{"id":"https://openalex.org/W1501987291","doi":"https://doi.org/10.1109/icassp.2015.7178031","title":"Robust sound event recognition using convolutional neural networks","display_name":"Robust sound event recognition using convolutional neural networks","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1501987291","doi":"https://doi.org/10.1109/icassp.2015.7178031","mag":"1501987291"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/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, University of Science and Technology of China, Hefei, PRC","National Engineering Laboratory of Speech and Language Information Processing, The University of Science & Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, 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, The University of Science & Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, PRC","National Engineering Laboratory of Speech and Language Information Processing, The University of Science & Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, 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, The University of Science & Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","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, University of Science and Technology of China, Hefei, PRC","National Engineering Laboratory of Speech and Language Information Processing, The University of Science & Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, 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, The University of Science & Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":15.0555,"has_fulltext":false,"cited_by_count":264,"citation_normalized_percentile":{"value":0.99438789,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"559","last_page":"563"},"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":0.9998000264167786,"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":0.9898999929428101,"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/spectrogram","display_name":"Spectrogram","score":0.8868875503540039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8082365393638611},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.713533341884613},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6868354678153992},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6543095111846924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6287128925323486},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.61543208360672},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6023734211921692},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5172034502029419},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4602261185646057},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4570574462413788},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43109434843063354},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08306223154067993}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8868875503540039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082365393638611},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.713533341884613},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6868354678153992},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6543095111846924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6287128925323486},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.61543208360672},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6023734211921692},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5172034502029419},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4602261185646057},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4570574462413788},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43109434843063354},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08306223154067993},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:55020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ICASSP.2015.7178031>)","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":"Conference proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W614822286","https://openalex.org/W837720621","https://openalex.org/W1530136128","https://openalex.org/W1538131130","https://openalex.org/W1970578576","https://openalex.org/W2005122913","https://openalex.org/W2089959702","https://openalex.org/W2090431713","https://openalex.org/W2092216166","https://openalex.org/W2103434133","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2130640900","https://openalex.org/W2133693888","https://openalex.org/W2146171479","https://openalex.org/W2155273149","https://openalex.org/W2168441989","https://openalex.org/W2182578244","https://openalex.org/W2186582651","https://openalex.org/W2187281534","https://openalex.org/W6631886576","https://openalex.org/W6632100814","https://openalex.org/W6679901780","https://openalex.org/W6686660277","https://openalex.org/W6686999899"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2167155152","https://openalex.org/W2606551632","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"],"abstract_inverted_index":{"Traditional":[0],"sound":[1],"event":[2],"recognition":[3],"methods":[4,18],"based":[5],"on":[6,126],"informative":[7],"front":[8],"end":[9,16,85],"features":[10,49,66,94],"such":[11,19,67],"as":[12,20,68],"MFCC,":[13],"with":[14,62,101],"back":[15,84],"sequencing":[17],"HMM,":[21],"tend":[22],"to":[23,45,78],"perform":[24],"poorly":[25],"in":[26,39,54,135,141],"the":[27,79,83,102,131,136],"presence":[28],"of":[29,82,106,139],"interfering":[30],"acoustic":[31],"noise.":[32],"Since":[33],"noise":[34],"corruption":[35],"may":[36],"be":[37],"unavoidable":[38],"practical":[40],"situations,":[41],"it":[42],"is":[43],"important":[44],"develop":[46],"more":[47],"robust":[48],"and":[50],"classifiers.":[51,86],"Recent":[52],"advances":[53],"this":[55,89,134,142],"field":[56],"use":[57],"powerful":[58,103],"machine":[59],"learning":[60],"techniques":[61],"high":[63],"dimensional":[64],"input":[65],"spectrograms":[69],"or":[70],"auditory":[71],"image.":[72],"These":[73],"improve":[74],"robustness":[75],"largely":[76],"thanks":[77],"discriminative":[80],"capabilities":[81,105],"We":[87],"extend":[88],"further":[90],"by":[91],"proposing":[92],"novel":[93],"derived":[95],"from":[96],"spectrogram":[97],"energy":[98],"triggering,":[99],"allied":[100],"classification":[104],"a":[107],"convolutional":[108],"neural":[109],"network":[110],"(CNN).":[111],"The":[112],"proposed":[113],"method":[114],"demonstrates":[115],"excellent":[116],"performance":[117],"under":[118],"noise-corrupted":[119],"conditions":[120],"when":[121],"compared":[122],"against":[123],"state-of-the-art":[124],"approaches":[125],"standard":[127],"evaluation":[128],"tasks.":[129],"To":[130],"author's":[132],"knowledge":[133],"first":[137],"application":[138],"CNN":[140],"field.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":41},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}