{"id":"https://openalex.org/W2765177038","doi":"https://doi.org/10.23919/eusipco.2017.8081712","title":"A neural network approach for sound event detection in real life audio","display_name":"A neural network approach for sound event detection in real life audio","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2765177038","doi":"https://doi.org/10.23919/eusipco.2017.8081712","mag":"2765177038"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2017.8081712","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th European Signal Processing Conference (EUSIPCO)","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/A5110940312","display_name":"Michele Valenti","orcid":null},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Michele Valenti","raw_affiliation_strings":["Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050432816","display_name":"Dario Tonelli","orcid":null},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Dario Tonelli","raw_affiliation_strings":["Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009982837","display_name":"Fabio Vesperini","orcid":"https://orcid.org/0000-0001-7748-5454"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Vesperini","raw_affiliation_strings":["Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004777557","display_name":"Emanuele Principi","orcid":"https://orcid.org/0000-0002-2835-7277"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Principi","raw_affiliation_strings":["Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034253968","display_name":"Stefano Squartini","orcid":"https://orcid.org/0000-0001-9374-0128"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Squartini","raw_affiliation_strings":["Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universita Politecnica delle Marche, Ancona, Italy","institution_ids":["https://openalex.org/I122534668"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5110940312"],"corresponding_institution_ids":["https://openalex.org/I122534668"],"apc_list":null,"apc_paid":null,"fwci":0.5548,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.66128476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2754","last_page":"2758"},"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":0.9994999766349792,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7480360269546509},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6223810911178589},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6115589141845703},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5712663531303406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5187097191810608},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5128107666969299},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.48552823066711426},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.35347309708595276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22718289494514465},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1600932478904724},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1522073745727539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480360269546509},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6223810911178589},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6115589141845703},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5712663531303406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5187097191810608},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5128107666969299},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.48552823066711426},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.35347309708595276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22718289494514465},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1600932478904724},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1522073745727539},{"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:10.23919/eusipco.2017.8081712","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.univpm.it:11566/252459","is_oa":false,"landing_page_url":"http://hdl.handle.net/11566/252459","pdf_url":null,"source":{"id":"https://openalex.org/S4306402571","display_name":"Universit\u00e0 Politecnica delle Marche (Universit\u00e0 Politecnica delle Marche)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122534668","host_organization_name":"Marche Polytechnic University","host_organization_lineage":["https://openalex.org/I122534668"],"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1165382972","https://openalex.org/W1500640442","https://openalex.org/W1522301498","https://openalex.org/W1533561824","https://openalex.org/W1822987211","https://openalex.org/W1844944916","https://openalex.org/W1964538581","https://openalex.org/W1973134616","https://openalex.org/W2086468861","https://openalex.org/W2089368853","https://openalex.org/W2090777335","https://openalex.org/W2114777924","https://openalex.org/W2129120544","https://openalex.org/W2130640900","https://openalex.org/W2141739745","https://openalex.org/W2160860215","https://openalex.org/W2164266899","https://openalex.org/W2305675433","https://openalex.org/W2343389358","https://openalex.org/W2487315868","https://openalex.org/W2526050071","https://openalex.org/W2566935005","https://openalex.org/W2622742434","https://openalex.org/W2964121744","https://openalex.org/W3100031071","https://openalex.org/W4298018175","https://openalex.org/W6632323398","https://openalex.org/W6677170001","https://openalex.org/W6683682394","https://openalex.org/W6727253422","https://openalex.org/W6739564277"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W3110605476","https://openalex.org/W3043119899","https://openalex.org/W2766269877"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"and":[3,26,39,44,95,112,142,165,178],"compares":[4],"two":[5,88,120,134],"algorithms":[6],"based":[7],"on":[8,60,83,150,162],"artificial":[9],"neural":[10,136,144],"networks":[11],"(ANNs)":[12],"for":[13,32],"sound":[14],"event":[15],"detection":[16,124],"in":[17,194],"real":[18],"life":[19],"audio.":[20,69],"Both":[21],"systems":[22],"have":[23],"been":[24],"developed":[25],"evaluated":[27],"with":[28,108,119,133],"the":[29,33,37,50,65,77,87,91,96,99,151,190,195],"material":[30],"provided":[31],"third":[34],"task":[35],"of":[36,41,56,171,176,183],"Detection":[38],"Classification":[40],"Acoustic":[42],"Scenes":[43],"Events":[45],"(DCASE)":[46],"2016":[47,153,197],"challenge.":[48,198],"For":[49],"first":[51],"algorithm,":[52],"we":[53,71,128],"make":[54],"use":[55],"an":[57,172,179,187],"ANN":[58],"trained":[59,161],"different":[61,85,121,135],"features":[62,164],"extracted":[63,118],"from":[64],"down-mixed":[66],"mono":[67],"channel":[68],"Secondly,":[70],"analyse":[72],"a":[73,159],"binaural":[74,89,100,163],"algorithm":[75],"where":[76],"same":[78],"feature":[79,104],"extraction":[80],"is":[81],"performed":[82],"four":[84],"channels:":[86],"channels,":[90],"averaged":[92,173,180],"monaural":[93],"signal":[94],"difference":[97],"between":[98],"channels.":[101],"The":[102,146],"proposed":[103],"set":[105],"comprehends,":[106],"along":[107],"mel-frequency":[109],"cepstral":[110],"coefficients":[111],"log-mel":[113],"energies,":[114],"also":[115],"activity":[116,123],"information":[117],"voice":[122],"(VAD)":[125],"algorithms.":[126],"Moreover,":[127],"will":[129],"present":[130],"results":[131],"obtained":[132,149],"architectures,":[137],"namely":[138],"multi-layer":[139],"perceptrons":[140],"(MLPs)":[141],"recurrent":[143],"networks.":[145],"highest":[147],"scores":[148],"DCASE":[152,196],"evaluation":[154],"dataset":[155],"are":[156],"achieved":[157],"by":[158],"MLP":[160],"adaptive":[166],"energy":[167],"VAD;":[168],"they":[169],"consist":[170],"error":[174],"rate":[175],"0.79":[177],"F1":[181],"score":[182,192],"48.1%,":[184],"thus":[185],"marking":[186],"improvement":[188],"over":[189],"best":[191],"registered":[193]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}