{"id":"https://openalex.org/W1970578576","doi":"https://doi.org/10.1109/taslp.2015.2389618","title":"Robust Sound Event Classification Using Deep Neural Networks","display_name":"Robust Sound Event Classification Using Deep Neural Networks","publication_year":2015,"publication_date":"2015-01-07","ids":{"openalex":"https://openalex.org/W1970578576","doi":"https://doi.org/10.1109/taslp.2015.2389618","mag":"1970578576"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2389618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2389618","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["The University of Science and Technology of China, Hefei, Anhui, P.R. China","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Science and Technology of China, Hefei, Anhui, P.R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035330165","display_name":"Haomin Zhang","orcid":"https://orcid.org/0000-0002-9439-1625"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haomin Zhang","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, PRC","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, PRC","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112098283","display_name":"Zhipeng Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Xie","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, PRC","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, PRC","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, PRC","National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, The University of Science and Technology of China, Hefei, PRC","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101703681","display_name":"Xiao Wei","orcid":"https://orcid.org/0000-0002-6258-6129"},"institutions":[{"id":"https://openalex.org/I4210129353","display_name":"Huawei Technologies (Germany)","ror":"https://ror.org/038cdme44","country_code":"DE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wei Xiao","raw_affiliation_strings":["Huawei Technologies Duesseldorf GmbH, European Research Center, Munich, Germany","European Research Center, Huawei Technologies Duesseldorf GmbH, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Duesseldorf GmbH, European Research Center, Munich, Germany","institution_ids":["https://openalex.org/I4210129353"]},{"raw_affiliation_string":"European Research Center, Huawei Technologies Duesseldorf GmbH, Munich, Germany","institution_ids":["https://openalex.org/I4210129353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":24.1602,"has_fulltext":false,"cited_by_count":265,"citation_normalized_percentile":{"value":0.99723919,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"23","issue":"3","first_page":"540","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8416370153427124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433052062988281},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.660502016544342},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6223263740539551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5893812775611877},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.554904580116272},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5490824580192566},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5457765460014343},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5226287841796875},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4966924786567688},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4678179919719696},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4548810124397278},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41113120317459106},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39944693446159363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35086870193481445},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2918857932090759},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08501598238945007}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8416370153427124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433052062988281},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.660502016544342},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6223263740539551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5893812775611877},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.554904580116272},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5490824580192566},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5457765460014343},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5226287841796875},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4966924786567688},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4678179919719696},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4548810124397278},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41113120317459106},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39944693446159363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35086870193481445},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2918857932090759},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08501598238945007},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2015.2389618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2389618","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:kar.kent.ac.uk:51341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TASLP.2015.2389618>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G352716874","display_name":"\u57fa\u4e8e\u60c5\u5883\u5efa\u6a21\u7684\u9ad8\u6548\u89c6\u89c9\u5339\u914d\u65b9\u6cd5\u53ca\u5176\u5e94\u7528\u7814\u7a76","funder_award_id":"61172158","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6708228564","display_name":null,"funder_award_id":"YB2012120147","funder_id":"https://openalex.org/F4320322183","funder_display_name":"Huawei Technologies"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322183","display_name":"Huawei Technologies","ror":"https://ror.org/00cmhce21"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W584947174","https://openalex.org/W614822286","https://openalex.org/W837720621","https://openalex.org/W1485835175","https://openalex.org/W1530136128","https://openalex.org/W1571966798","https://openalex.org/W1579714047","https://openalex.org/W1929391603","https://openalex.org/W1966273763","https://openalex.org/W1973746598","https://openalex.org/W1987809904","https://openalex.org/W1992095472","https://openalex.org/W1993882792","https://openalex.org/W2005122913","https://openalex.org/W2010486494","https://openalex.org/W2013020033","https://openalex.org/W2022011789","https://openalex.org/W2060539877","https://openalex.org/W2090431713","https://openalex.org/W2092216166","https://openalex.org/W2103279261","https://openalex.org/W2103434133","https://openalex.org/W2116206474","https://openalex.org/W2119110418","https://openalex.org/W2126109423","https://openalex.org/W2130640900","https://openalex.org/W2136922672","https://openalex.org/W2137270971","https://openalex.org/W2146171479","https://openalex.org/W2153635508","https://openalex.org/W2154221499","https://openalex.org/W2160815625","https://openalex.org/W2162867699","https://openalex.org/W2168441989","https://openalex.org/W2182578244","https://openalex.org/W2186582651","https://openalex.org/W2187281534","https://openalex.org/W2197594614","https://openalex.org/W2331166300","https://openalex.org/W2397348385","https://openalex.org/W2403021840","https://openalex.org/W4290464992","https://openalex.org/W6629029132","https://openalex.org/W6634650221","https://openalex.org/W6686660277","https://openalex.org/W6702387769","https://openalex.org/W6712225675","https://openalex.org/W6713287264"],"related_works":["https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2138847091","https://openalex.org/W1547433061","https://openalex.org/W2074549717","https://openalex.org/W2249987663"],"abstract_inverted_index":{"The":[0],"automatic":[1],"recognition":[2,75],"of":[3,12,36,152],"sound":[4,52,93,114],"events":[5],"by":[6],"computers":[7],"is":[8,64,141],"an":[9,65],"important":[10],"aspect":[11],"emerging":[13],"applications":[14],"such":[15,79],"as":[16,30,32,80],"automated":[17],"surveillance,":[18],"machine":[19,28,134],"hearing":[20],"and":[21,135,155,160],"auditory":[22,39,100,120],"scene":[23],"understanding.":[24],"Recent":[25],"advances":[26,44],"in":[27,33,45,108,149],"learning,":[29],"well":[31,90,165],"computational":[34],"models":[35],"the":[37,55,73,92],"human":[38],"system,":[40],"have":[41,84],"contributed":[42],"to":[43,57,87,162],"this":[46],"increasingly":[47],"popular":[48],"research":[49],"field.":[50],"Robust":[51],"event":[53,94,115],"classification,":[54],"ability":[56],"recognise":[58],"sounds":[59],"under":[60],"real-world":[61],"noisy":[62],"conditions,":[63],"especially":[66],"challenging":[67],"task.":[68],"Classification":[69],"methods":[70],"translated":[71],"from":[72],"speech":[74],"domain,":[76],"using":[77,131],"features":[78,124],"mel-frequency":[81],"cepstral":[82],"coefficients,":[83],"been":[85],"shown":[86,161],"perform":[88],"reasonably":[89],"for":[91],"classification":[95,116,147,169],"task,":[96],"although":[97],"spectrogram-based":[98],"or":[99],"image":[101,121],"analysis":[102],"techniques":[103],"reportedly":[104],"achieve":[105],"superior":[106],"performance":[107],"noise.":[109],"This":[110],"paper":[111],"outlines":[112],"a":[113,144],"framework":[117],"that":[118],"compares":[119],"front":[122,128],"end":[123,129],"with":[125,156,166],"spectrogram":[126],"image-based":[127],"features,":[130],"support":[132],"vector":[133],"deep":[136],"neural":[137],"network":[138],"classifiers.":[139],"Performance":[140],"evaluated":[142],"on":[143],"standard":[145],"robust":[146],"task":[148],"different":[150],"levels":[151],"corrupting":[153],"noise,":[154],"several":[157],"system":[158],"enhancements,":[159],"compare":[163],"very":[164],"current":[167],"state-of-the-art":[168],"techniques.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":40},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":33},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}