{"id":"https://openalex.org/W3003283641","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207532","title":"Sound Event Detection with Depthwise Separable and Dilated Convolutions","display_name":"Sound Event Detection with Depthwise Separable and Dilated Convolutions","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3003283641","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207532","mag":"3003283641"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.00476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108358814","display_name":"Konstantinos Drossos","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Konstantinos Drossos","raw_affiliation_strings":["Tampere University,Audio Research Group,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Audio Research Group,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044396558","display_name":"Stylianos Ioannis Mimilakis","orcid":"https://orcid.org/0000-0003-4633-5538"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stylianos I. Mimilakis","raw_affiliation_strings":["Fraunhofer-IDMT,Semantic Music Technologies Group,Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer-IDMT,Semantic Music Technologies Group,Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058426639","display_name":"Shayan Gharib","orcid":"https://orcid.org/0009-0000-8010-6320"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Shayan Gharib","raw_affiliation_strings":["Tampere University,Audio Research Group,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Audio Research Group,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070863631","display_name":"Yanxiong Li","orcid":"https://orcid.org/0000-0003-4362-1125"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxiong Li","raw_affiliation_strings":["South China University of Technology,School of Electronic & Information Engineering,Guangzhou,China","South China University of Technology,School of Electronic and Information Engineering,GuangZhou,China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Electronic & Information Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"South China University of Technology,School of Electronic and Information Engineering,GuangZhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"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/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Tampere University,Audio Research Group,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Audio Research Group,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5108358814"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.3043,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51153094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9997000098228455,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8515723943710327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7117050886154175},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6021047830581665},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5630126595497131},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5613260865211487},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5607438683509827},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.557367742061615},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.5176213383674622},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5017805099487305},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.45180076360702515},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4366624057292938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4285367727279663},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38120877742767334},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3794010877609253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19923299551010132}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8515723943710327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117050886154175},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6021047830581665},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5630126595497131},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5613260865211487},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5607438683509827},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.557367742061615},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.5176213383674622},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5017805099487305},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.45180076360702515},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4366624057292938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4285367727279663},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38120877742767334},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3794010877609253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19923299551010132},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207532","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.00476","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00476","pdf_url":"https://arxiv.org/pdf/2002.00476","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:3003283641","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.00476.pdf","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":"pmh:oai:publica.fraunhofer.de:publica/414211","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/414211","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"paper"},{"id":"doi:10.48550/arxiv.2002.00476","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.00476","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.00476","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00476","pdf_url":"https://arxiv.org/pdf/2002.00476","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":[{"id":"https://metadata.un.org/sdg/8","score":0.5899999737739563,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3836581028","display_name":null,"funder_award_id":"75/2-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G4132985236","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G4441379325","display_name":null,"funder_award_id":"MU 2686/11-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6743243744","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7726612598","display_name":null,"funder_award_id":"6/11-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7794680673","display_name":null,"funder_award_id":"AB 675/2-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3003283641.pdf","grobid_xml":"https://content.openalex.org/works/W3003283641.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1610060839","https://openalex.org/W1836465849","https://openalex.org/W2097117768","https://openalex.org/W2116988482","https://openalex.org/W2157331557","https://openalex.org/W2183341477","https://openalex.org/W2510642588","https://openalex.org/W2531409750","https://openalex.org/W2591013610","https://openalex.org/W2593610980","https://openalex.org/W2605646998","https://openalex.org/W2612445135","https://openalex.org/W2621651613","https://openalex.org/W2751116311","https://openalex.org/W2810934215","https://openalex.org/W2897451716","https://openalex.org/W2899579490","https://openalex.org/W2953352227","https://openalex.org/W2959539607","https://openalex.org/W2963162200","https://openalex.org/W2963840672","https://openalex.org/W2964121744","https://openalex.org/W2964206887","https://openalex.org/W2964264308","https://openalex.org/W2966527417","https://openalex.org/W2982070294","https://openalex.org/W2982343573","https://openalex.org/W2982429715","https://openalex.org/W2982549770","https://openalex.org/W2982555889","https://openalex.org/W3015594652","https://openalex.org/W4251033893","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6696085341","https://openalex.org/W6737664043","https://openalex.org/W6738953990","https://openalex.org/W6743647910","https://openalex.org/W6753618346","https://openalex.org/W6755528852"],"related_works":["https://openalex.org/W3091490309","https://openalex.org/W3117580511","https://openalex.org/W2891179104","https://openalex.org/W2897409614","https://openalex.org/W2966296720","https://openalex.org/W2883089954","https://openalex.org/W2755843045","https://openalex.org/W3091692808","https://openalex.org/W2971742398","https://openalex.org/W2907013149","https://openalex.org/W3011862741","https://openalex.org/W2891355459","https://openalex.org/W3080226283","https://openalex.org/W2907719996","https://openalex.org/W2913749182","https://openalex.org/W2949407480","https://openalex.org/W2519373937","https://openalex.org/W2949192817","https://openalex.org/W2529337537","https://openalex.org/W2903041377"],"abstract_inverted_index":{"State-of-the-art":[0],"sound":[1],"event":[2],"detection":[3],"(SED)":[4],"methods":[5],"usually":[6,79],"employ":[7],"a":[8,57,73,148,154,159],"series":[9],"of":[10,41,44,49,53,64,66,75,96,113,126,136,161,164,189],"convolutional":[11,150],"neural":[12,27,151],"networks":[13,28],"(CNNs)":[14],"to":[15,30,72,88,147],"extract":[16],"useful":[17],"features":[18],"from":[19],"the":[20,36,42,45,50,54,61,67,78,94,111,114,124,127,134,137,144,162,179,190],"input":[21,87],"audio":[22],"signal,":[23],"and":[24,47,109,133,157,168,176,187,196],"then":[25],"recurrent":[26],"(RNNs)":[29],"model":[31],"longer":[32],"temporal":[33],"context":[34],"in":[35],"extracted":[37],"features.":[38],"The":[39],"number":[40],"channels":[43],"CNNs":[46,128],"size":[48],"weight":[51],"matrices":[52],"RNNs":[55,138],"have":[56],"direct":[58],"effect":[59],"on":[60,153],"total":[62],"amount":[63,163],"parameters":[65,165],"SED":[68,90,115,155],"method,":[69],"which":[70],"is":[71],"couple":[74],"millions.":[76],"Additionally,":[77],"long":[80],"sequences":[81],"that":[82],"are":[83],"used":[84],"as":[85],"an":[86,89,97,177],"method":[91,146],"along":[92],"with":[93,129,139],"employment":[95],"RNN,":[98],"introduce":[99],"implications":[100],"like":[101],"increased":[102],"training":[103,170],"time,":[104],"difficulty":[105],"at":[106],"gradient":[107],"flow,":[108],"impeding":[110],"parallelization":[112],"method.":[116],"To":[117],"tackle":[118],"all":[119],"these":[120],"problems,":[121],"we":[122],"propose":[123],"replacement":[125,135],"depthwise":[130],"separable":[131],"convolutions":[132],"dilated":[140],"convolutions.":[141],"We":[142],"compare":[143],"proposed":[145],"baseline":[149],"network":[152],"task,":[156],"achieve":[158],"reduction":[160,188],"by":[166,174,194],"85%":[167],"average":[169,180,191],"time":[171],"per":[172],"epoch":[173],"78%,":[175],"increase":[178],"frame-wise":[181],"F":[182],"<sub":[183],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[184],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[185],"score":[186],"error":[192],"rate":[193],"4.6%":[195],"3.8%,":[197],"respectively.":[198]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}