{"id":"https://openalex.org/W3008500714","doi":"https://doi.org/10.1109/isspit47144.2019.9001814","title":"Scalogram Neural Network Activations with Machine Learning for Domestic Multi-channel Audio Classification","display_name":"Scalogram Neural Network Activations with Machine Learning for Domestic Multi-channel Audio Classification","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008500714","doi":"https://doi.org/10.1109/isspit47144.2019.9001814","mag":"3008500714"},"language":"en","primary_location":{"id":"doi:10.1109/isspit47144.2019.9001814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit47144.2019.9001814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","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/A5053459575","display_name":"Abigail Copiaco","orcid":"https://orcid.org/0000-0003-2542-8604"},"institutions":[{"id":"https://openalex.org/I55990551","display_name":"University of Wollongong in Dubai","ror":"https://ror.org/0447ajy94","country_code":"AE","type":"education","lineage":["https://openalex.org/I204824540","https://openalex.org/I55990551"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Abigail Copiaco","raw_affiliation_strings":["University of Wollongong in Dubai, UAE"],"affiliations":[{"raw_affiliation_string":"University of Wollongong in Dubai, UAE","institution_ids":["https://openalex.org/I55990551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033818201","display_name":"Christian Ritz","orcid":"https://orcid.org/0000-0002-3768-7569"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christian Ritz","raw_affiliation_strings":["University of Wollongong, Australia"],"affiliations":[{"raw_affiliation_string":"University of Wollongong, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072869362","display_name":"Stefano Fasciani","orcid":"https://orcid.org/0000-0001-5555-3225"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Stefano Fasciani","raw_affiliation_strings":["University of Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"University of Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002768772","display_name":"Nidhal Abdulaziz","orcid":null},"institutions":[{"id":"https://openalex.org/I55990551","display_name":"University of Wollongong in Dubai","ror":"https://ror.org/0447ajy94","country_code":"AE","type":"education","lineage":["https://openalex.org/I204824540","https://openalex.org/I55990551"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Nidhal Abdulaziz","raw_affiliation_strings":["University of Wollongong in Dubai, UAE"],"affiliations":[{"raw_affiliation_string":"University of Wollongong in Dubai, UAE","institution_ids":["https://openalex.org/I55990551"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053459575"],"corresponding_institution_ids":["https://openalex.org/I55990551"],"apc_list":null,"apc_paid":null,"fwci":1.3357,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.82343274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2019","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":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":0.9976999759674072,"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":0.9853000044822693,"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/spectrogram","display_name":"Spectrogram","score":0.8324320316314697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7661961317062378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7366136312484741},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7196444272994995},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6218838691711426},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6094199419021606},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5518815517425537},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5186368823051453},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48270511627197266},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4729093015193939},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41805756092071533},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.400684118270874},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11185896396636963}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8324320316314697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661961317062378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7366136312484741},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7196444272994995},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6218838691711426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6094199419021606},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5518815517425537},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5186368823051453},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48270511627197266},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4729093015193939},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41805756092071533},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.400684118270874},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11185896396636963}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/isspit47144.2019.9001814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isspit47144.2019.9001814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:ro.uow.edu.au:eispapers1-4863","is_oa":false,"landing_page_url":"https://ro.uow.edu.au/eispapers1/3836","pdf_url":null,"source":{"id":"https://openalex.org/S4306400510","display_name":"Research Online (University of Wollongong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204824540","host_organization_name":"University of Wollongong","host_organization_lineage":["https://openalex.org/I204824540"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty of Engineering and Information Sciences - Papers: Part B","raw_type":"presentation"},{"id":"mag:3089514412","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002255186175414","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":[{"id":"https://metadata.un.org/sdg/17","score":0.41999998688697815,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2037230813","https://openalex.org/W2075475278","https://openalex.org/W2080271204","https://openalex.org/W2097117768","https://openalex.org/W2098441927","https://openalex.org/W2130745297","https://openalex.org/W2147860648","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2274287116","https://openalex.org/W2531409750","https://openalex.org/W2605646998","https://openalex.org/W2618530766","https://openalex.org/W2618553051","https://openalex.org/W2622742434","https://openalex.org/W2766727525","https://openalex.org/W2795280371","https://openalex.org/W2796101164","https://openalex.org/W2796384729","https://openalex.org/W2799668299","https://openalex.org/W2807069441","https://openalex.org/W2883618873","https://openalex.org/W2896082894","https://openalex.org/W2904809000","https://openalex.org/W2963590343","https://openalex.org/W2964350391","https://openalex.org/W3036237438","https://openalex.org/W4300972885","https://openalex.org/W6687483927","https://openalex.org/W6694260854","https://openalex.org/W6739564277","https://openalex.org/W6753158756","https://openalex.org/W6779574021","https://openalex.org/W7048424596"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W4360764600","https://openalex.org/W2910935116","https://openalex.org/W4316036082","https://openalex.org/W2103924733"],"abstract_inverted_index":{"Current":[0],"methodologies":[1],"explored":[2],"for":[3,46,100,151],"audio":[4,26],"classification,":[5],"particularly":[6],"multi-channel":[7,25],"audio,":[8,60],"commonly":[9],"involve":[10],"the":[11,59,69,79,83,96,104,109,114,117,121,127,135,138,152,156,162,171,177],"use":[12],"of":[13,31,34,82,103,113,120,148,155],"individual":[14],"deep":[15,110],"learning":[16,98,111],"approaches.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"look":[22],"at":[23,185],"domestic":[24],"classification":[27],"through":[28,68],"a":[29,167],"comparison":[30],"various":[32],"combinations":[33],"existing":[35],"pre-trained":[36],"Neural":[37],"Network":[38],"(NN)":[39],"models,":[40],"with":[41,54,161],"Support":[42],"Vector":[43],"Machine":[44],"(SVM)":[45],"classification.":[47,101],"The":[48],"NN":[49],"model":[50],"is":[51],"first":[52],"trained":[53],"spectro-temporal":[55],"features":[56,92,119],"extracted":[57,77,125],"from":[58,78,108,126,170],"characterized":[61],"by":[62],"scalogram":[63],"images":[64],"that":[65,75,123],"are":[66,76,88,124],"generated":[67],"Continuous":[70],"Wavelet":[71],"Transform":[72],"(CWT).":[73],"Activations":[74],"selected":[80],"layer":[81,154],"concerned":[84],"neural":[85],"network":[86,105,158],"model,":[87],"then":[89],"sent":[90],"as":[91],"used":[93],"to":[94,134],"train":[95],"machine":[97],"approach":[99],"Utilization":[102],"activations":[106],"learnt":[107],"component":[112],"classifier":[115],"strengthens":[116],"time-frequency":[118],"signal":[122],"spectrogram.":[128],"This":[129],"therefore":[130],"allows":[131],"further":[132],"improvement":[133,169],"accuracy.":[136],"For":[137],"full":[139],"SINS":[140],"development":[141],"database,":[142],"best":[143],"results":[144],"yielded":[145],"an":[146],"F1-score":[147,174],"over":[149],"97%":[150],"tenth":[153],"Xception":[157],"when":[159],"combined":[160],"multi-class":[163],"Linear":[164],"SVM,":[165],"showing":[166],"drastic":[168],"top":[172],"performing":[173],"achieved":[175],"in":[176],"DCASE":[178],"2018":[179],"Task":[180],"5":[181],"challenge,":[182],"which":[183],"rests":[184],"around":[186],"89%.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}