{"id":"https://openalex.org/W3015594652","doi":"https://doi.org/10.1109/icassp40776.2020.9054433","title":"Sound Event Detection Via Dilated Convolutional Recurrent Neural Networks","display_name":"Sound Event Detection Via Dilated Convolutional Recurrent Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015594652","doi":"https://doi.org/10.1109/icassp40776.2020.9054433","mag":"3015594652"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":true,"raw_author_name":"Yanxiong Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055957682","display_name":"Mingle Liu","orcid":null},"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":"Mingle Liu","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","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":false,"raw_author_name":"Konstantinos Drossos","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"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":["Audio Research Group, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070863631"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":4.1089,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.9476649,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"286","last_page":"290"},"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":0.996999979019165,"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":0.7184150218963623},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7124705910682678},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5554444193840027},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5446932911872864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4996969699859619},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49624305963516235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4533613622188568},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.41419801115989685},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3851551413536072},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25901633501052856},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0829215943813324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7184150218963623},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7124705910682678},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5554444193840027},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5446932911872864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4996969699859619},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49624305963516235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4533613622188568},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.41419801115989685},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3851551413536072},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25901633501052856},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0829215943813324},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054433","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1576792455","https://openalex.org/W1970578576","https://openalex.org/W2052711563","https://openalex.org/W2065529590","https://openalex.org/W2079735306","https://openalex.org/W2093328288","https://openalex.org/W2103235956","https://openalex.org/W2116681922","https://openalex.org/W2165320399","https://openalex.org/W2341412280","https://openalex.org/W2591013610","https://openalex.org/W2746554716","https://openalex.org/W2895776009","https://openalex.org/W2897371647","https://openalex.org/W2928717951","https://openalex.org/W2963099423","https://openalex.org/W2963840672","https://openalex.org/W2964121744","https://openalex.org/W2964264308","https://openalex.org/W2968134922","https://openalex.org/W2982555889","https://openalex.org/W2997981428","https://openalex.org/W4251033893","https://openalex.org/W6631190155","https://openalex.org/W6636641721","https://openalex.org/W6684354967","https://openalex.org/W6696085341","https://openalex.org/W6772029211"],"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/W2229372569"],"abstract_inverted_index":{"Convolutional":[0],"recurrent":[1],"neural":[2],"networks":[3],"(CRNNs)":[4],"have":[5],"achieved":[6],"state-of-the-art":[7],"performance":[8],"for":[9,35],"sound":[10],"event":[11],"detection":[12],"(SED).":[13],"In":[14],"this":[15],"paper,":[16],"we":[17],"propose":[18],"to":[19,55,68],"use":[20],"a":[21,25,28,49,82,94],"dilated":[22,29,79],"CRNN,":[23,74],"namely":[24],"CRNN":[26,50,80],"with":[27,51],"convolutional":[30],"kernel,":[31],"as":[32],"the":[33,36,42,62,69,72,75,78,107,113,117,123],"classifier":[34,70,76],"task":[37],"of":[38,44,64,71,77,85,97,112],"SED.":[39],"We":[40],"investigate":[41],"effectiveness":[43],"dilation":[45],"operations":[46],"which":[47],"provide":[48],"expanded":[52],"receptive":[53],"fields":[54],"capture":[56],"long":[57],"temporal":[58],"context":[59],"without":[60],"increasing":[61],"amount":[63],"CRNN's":[65],"parameters.":[66],"Compared":[67],"baseline":[73],"obtains":[81],"maximum":[83,95],"increase":[84],"1.9%,":[86],"6.3%":[87],"and":[88,93,100,122],"2.5%":[89],"at":[90,102],"F1":[91],"score":[92],"decrease":[96],"1.7%,":[98],"4.1%":[99],"3.9%":[101],"error":[103],"rate":[104],"(ER),":[105],"on":[106],"publicly":[108],"available":[109],"audio":[110],"corpora":[111],"TUTSED":[114],"Synthetic":[115],"2016,":[116],"TUT":[118,124],"Sound":[119,125],"Event":[120,126],"2016":[121],"2017,":[127],"respectively.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":5}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}