose":[96],"new":[98],"type":[99],"pooling":[101],"layer":[102,127,158],"aimed":[103],"at":[104],"compensating":[105],"non-relevant":[106],"information":[107],"events":[110],"an":[113],"adaptive":[114],"transformation":[115,132],"maps":[120],"in":[121,165],"temporal":[123,131],"axis.":[124],"The":[125,145],"proposed":[126,157],"performs":[128],"non-linear":[130],"follows":[134],"uniform":[136],"distance":[137],"subsampling":[138],"criterion":[139],"learned":[142],"space.":[144],"experiments":[146],"conducted":[147],"different":[149],"datasets":[150],"show":[151],"significant":[152],"improvements":[154],"added":[160],"baseline":[162],"models,":[163],"resulting":[164],"generalize":[168],"mismatching":[171],"test":[172],"conditions":[173],"learn":[175],"robustly":[177],"from":[178],"labeled":[180],"data.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}