{"id":"https://openalex.org/W3007045810","doi":"https://doi.org/10.1145/3378184.3378186","title":"A deep convolutionary network for automatic detection of audio events","display_name":"A deep convolutionary network for automatic detection of audio events","publication_year":2020,"publication_date":"2020-01-07","ids":{"openalex":"https://openalex.org/W3007045810","doi":"https://doi.org/10.1145/3378184.3378186","mag":"3007045810"},"language":"en","primary_location":{"id":"doi:10.1145/3378184.3378186","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378184.3378186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Applications of Intelligent Systems","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/A5084532664","display_name":"Antonio Roberto","orcid":"https://orcid.org/0000-0002-3220-1152"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Antonio Roberto","raw_affiliation_strings":["Dept. of Information Eng., Electrical Eng. and Applied Mathematics (DIEM) - University of Salerno, Fisciano (SA), Italy"],"affiliations":[{"raw_affiliation_string":"Dept. of Information Eng., Electrical Eng. and Applied Mathematics (DIEM) - University of Salerno, Fisciano (SA), Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083939361","display_name":"Alessia Saggese","orcid":"https://orcid.org/0000-0003-4687-7994"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessia Saggese","raw_affiliation_strings":["Dept. of Information Eng., Electrical Eng. and Applied Mathematics (DIEM) - University of Salerno, Fisciano (SA), Italy"],"affiliations":[{"raw_affiliation_string":"Dept. of Information Eng., Electrical Eng. and Applied Mathematics (DIEM) - University of Salerno, Fisciano (SA), Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027593663","display_name":"Mario Vento","orcid":"https://orcid.org/0000-0002-2948-741X"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mario Vento","raw_affiliation_strings":["Dept. of Information Eng., Electrical Eng. and Applied Mathematics (DIEM) - University of Salerno, Fisciano (SA), Italy"],"affiliations":[{"raw_affiliation_string":"Dept. of Information Eng., Electrical Eng. and Applied Mathematics (DIEM) - University of Salerno, Fisciano (SA), Italy","institution_ids":["https://openalex.org/I131729948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084532664"],"corresponding_institution_ids":["https://openalex.org/I131729948"],"apc_list":null,"apc_paid":null,"fwci":0.6061,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.64726794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.996999979019165,"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":0.9746999740600586,"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":0.7342570424079895},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.47338953614234924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4672280251979828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.329983115196228},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.306308388710022},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2100662887096405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7342570424079895},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.47338953614234924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4672280251979828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.329983115196228},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.306308388710022},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2100662887096405}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3378184.3378186","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378184.3378186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Applications of Intelligent Systems","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":15,"referenced_works":["https://openalex.org/W821549425","https://openalex.org/W2045871908","https://openalex.org/W2052384514","https://openalex.org/W2108880818","https://openalex.org/W2118230268","https://openalex.org/W2135131618","https://openalex.org/W2158698691","https://openalex.org/W2509065397","https://openalex.org/W2544224704","https://openalex.org/W2556437173","https://openalex.org/W2774097455","https://openalex.org/W2915067382","https://openalex.org/W2964052309","https://openalex.org/W3098357269","https://openalex.org/W4289743400"],"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":{"In":[0,34],"the":[1,8,15,29,55,63,78,83,92,95,99,110,123],"last":[2],"years,":[3],"a":[4,45],"growing":[5],"interest":[6,27],"of":[7,17,26,31,70,85,94,122],"scientific":[9],"community":[10],"has":[11],"been":[12],"devoted":[13],"to":[14,61,75,87,120],"design":[16],"efficient":[18],"and":[19,72,132],"effective":[20],"solutions":[21],"for":[22,82,106],"automatically":[23,76],"identifying":[24],"sounds":[25,84],"in":[28,52,59],"field":[30],"audio":[32],"surveillance.":[33],"this":[35],"paper,":[36],"we":[37],"propose":[38],"an":[39],"event":[40],"detection":[41],"architecture":[42],"based":[43,126],"on":[44,127],"convolutional":[46],"neural":[47],"network.":[48],"The":[49],"network":[50],"takes":[51],"input":[53],"directly":[54],"raw":[56],"sampled":[57],"waveform,":[58],"order":[60],"reduce":[62],"information":[64],"loss":[65],"introduced":[66],"by":[67],"any":[68],"type":[69],"preprocessing":[71],"is":[73],"able":[74],"learn":[77],"most":[79],"important":[80],"frequencies":[81],"interests":[86],"be":[88],"recognized.":[89],"We":[90],"evaluate":[91],"performance":[93],"proposed":[96],"approach":[97],"over":[98],"MIVIA":[100],"Audio":[101],"Events":[102],"dataset,":[103],"widely":[104],"adopted":[105],"benchmarking":[107],"purposes,":[108],"achieving":[109],"best":[111],"results":[112],"and,":[113],"therefore,":[114],"confirming":[115],"its":[116],"effectiveness":[117],"with":[118],"respect":[119],"state":[121],"art":[124],"methodologies,":[125],"both":[128],"traditional":[129],"machine":[130],"learning":[131,134],"deep":[133],"methodologies.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}