{"id":"https://openalex.org/W2576072808","doi":"https://doi.org/10.1109/mmsp.2016.7813376","title":"Robust sound event classification by using denoising autoencoder","display_name":"Robust sound event classification by using denoising autoencoder","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2576072808","doi":"https://doi.org/10.1109/mmsp.2016.7813376","mag":"2576072808"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2016.7813376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2016.7813376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)","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/A5071996405","display_name":"Jianchao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianchao Zhou","raw_affiliation_strings":["Institute of Computer Science & Technology, Peking University, Haidian District Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Haidian District Beijing, P. R. China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071057752","display_name":"Liqun Peng","orcid":"https://orcid.org/0000-0002-9275-5990"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqun Peng","raw_affiliation_strings":["Institute of Computer Science & Technology, Peking University, Haidian District Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Haidian District Beijing, P. R. China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017207620","display_name":"Xiaoou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoou Chen","raw_affiliation_strings":["Institute of Computer Science & Technology, Peking University, Haidian District Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Haidian District Beijing, P. R. China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100885747","display_name":"Deshun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deshun Yang","raw_affiliation_strings":["Institute of Computer Science & Technology, Peking University, Haidian District Beijing, P. R. China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, Haidian District Beijing, P. R. China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071996405"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.7641,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7420205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2016","issue":null,"first_page":"1","last_page":"6"},"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":0.9951000213623047,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7552241683006287},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6689835786819458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6217764019966125},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5809808969497681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5295014381408691},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4578610062599182},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.44444963335990906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4298778474330902},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.17752966284751892},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1653003692626953}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7552241683006287},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6689835786819458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6217764019966125},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5809808969497681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5295014381408691},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4578610062599182},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.44444963335990906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4298778474330902},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.17752966284751892},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1653003692626953},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mmsp.2016.7813376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2016.7813376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 18th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"},{"id":"mag:2747846023","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/20090422/201702283583643016","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324887","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W953419521","https://openalex.org/W1501987291","https://openalex.org/W1581984155","https://openalex.org/W1618108441","https://openalex.org/W1757247158","https://openalex.org/W1970088388","https://openalex.org/W1970578576","https://openalex.org/W1973681148","https://openalex.org/W2025768430","https://openalex.org/W2054857826","https://openalex.org/W2066201752","https://openalex.org/W2090431713","https://openalex.org/W2091432990","https://openalex.org/W2100279255","https://openalex.org/W2107789863","https://openalex.org/W2108196886","https://openalex.org/W2110798204","https://openalex.org/W2114486803","https://openalex.org/W2139689188","https://openalex.org/W2245569228","https://openalex.org/W2296581541","https://openalex.org/W2405774341","https://openalex.org/W2540556213","https://openalex.org/W2963074454","https://openalex.org/W6624928425","https://openalex.org/W6637735428","https://openalex.org/W6676071220","https://openalex.org/W6681113844","https://openalex.org/W6690610466"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601","https://openalex.org/W3037110488"],"abstract_inverted_index":{"Over":[0],"the":[1,25,30,84],"last":[2],"decade,":[3],"a":[4,16,52,89,93],"lot":[5],"of":[6,32,83,107],"research":[7],"has":[8],"been":[9],"done":[10],"on":[11,96],"sound":[12,20,64],"event":[13,21,65],"classification.":[14],"But":[15],"main":[17],"problem":[18],"with":[19,99,105],"classification":[22,66,90],"is":[23,68,86],"that":[24,106],"performance":[26,45,124],"sharply":[27],"degrades":[28],"in":[29,46],"presence":[31],"noise.":[33],"As":[34],"spectrogram-based":[35],"image":[36,60,70,117],"features":[37,109],"and":[38,103,115],"denoising":[39,57,79],"auto":[40,58,80],"encoder":[41,59],"reportedly":[42],"have":[43],"superior":[44],"noisy":[47],"conditions,":[48],"this":[49],"paper":[50],"proposes":[51],"new":[53],"robust":[54],"feature":[55,61,71,85],"called":[56],"(DIF)":[62],"for":[63],"which":[67],"an":[69,74],"extracted":[72],"from":[73],"image-like":[75],"representation":[76],"produced":[77],"by":[78,88],"encoder.":[81],"Performance":[82],"evaluated":[87],"experiment":[91],"using":[92],"SVM":[94],"classifier":[95],"audio":[97],"examples":[98],"different":[100],"noise":[101],"levels,":[102],"compared":[104],"baseline":[108],"including":[110],"mel-frequency":[111],"cepstral":[112],"coefficients":[113],"(MFCC)":[114],"spectrogram":[116],"feature.":[118],"The":[119],"proposed":[120],"DIF":[121],"demonstrates":[122],"better":[123],"under":[125],"noise-corrupted":[126],"conditions.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}