{"id":"https://openalex.org/W4286507093","doi":"https://doi.org/10.1109/cits55221.2022.9832991","title":"A Deep Learning Based Sound Event Location and Detection Algorithm Using Convolutional Recurrent Neural Network","display_name":"A Deep Learning Based Sound Event Location and Detection Algorithm Using Convolutional Recurrent Neural Network","publication_year":2022,"publication_date":"2022-07-13","ids":{"openalex":"https://openalex.org/W4286507093","doi":"https://doi.org/10.1109/cits55221.2022.9832991"},"language":"en","primary_location":{"id":"doi:10.1109/cits55221.2022.9832991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cits55221.2022.9832991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Computer, Information and Telecommunication Systems (CITS)","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/A5100568585","display_name":"Hongxiang Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongxiang Zhu","raw_affiliation_strings":["Nanjing University of Posts & Telecommunications,College of Communication & Information Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts & Telecommunications,College of Communication & Information Engineering,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101543711","display_name":"Jun Yan","orcid":"https://orcid.org/0000-0002-9434-1388"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yan","raw_affiliation_strings":["Nanjing University of Posts & Telecommunications,College of Communication & Information Engineering,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts & Telecommunications,College of Communication & Information Engineering,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100568585"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.8915,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71742795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9860000014305115,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.801167368888855},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6122320294380188},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6080935001373291},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5379742980003357},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5339371562004089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.501776933670044},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4971020519733429},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4775334596633911},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4699934422969818},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4597814679145813},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.443377286195755},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4176488220691681},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3321225345134735},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32312706112861633},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15507400035858154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.801167368888855},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6122320294380188},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6080935001373291},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5379742980003357},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5339371562004089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.501776933670044},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4971020519733429},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4775334596633911},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4699934422969818},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4597814679145813},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.443377286195755},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4176488220691681},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3321225345134735},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32312706112861633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15507400035858154},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cits55221.2022.9832991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cits55221.2022.9832991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Computer, Information and Telecommunication Systems (CITS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1501987291","https://openalex.org/W1533561824","https://openalex.org/W1603075283","https://openalex.org/W2037684811","https://openalex.org/W2062164080","https://openalex.org/W2113638573","https://openalex.org/W2113744809","https://openalex.org/W2341412280","https://openalex.org/W2470628481","https://openalex.org/W2810934215","https://openalex.org/W2963091558","https://openalex.org/W3204744130","https://openalex.org/W3215241116","https://openalex.org/W4244779849","https://openalex.org/W6632323398","https://openalex.org/W6650618909","https://openalex.org/W6720377305","https://openalex.org/W6804528392"],"related_works":["https://openalex.org/W2963891724","https://openalex.org/W3093612317","https://openalex.org/W2175746458","https://openalex.org/W2732542196","https://openalex.org/W2760085659","https://openalex.org/W2883200793","https://openalex.org/W2738221750","https://openalex.org/W3012978760","https://openalex.org/W2912288872","https://openalex.org/W2940661641"],"abstract_inverted_index":{"With":[0],"the":[1,44,61,67,90,104,133],"application":[2],"of":[3,63,66,83],"sound":[4,14,30,114,117],"event":[5,15,31],"detection":[6,18,34],"in":[7],"more":[8,10],"and":[9,17,33,78,86,116,125,137,143],"fields,":[11],"an":[12],"accurate":[13,140],"location":[16,32,144],"system":[19],"has":[20],"attracted":[21],"wide":[22],"attention.":[23],"In":[24,43],"this":[25],"paper,":[26],"we":[27,72],"propose":[28],"a":[29,109],"algorithm":[35,56,134],"based":[36],"on":[37],"convolutional":[38],"recurrent":[39],"neural":[40],"network":[41],"(CRNN).":[42],"offline":[45],"phase,":[46],"complete":[47],"ensemble":[48],"empirical":[49],"mode":[50],"decomposition":[51],"with":[52,98],"adaptive":[53],"noise":[54,62],"(CEEMDAN)":[55],"is":[57,108,120,135],"used":[58],"to":[59,94,102],"remove":[60],"unknown":[64],"distribution":[65],"collected":[68],"data":[69],"set.":[70],"Then,":[71],"extract":[73],"filter":[74],"banks":[75],"(FBANK)":[76],"features":[77,82,91],"cross":[79],"correlation":[80],"(GCC)":[81],"each":[84],"channel":[85],"fuse":[87],"them.":[88],"Finally,":[89],"are":[92],"input":[93],"CRNN":[95,107],"which":[96],"combined":[97],"soft":[99],"attention":[100],"mechanism":[101],"train":[103],"model.":[105],"The":[106],"multi-task":[110],"learning":[111],"framework.":[112],"For":[113],"category":[115,141],"location,":[118],"it":[119],"realized":[121],"by":[122],"classification":[123],"task":[124,127],"regression":[126],"respectively.":[128],"Experimental":[129],"results":[130],"show":[131],"that":[132],"effective":[136],"can":[138],"provide":[139],"estimation":[142],"estimation.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}