{"id":"https://openalex.org/W2900974552","doi":"https://doi.org/10.1007/978-3-030-19909-8_16","title":"Recognition of Urban Sound Events Using Deep Context-Aware Feature Extractors and Handcrafted Features","display_name":"Recognition of Urban Sound Events Using Deep Context-Aware Feature Extractors and Handcrafted Features","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2900974552","doi":"https://doi.org/10.1007/978-3-030-19909-8_16","mag":"2900974552"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-19909-8_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-19909-8_16","pdf_url":null,"source":{"id":"https://openalex.org/S4210185096","display_name":"IFIP advances in information and communication technology","issn_l":"1868-422X","issn":["1868-422X","1868-4238"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IFIP Advances in Information and Communication Technology","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://inria.hal.science/hal-02363844","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112254358","display_name":"Theodore Giannakopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Theodore Giannakopoulos","raw_affiliation_strings":["National Center for Scientific Research - \u201cDemokritos\u201d, Athens, Greece","NCSR - National Center for Scientific Research 'Demokritos' (Agia Paraskevi Attikis, P.O.Box 60228, 153 10 ATHENS, GREECE - Greece)"],"affiliations":[{"raw_affiliation_string":"National Center for Scientific Research - \u201cDemokritos\u201d, Athens, Greece","institution_ids":["https://openalex.org/I203474044"]},{"raw_affiliation_string":"NCSR - National Center for Scientific Research 'Demokritos' (Agia Paraskevi Attikis, P.O.Box 60228, 153 10 ATHENS, GREECE - Greece)","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514799","display_name":"Evaggelos Spyrou","orcid":"https://orcid.org/0000-0003-2067-9949"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]},{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Evaggelos Spyrou","raw_affiliation_strings":["National Center for Scientific Research - \u201cDemokritos\u201d, Athens, Greece","University of Thessaly, Lamia, Greece","University of Thessaly [Lamia] (Greece)","NCSR - National Center for Scientific Research 'Demokritos' (Agia Paraskevi Attikis, P.O.Box 60228, 153 10 ATHENS, GREECE - Greece)"],"affiliations":[{"raw_affiliation_string":"National Center for Scientific Research - \u201cDemokritos\u201d, Athens, Greece","institution_ids":["https://openalex.org/I203474044"]},{"raw_affiliation_string":"University of Thessaly, Lamia, Greece","institution_ids":["https://openalex.org/I145722265"]},{"raw_affiliation_string":"University of Thessaly [Lamia] (Greece)","institution_ids":["https://openalex.org/I145722265"]},{"raw_affiliation_string":"NCSR - National Center for Scientific Research 'Demokritos' (Agia Paraskevi Attikis, P.O.Box 60228, 153 10 ATHENS, GREECE - Greece)","institution_ids":["https://openalex.org/I203474044"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109045430","display_name":"Stavros Perantonis","orcid":null},"institutions":[{"id":"https://openalex.org/I203474044","display_name":"National Centre of Scientific Research \"Demokritos\"","ror":"https://ror.org/038jp4m40","country_code":"GR","type":"facility","lineage":["https://openalex.org/I203474044"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stavros J. Perantonis","raw_affiliation_strings":["National Center for Scientific Research - \u201cDemokritos\u201d, Athens, Greece","NCSR - National Center for Scientific Research 'Demokritos' (Agia Paraskevi Attikis, P.O.Box 60228, 153 10 ATHENS, GREECE - Greece)"],"affiliations":[{"raw_affiliation_string":"National Center for Scientific Research - \u201cDemokritos\u201d, Athens, Greece","institution_ids":["https://openalex.org/I203474044"]},{"raw_affiliation_string":"NCSR - National Center for Scientific Research 'Demokritos' (Agia Paraskevi Attikis, P.O.Box 60228, 153 10 ATHENS, GREECE - Greece)","institution_ids":["https://openalex.org/I203474044"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112254358"],"corresponding_institution_ids":["https://openalex.org/I203474044"],"apc_list":null,"apc_paid":null,"fwci":3.1724,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91407407,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11692","display_name":"Noise Effects and Management","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8311248421669006},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7078697085380554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6145609617233276},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5683973431587219},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5653036832809448},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5071573257446289},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.49341168999671936},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.45893925428390503},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.448561429977417},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.44097137451171875},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42234060168266296},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40803417563438416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36655962467193604},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34005123376846313},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.30781280994415283},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13158687949180603},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09299442172050476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311248421669006},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7078697085380554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6145609617233276},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5683973431587219},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5653036832809448},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5071573257446289},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49341168999671936},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.45893925428390503},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.448561429977417},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.44097137451171875},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42234060168266296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40803417563438416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36655962467193604},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34005123376846313},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.30781280994415283},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13158687949180603},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09299442172050476},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-030-19909-8_16","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-19909-8_16","pdf_url":null,"source":{"id":"https://openalex.org/S4210185096","display_name":"IFIP advances in information and communication technology","issn_l":"1868-422X","issn":["1868-422X","1868-4238"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IFIP Advances in Information and Communication Technology","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-02363844v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02363844","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2019, Hersonissos, Greece. pp.184-195, ⟨10.1007/978-3-030-19909-8_16⟩","raw_type":"Conference papers"},{"id":"pmh:oai:ir.lib.uth.gr:11615/72309","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/72309","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IFIP Advances in Information and Communication Technology","raw_type":"conferenceItem"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02363844v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02363844","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2019, Hersonissos, Greece. pp.184-195, ⟨10.1007/978-3-030-19909-8_16⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W216108723","https://openalex.org/W585519466","https://openalex.org/W1972567154","https://openalex.org/W1975572074","https://openalex.org/W1995396582","https://openalex.org/W2007041967","https://openalex.org/W2009238619","https://openalex.org/W2038484192","https://openalex.org/W2042390666","https://openalex.org/W2052666245","https://openalex.org/W2055911634","https://openalex.org/W2076063813","https://openalex.org/W2095705004","https://openalex.org/W2107789863","https://openalex.org/W2115629999","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2192412620","https://openalex.org/W2207975468","https://openalex.org/W2271840356","https://openalex.org/W2509065397","https://openalex.org/W2514305047","https://openalex.org/W2548717229","https://openalex.org/W2552850818","https://openalex.org/W2566935005","https://openalex.org/W2641889749","https://openalex.org/W2775505379","https://openalex.org/W2963451564","https://openalex.org/W3098357269"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4243888788","https://openalex.org/W2157165686","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2088690926"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,18,47,75,138],"method":[4,48],"for":[5,177],"recognizing":[6],"audio":[7,15,35,53,78,100,112,117,158,173],"events":[8],"in":[9,83,102,107,142],"urban":[10],"environments":[11],"that":[12,55,122,156,184],"combines":[13],"handcrafted":[14,99,134],"features":[16,54,101],"with":[17,98,131],"deep":[19,52,126],"learning":[20,127],"architectural":[21],"scheme":[22],"(Convolutional":[23],"Neural":[24],"Networks,":[25],"CNNs),":[26],"which":[27,80],"has":[28],"been":[29],"trained":[30,73],"to":[31,42,49,61,109,137],"distinguish":[32],"between":[33],"different":[34],"context":[36],"classes.":[37],"The":[38,147],"core":[39],"idea":[40],"is":[41,72,96,153],"use":[43],"the":[44,70,111,123,132,154,169,172],"CNNs":[45,162],"as":[46,163],"extract":[50],"context-aware":[51,125],"can":[56,166],"offer":[57],"supplementary":[58],"feature":[59,164],"representations":[60],"any":[62],"soundscape":[63],"analysis":[64],"classification":[65,145],"task.":[66],"Towards":[67],"this":[68,151],"end,":[69],"CNN":[71,178],"on":[74],"database":[76],"of":[77,85,114,144,150,171],"samples":[79],"are":[81],"annotated":[82],"terms":[84,143],"their":[86],"respective":[87],"\u201cscene\u201d":[88],"(e.g.":[89],"train,":[90],"street,":[91],"park),":[92],"and":[93,188],"then":[94],"it":[95],"combined":[97,130],"an":[103,115],"early":[104],"fusion":[105],"approach,":[106],"order":[108],"recognize":[110],"event":[113],"unknown":[116],"recording.":[118],"Detailed":[119],"experimentation":[120],"proves":[121],"proposed":[124],"scheme,":[128],"when":[129],"typical":[133],"features,":[135],"leads":[136],"significant":[139],"performance":[140,170],"boosting":[141],"accuracy.":[146],"main":[148],"contribution":[149],"work":[152],"demonstration":[155],"transferring":[157],"contextual":[159],"knowledge":[160],"using":[161],"extractors":[165],"significantly":[167],"improve":[168],"classifier,":[174],"without":[175],"need":[176],"training":[179],"(a":[180],"rather":[181],"demanding":[182],"process":[183],"requires":[185],"huge":[186],"datasets":[187],"complex":[189],"data":[190],"augmentation":[191],"procedures).":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-11-29T00:00:00"}