{"id":"https://openalex.org/W4224918070","doi":"https://doi.org/10.1109/icassp43922.2022.9746093","title":"Scalable Neural Architectures for End-to-End Environmental Sound Classification","display_name":"Scalable Neural Architectures for End-to-End Environmental Sound Classification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918070","doi":"https://doi.org/10.1109/icassp43922.2022.9746093"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746093","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5019442580","display_name":"Francesco Paissan","orcid":"https://orcid.org/0000-0002-5553-7935"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Paissan","raw_affiliation_strings":["Fondazione Bruno Kessler,Digital Society (DiGis) Center","Digital Society (DiGis) Center, Fondazione Bruno Kessler"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Digital Society (DiGis) Center","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Digital Society (DiGis) Center, Fondazione Bruno Kessler","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046416586","display_name":"Alberto Ancilotto","orcid":"https://orcid.org/0000-0002-1396-3709"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Ancilotto","raw_affiliation_strings":["Fondazione Bruno Kessler,Digital Society (DiGis) Center","Digital Society (DiGis) Center, Fondazione Bruno Kessler"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Digital Society (DiGis) Center","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Digital Society (DiGis) Center, Fondazione Bruno Kessler","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066363315","display_name":"Alessio Brutti","orcid":"https://orcid.org/0000-0003-4146-3071"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Brutti","raw_affiliation_strings":["Fondazione Bruno Kessler,Digital Society (DiGis) Center","Digital Society (DiGis) Center, Fondazione Bruno Kessler"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Digital Society (DiGis) Center","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Digital Society (DiGis) Center, Fondazione Bruno Kessler","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068548938","display_name":"Elisabetta Farella","orcid":"https://orcid.org/0000-0001-9047-9868"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisabetta Farella","raw_affiliation_strings":["Fondazione Bruno Kessler,Digital Society (DiGis) Center","Digital Society (DiGis) Center, Fondazione Bruno Kessler"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Digital Society (DiGis) Center","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Digital Society (DiGis) Center, Fondazione Bruno Kessler","institution_ids":["https://openalex.org/I2277624104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2277624104"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"641","last_page":"645"},"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":0.9990000128746033,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8104681968688965},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7665009498596191},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6639962792396545},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5383042097091675},{"id":"https://openalex.org/keywords/home-automation","display_name":"Home automation","score":0.42223265767097473},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4158763885498047},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41279298067092896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2616821527481079},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19081750512123108},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1408955454826355},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09152060747146606}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8104681968688965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7665009498596191},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6639962792396545},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5383042097091675},{"id":"https://openalex.org/C507571656","wikidata":"https://www.wikidata.org/wiki/Q848436","display_name":"Home automation","level":2,"score":0.42223265767097473},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4158763885498047},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41279298067092896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2616821527481079},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19081750512123108},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1408955454826355},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09152060747146606},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746093","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1972567154","https://openalex.org/W2038484192","https://openalex.org/W2060365990","https://openalex.org/W2509065397","https://openalex.org/W2526050071","https://openalex.org/W2531409750","https://openalex.org/W2593451766","https://openalex.org/W2769912137","https://openalex.org/W2777662428","https://openalex.org/W2945399614","https://openalex.org/W2955425717","https://openalex.org/W2963628261","https://openalex.org/W2964052309","https://openalex.org/W2972824267","https://openalex.org/W2999803881","https://openalex.org/W3004034302","https://openalex.org/W3047691788","https://openalex.org/W3091490309","https://openalex.org/W3098357269","https://openalex.org/W3105515454","https://openalex.org/W3176445421","https://openalex.org/W3201065055","https://openalex.org/W4210269029","https://openalex.org/W4298091485","https://openalex.org/W4391156722","https://openalex.org/W6638523607","https://openalex.org/W6643326691","https://openalex.org/W6728184133","https://openalex.org/W6746451879","https://openalex.org/W6747381837","https://openalex.org/W6762718338","https://openalex.org/W6778936657","https://openalex.org/W6779341498","https://openalex.org/W6786356651","https://openalex.org/W6797810191","https://openalex.org/W6801814890"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W2065606036","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W2016904525"],"abstract_inverted_index":{"Sound":[0],"Event":[1],"Detection":[2],"(SED)":[3],"is":[4,14,25],"a":[5,26],"complex":[6],"task":[7],"simulating":[8],"human":[9],"ability":[10],"to":[11,53,110,144],"recognize":[12],"what":[13],"happening":[15],"in":[16,29,47,132],"the":[17,112],"surrounding":[18],"from":[19],"auditory":[20],"signals":[21],"only.":[22],"This":[23],"technology":[24],"crucial":[27],"asset":[28],"many":[30],"applications":[31],"such":[32],"as":[33],"smart":[34],"cities.":[35],"Here,":[36],"urban":[37],"sounds":[38],"can":[39,116],"be":[40],"detected":[41],"and":[42,76,115,121],"processed":[43],"by":[44],"embedded":[45],"devices":[46],"an":[48],"Internet":[49],"of":[50],"Things":[51],"(IoT)":[52],"identify":[54],"meaningful":[55],"events":[56],"for":[57,68,81,96],"municipalities":[58],"or":[59],"law":[60],"enforcement.":[61],"However,":[62],"while":[63],"current":[64,145],"deep":[65],"learning":[66],"techniques":[67],"SED":[69],"are":[70,73,107],"effective,":[71],"they":[72],"also":[74],"resource-":[75],"power-hungry,":[77],"thus":[78],"not":[79],"appropriate":[80],"pervasive":[82],"battery-powered":[83],"devices.":[84],"In":[85,123],"this":[86],"paper,":[87],"we":[88],"propose":[89],"novel":[90],"neural":[91],"architectures":[92,126],"based":[93],"on":[94,101,119,130],"PhiNets":[95],"real-time":[97],"acoustic":[98],"event":[99],"detection":[100],"microcontroller":[102],"units.":[103],"The":[104],"proposed":[105],"models":[106],"easily":[108],"scalable":[109],"fit":[111],"hardware":[113],"requirements":[114],"operate":[117],"both":[118],"spectrograms":[120],"waveforms.":[122],"particular,":[124],"our":[125],"achieve":[127],"state-of-the-art":[128,146],"performance":[129],"UrbanSound8K":[131],"spectrogram":[133],"classification":[134],"(around":[135],"77%)":[136],"with":[137,142],"extreme":[138],"compression":[139],"factors":[140],"(99.8%)":[141],"respect":[143],"architectures.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
