{"id":"https://openalex.org/W3198371936","doi":"https://doi.org/10.1109/tsp52935.2021.9522625","title":"On the Performance Improvements of Deep Learning Methods for Audio Event Detection and Classification","display_name":"On the Performance Improvements of Deep Learning Methods for Audio Event Detection and Classification","publication_year":2021,"publication_date":"2021-07-26","ids":{"openalex":"https://openalex.org/W3198371936","doi":"https://doi.org/10.1109/tsp52935.2021.9522625","mag":"3198371936"},"language":"en","primary_location":{"id":"doi:10.1109/tsp52935.2021.9522625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp52935.2021.9522625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 44th International Conference on Telecommunications and Signal Processing (TSP)","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/A5051328344","display_name":"Claudio Eutizi","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Claudio Eutizi","raw_affiliation_strings":["Signal Processing for Telecommunications and Economics (SP4TE), University of Roma Tre, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Signal Processing for Telecommunications and Economics (SP4TE), University of Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066071482","display_name":"Francesco Benedetto","orcid":"https://orcid.org/0000-0002-9203-1642"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Benedetto","raw_affiliation_strings":["Signal Processing for Telecommunications and Economics (SP4TE), University of Roma Tre, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Signal Processing for Telecommunications and Economics (SP4TE), University of Roma Tre, Rome, Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051328344"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":null,"apc_paid":null,"fwci":0.7618,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71108857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"141","last_page":"145"},"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":0.993399977684021,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8171299695968628},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6460400819778442},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.640465259552002},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5576010942459106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5481271743774414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5435516834259033},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4579940438270569},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.4451938569545746},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4440236985683441},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4246622323989868},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41906043887138367},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.13618868589401245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8171299695968628},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6460400819778442},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.640465259552002},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5576010942459106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5481271743774414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5435516834259033},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4579940438270569},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.4451938569545746},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4440236985683441},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4246622323989868},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41906043887138367},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.13618868589401245},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsp52935.2021.9522625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp52935.2021.9522625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 44th International Conference on Telecommunications and Signal Processing (TSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/393053","is_oa":false,"landing_page_url":"http://hdl.handle.net/11590/393053","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W2038484192","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2613718673","https://openalex.org/W2796347433","https://openalex.org/W2884367402","https://openalex.org/W2962835968","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963492800","https://openalex.org/W2972006294","https://openalex.org/W3042687732","https://openalex.org/W3083485545","https://openalex.org/W3097700606","https://openalex.org/W4293584584","https://openalex.org/W6637373629","https://openalex.org/W6695314431","https://openalex.org/W6750227808","https://openalex.org/W6780522411"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W1590604789","https://openalex.org/W2088690926","https://openalex.org/W2155527258","https://openalex.org/W2910700619"],"abstract_inverted_index":{"With":[0],"the":[1,12,26,95,113,116],"explosive":[2],"growth":[3],"of":[4,14,23,102,109,115],"high":[5],"precision":[6],"and":[7,17,54,86,123],"high-performance":[8],"deep":[9],"learning":[10],"methods,":[11],"issue":[13],"object":[15,38],"detection":[16,39,89,122],"classification":[18,85],"has":[19],"received":[20],"a":[21,50],"lot":[22],"attention":[24],"in":[25,67],"last":[27],"years.":[28],"More":[29],"recently,":[30],"similar":[31],"approaches":[32],"have":[33],"been":[34],"investigated":[35],"for":[36,82,119],"audio":[37,44,68,84,87,98,107,120],"with":[40],"promising":[41],"results.":[42],"The":[43],"signal":[45],"is":[46],"first":[47],"converted":[48],"to":[49],"2D":[51],"time-frequency":[52],"representation":[53],"then,":[55],"by":[56],"using":[57],"multiple":[58,62],"convolutional":[59,63],"layers":[60],"or":[61],"groups,":[64],"patterns":[65],"contained":[66],"recordings":[69],"are":[70],"localized.":[71],"Here,":[72],"we":[73],"apply":[74],"four":[75],"computer":[76],"vision\u2019s":[77],"state-of-the-art":[78],"CNNs":[79],"adapting":[80],"them":[81],"our":[83],"event":[88,121],"tasks.":[90],"Our":[91],"results,":[92],"performed":[93],"on":[94],"publicly":[96],"available":[97],"dataset":[99],"UrbanSound8K":[100],"composed":[101],"more":[103],"than":[104],"8700":[105],"short":[106],"clips":[108],"urban":[110],"sounds,":[111],"confirm":[112],"effectiveness":[114],"proposed":[117],"approach":[118],"classification.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}