{"id":"https://openalex.org/W3008335638","doi":"https://doi.org/10.1109/isspit47144.2019.9001843","title":"Noise Robust Sound Event Detection Using Deep Learning and Audio Enhancement","display_name":"Noise Robust Sound Event Detection Using Deep Learning and Audio Enhancement","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008335638","doi":"https://doi.org/10.1109/isspit47144.2019.9001843","mag":"3008335638"},"language":"en","primary_location":{"id":"doi:10.1109/isspit47144.2019.9001843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit47144.2019.9001843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","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/A5059992409","display_name":"Tongtang Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tongtang Wan","raw_affiliation_strings":["School of communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005083930","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0001-7445-226X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["School of communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102289086","display_name":"Yongbao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongbao Ma","raw_affiliation_strings":["Suresense Technology Co. Ltd., Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Suresense Technology Co. Ltd., Chongqing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102001094","display_name":"Hongqing Liu","orcid":"https://orcid.org/0000-0002-2069-0390"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongqing Liu","raw_affiliation_strings":["School of communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059992409"],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":1.1689,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80379747,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9764000177383423,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7962936162948608},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7352346777915955},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6170192360877991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6046157479286194},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6031123399734497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5367720127105713},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5216922163963318},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5134092569351196},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4855325222015381},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4618239998817444},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4559614360332489},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43101412057876587},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4224834740161896},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.42003703117370605},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4131353795528412},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40696004033088684},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15519246459007263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962936162948608},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7352346777915955},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6170192360877991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6046157479286194},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6031123399734497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367720127105713},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5216922163963318},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5134092569351196},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4855325222015381},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4618239998817444},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4559614360332489},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43101412057876587},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4224834740161896},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.42003703117370605},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4131353795528412},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40696004033088684},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15519246459007263},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isspit47144.2019.9001843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit47144.2019.9001843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","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":22,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1533561824","https://openalex.org/W1565317727","https://openalex.org/W1650531274","https://openalex.org/W1970578576","https://openalex.org/W2011869890","https://openalex.org/W2034940213","https://openalex.org/W2038509404","https://openalex.org/W2042593695","https://openalex.org/W2099454382","https://openalex.org/W2105995102","https://openalex.org/W2126942983","https://openalex.org/W2327970305","https://openalex.org/W2618269622","https://openalex.org/W2734691436","https://openalex.org/W2750162257","https://openalex.org/W2883135409","https://openalex.org/W2898801886","https://openalex.org/W2973152780","https://openalex.org/W6628904230","https://openalex.org/W6632323398","https://openalex.org/W6633780720"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2088690926","https://openalex.org/W2098934641"],"abstract_inverted_index":{"Sound":[0],"event":[1],"detection":[2,19],"(SED)":[3],"aims":[4],"to":[5,40,85,107,148],"identify":[6],"the":[7,10,14,41,47,62,87,90,109,112,116,132,144,149],"types":[8],"and":[9,31,46,68,93,135],"temporal":[11],"boundaries":[12],"of":[13,20,49,64,89,111],"target":[15],"sound":[16,22,50],"events.":[17,51],"Successful":[18],"various":[21],"events":[23],"can":[24],"reveal":[25],"rich":[26],"information":[27],"in":[28,129,131,141,143],"many":[29],"home":[30],"surveillance":[32],"applications.":[33],"However,":[34],"this":[35,53],"task":[36],"is":[37,77,105],"challenging":[38],"due":[39],"complicated":[42],"realworld":[43],"background":[44],"noise":[45],"overlapping":[48],"In":[52],"paper,":[54],"we":[55],"proposed":[56],"a":[57,80,124,136],"unified":[58],"approach":[59],"that":[60],"takes":[61],"advantage":[63],"both":[65],"deep":[66,81],"learning":[67],"audio":[69,102],"enhancement.":[70],"A":[71],"convolutional":[72],"recurrent":[73],"neural":[74,82],"network":[75,83],"(CRNN)":[76],"combined":[78],"with":[79],"(DNN)":[84],"improve":[86,108],"performance":[88],"SED":[91,113],"classifiers,":[92],"an":[94],"optimally":[95],"modified":[96],"log-spectral":[97],"amplitude":[98],"estimator":[99],"(OMLSA)":[100],"based":[101],"enhancement":[103],"method":[104],"employed":[106],"robustness":[110],"system":[114],"on":[115,120],"noisy":[117,145],"environment.":[118],"Experiments":[119],"several":[121],"datasets":[122],"show":[123],"more":[125,137],"than":[126,138],"3%":[127],"increase":[128,140],"accuracy":[130,142],"normal":[133],"environment":[134,146],"9%":[139],"compared":[147],"state-of-the-art":[150],"approaches.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}