{"id":"https://openalex.org/W3011862741","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023308","title":"Dilated-Gated Convolutional Neural Network with A New Loss Function on Sound Event Detection","display_name":"Dilated-Gated Convolutional Neural Network with A New Loss Function on Sound Event Detection","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011862741","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023308","mag":"3011862741"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5100571521","display_name":"Kexin He","orcid":"https://orcid.org/0009-0009-9722-9613"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ke-Xin He","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625092","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-1415-1195"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100742036","display_name":"Yao Liu","orcid":"https://orcid.org/0000-0001-5342-9896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Liu","raw_affiliation_strings":["China General Technology Research Institute"],"affiliations":[{"raw_affiliation_string":"China General Technology Research Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100571521"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1669,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.49750487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2019","issue":null,"first_page":"1491","last_page":"1495"},"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":0.9994000196456909,"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":0.9908000230789185,"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":0.7866185307502747},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7176625728607178},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6639877557754517},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5713739991188049},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.562854528427124},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5618811845779419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5117623805999756},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.5076593160629272},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4924720227718353},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4664475619792938},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4556174874305725},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4493841528892517},{"id":"https://openalex.org/keywords/alarm","display_name":"ALARM","score":0.4263852834701538},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4198974370956421},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40492862462997437},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07769733667373657},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06409561634063721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7866185307502747},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7176625728607178},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6639877557754517},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5713739991188049},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.562854528427124},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5618811845779419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5117623805999756},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.5076593160629272},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4924720227718353},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4664475619792938},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4556174874305725},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4493841528892517},{"id":"https://openalex.org/C2779119184","wikidata":"https://www.wikidata.org/wiki/Q294350","display_name":"ALARM","level":2,"score":0.4263852834701538},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4198974370956421},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40492862462997437},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07769733667373657},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06409561634063721},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/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/apsipaasc47483.2019.9023308","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023308","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"mag:3041192877","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002287146674685","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1923697677","https://openalex.org/W2065427498","https://openalex.org/W2095705004","https://openalex.org/W2156387975","https://openalex.org/W2194775991","https://openalex.org/W2408239454","https://openalex.org/W2566935005","https://openalex.org/W2591013610","https://openalex.org/W2593610980","https://openalex.org/W2775505379","https://openalex.org/W2804233018","https://openalex.org/W2884561390","https://openalex.org/W2963840672","https://openalex.org/W2964066126","https://openalex.org/W2972922917","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6682889407","https://openalex.org/W6742348326","https://openalex.org/W6747331233"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1584123598","https://openalex.org/W1482209366","https://openalex.org/W2162582511"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,21,40,73],"propose":[4,41],"a":[5,23,42,75],"new":[6,43],"method":[7,88],"for":[8],"rare":[9],"sound":[10],"event":[11],"detection.":[12],"Compared":[13],"with":[14],"conventional":[15],"Convolutional":[16,25],"Recurrent":[17],"Neural":[18,26],"Network":[19,27],"(CRNN),":[20],"devise":[22],"Dilated-Gated":[24],"(DGCNN)":[28],"to":[29,53,63,79,83],"improve":[30],"the":[31,80,92,122],"detection":[32],"accuracy":[33],"as":[34,36],"well":[35],"computational":[37],"efficiency.":[38],"Furthermore,":[39],"loss":[44,81],"function.":[45],"Since":[46],"frame-level":[47],"predictions":[48],"will":[49,61],"be":[50],"post":[51],"processed":[52],"get":[54],"final":[55],"prediction,":[56],"continuous":[57],"false":[58,69],"alarm":[59,70],"frames":[60],"lead":[62],"more":[64],"insertion":[65,85],"errors":[66],"than":[67],"single":[68],"frame.":[71],"So":[72],"adopt":[74],"discriminative":[76],"penalty":[77],"term":[78],"function":[82],"reduce":[84],"errors.":[86],"Our":[87,108],"is":[89],"tested":[90],"on":[91,121],"dataset":[93,124],"of":[94,98,114,119,130,135],"Detection":[95],"and":[96,101,116,132],"Classification":[97],"Acoustic":[99],"Scenes":[100],"Events":[102],"(DCASE)":[103],"2017":[104],"Challenge":[105],"task":[106],"2.":[107],"model":[109],"can":[110],"achieve":[111],"an":[112,128],"F-score":[113,129],"91.3%":[115],"error":[117,133],"rate":[118,134],"0.16":[120],"evaluation":[123],"while":[125],"baseline":[126],"achieves":[127],"87.5%":[131],"0.23.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}