{"id":"https://openalex.org/W2553581788","doi":"https://doi.org/10.1109/ijcnn.2016.7727634","title":"Filterbank learning for deep neural network based polyphonic sound event detection","display_name":"Filterbank learning for deep neural network based polyphonic sound event detection","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2553581788","doi":"https://doi.org/10.1109/ijcnn.2016.7727634","mag":"2553581788"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2016.7727634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5071233423","display_name":"Emre \u00c7ak\u0131r","orcid":"https://orcid.org/0000-0001-8596-8923"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","JP"],"is_corresponding":true,"raw_author_name":"Emre Cakir","raw_affiliation_strings":["Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shenyang, China","Tokyo Institute of Technology, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shenyang, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042211249","display_name":"Ezgi Can Ozan","orcid":null},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ezgi Can Ozan","raw_affiliation_strings":["Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang, China","Oricon Energy Co. Ltd, Tokyo, Japan","Tokyo University"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Oricon Energy Co. Ltd, Tokyo, Japan","institution_ids":[]},{"raw_affiliation_string":"Tokyo University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang, China","Tokyo University"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Shenyang Institute of Automation, Shenyang, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Tokyo University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071233423"],"corresponding_institution_ids":["https://openalex.org/I114531698","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":3.5676,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.93887184,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3399","last_page":"3406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.8199613094329834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8155311346054077},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6155402064323425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6149060726165771},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6091573238372803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5508661866188049},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5260208249092102},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.51178377866745},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4843353033065796},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4663466811180115},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.4573279619216919},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44555899500846863},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4369767904281616},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.41978639364242554},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3374320864677429},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.14737936854362488},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08569970726966858}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.8199613094329834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155311346054077},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6155402064323425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6149060726165771},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6091573238372803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5508661866188049},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5260208249092102},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.51178377866745},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4843353033065796},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4663466811180115},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.4573279619216919},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44555899500846863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4369767904281616},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.41978639364242554},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3374320864677429},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.14737936854362488},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08569970726966858},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2016.7727634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2016.7727634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/213242","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/213242","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1533861849","https://openalex.org/W1542280630","https://openalex.org/W1650531274","https://openalex.org/W1822987211","https://openalex.org/W1846473900","https://openalex.org/W1905843645","https://openalex.org/W1969851134","https://openalex.org/W1972567154","https://openalex.org/W1984541135","https://openalex.org/W1995562189","https://openalex.org/W2006546815","https://openalex.org/W2034215399","https://openalex.org/W2037976268","https://openalex.org/W2046315679","https://openalex.org/W2048174296","https://openalex.org/W2101045344","https://openalex.org/W2103869314","https://openalex.org/W2119110418","https://openalex.org/W2125610452","https://openalex.org/W2137561966","https://openalex.org/W2143036568","https://openalex.org/W2159840028","https://openalex.org/W2160815625","https://openalex.org/W2161969291","https://openalex.org/W2174228052","https://openalex.org/W2200864288","https://openalex.org/W2211849486","https://openalex.org/W2295355370","https://openalex.org/W2312381234","https://openalex.org/W2317919972","https://openalex.org/W2398456099","https://openalex.org/W4231109964","https://openalex.org/W4234947109","https://openalex.org/W4285719527","https://openalex.org/W6629879345","https://openalex.org/W6631943919","https://openalex.org/W6636898527","https://openalex.org/W6685175097","https://openalex.org/W6712469065"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W10861731","https://openalex.org/W2050451745"],"abstract_inverted_index":{"Deep":[0],"learning":[1,69],"techniques":[2],"such":[3,30],"as":[4,31],"deep":[5,10,47,72,88,148],"feedforward":[6],"neural":[7,12,89,150],"networks":[8,13],"and":[9],"convolutional":[11,149],"have":[14],"recently":[15],"been":[16],"shown":[17],"to":[18,27,49,65,91,100,124],"improve":[19],"the":[20,37,44,67,75,83,112,119,127,168],"performance":[21],"in":[22,57],"sound":[23,113,177],"event":[24,114],"detection":[25,115,161],"compared":[26],"traditional":[28],"methods":[29],"Gaussian":[32],"mixture":[33],"models.":[34],"One":[35],"of":[36,40,46,54,71,78,86,103,175],"key":[38],"factors":[39],"this":[41,61,137],"improvement":[42],"is":[43],"capability":[45],"architectures":[48,73],"automatically":[50],"learn":[51,92],"higher":[52],"levels":[53],"acoustic":[55],"features":[56],"each":[58],"layer.":[59],"In":[60],"work,":[62],"we":[63],"aim":[64],"combine":[66],"feature":[68],"capabilities":[70],"with":[74,126,140,159],"empirical":[76],"knowledge":[77],"human":[79],"perception.":[80],"We":[81,117,134],"use":[82],"first":[84,120],"layer":[85,122],"a":[87,93,96,109],"network":[90],"mapping":[94],"from":[95],"high-resolution":[97],"magnitude":[98,132],"spectrum":[99],"smaller":[101],"amount":[102],"frequency":[104],"bands,":[105],"which":[106],"effectively":[107],"learns":[108],"filterbank":[110,131],"for":[111,172],"task.":[116],"initialize":[118],"hidden":[121],"weights":[123],"match":[125],"perceptually":[128],"motivated":[129],"mel":[130],"response.":[133],"also":[135,164],"integrate":[136],"initialization":[138],"scheme":[139],"context":[141],"windowing":[142],"by":[143],"using":[144],"an":[145],"appropriately":[146],"constrained":[147],"network.":[151],"The":[152],"proposed":[153],"method":[154],"does":[155],"not":[156],"only":[157],"result":[158],"better":[160,173],"accuracy,":[162],"but":[163],"provides":[165],"insight":[166],"on":[167],"frequencies":[169],"deemed":[170],"essential":[171],"discrimination":[174],"given":[176],"events.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}