{"id":"https://openalex.org/W2964066126","doi":"https://doi.org/10.21437/interspeech.2018-2323","title":"R-CRNN: Region-based Convolutional Recurrent Neural Network for Audio Event Detection","display_name":"R-CRNN: Region-based Convolutional Recurrent Neural Network for Audio Event Detection","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2964066126","doi":"https://doi.org/10.21437/interspeech.2018-2323","mag":"2964066126"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2323","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","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/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chieh-Chi Kao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiran Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407035","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-7427-793X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020775828"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.22437918,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.97626782,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1358","last_page":"1362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.972599983215332,"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":0.7743693590164185},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5904683470726013},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5888249278068542},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5671889781951904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38445234298706055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3667213022708893},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2602776288986206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7743693590164185},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5904683470726013},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5888249278068542},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5671889781951904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38445234298706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3667213022708893},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2602776288986206},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-2323","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2086384421","https://openalex.org/W2097450352","https://openalex.org/W2117539524","https://openalex.org/W2144506857","https://openalex.org/W2183644544","https://openalex.org/W2194775991","https://openalex.org/W2292996718","https://openalex.org/W2398932003","https://openalex.org/W2408239454","https://openalex.org/W2566935005","https://openalex.org/W2743672024","https://openalex.org/W2775505379"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W1889624880","https://openalex.org/W2578422401"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,22,36,83,101],"Region-based":[4],"Convolutional":[5],"Recurrent":[6],"Neural":[7],"Network":[8],"(R-CRNN)":[9],"for":[10,28,153],"audio":[11,111],"event":[12,92],"detection":[13],"(AED).The":[14],"proposed":[15,87,114],"network":[16,26,46,152],"is":[17,39,116,130],"inspired":[18],"by":[19],"Faster-RCNN":[20],"[1],":[21],"wellknown":[23],"region-based":[24,151],"convolutional":[25,45],"framework":[27],"visual":[29],"object":[30],"detection.Different":[31],"from":[32,53,82],"the":[33,44,49,54,60,77,86,106,124,131,149,166,172],"original":[34],"Faster-RCNN,":[35],"recurrent":[37],"layer":[38],"added":[40],"on":[41,63,118,143,165],"top":[42],"of":[43,59,80,110,126,163],"to":[47,75,148,174],"capture":[48],"long-term":[50],"temporal":[51],"context":[52],"extracted":[55],"highlevel":[56],"features.While":[57],"most":[58],"previous":[61],"works":[62],"AED":[64,154],"generate":[65],"predictions":[66,90],"at":[67,91],"frame":[68],"level":[69,93],"first,":[70],"and":[71,95,108,145],"then":[72],"use":[73],"post-processing":[74],"predict":[76],"onset/offset":[78],"timestamps":[79],"events":[81,112],"probability":[84],"sequence;":[85],"method":[88,115,135,170],"generates":[89],"directly":[94],"can":[96],"be":[97],"trained":[98],"end-to-end":[99],"with":[100,157],"multitask":[102],"loss,":[103],"which":[104],"optimizes":[105],"classification":[107],"localization":[109],"simultaneously.The":[113],"tested":[117],"DCASE":[119],"2017":[120],"Challenge":[121],"dataset":[122],"[2].To":[123],"best":[125,132],"our":[127,169],"knowledge,":[128],"R-CRNN":[129],"performing":[133],"single-model":[134],"among":[136],"all":[137],"methods":[138],"without":[139],"using":[140],"ensembles":[141],"both":[142],"development":[144,167],"evaluation":[146],"sets.Compared":[147],"other":[150],"(R-FCN":[155],"[3])":[156],"an":[158],"event-based":[159],"error":[160],"rate":[161],"(ER)":[162],"0.18":[164],"set,":[168],"reduced":[171],"ER":[173],"half.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":1}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}