{"id":"https://openalex.org/W2922137896","doi":"https://doi.org/10.1109/icosc.2019.8665547","title":"Acoustic Scene Classification Using Spatial Pyramid Pooling with Convolutional Neural Networks","display_name":"Acoustic Scene Classification Using Spatial Pyramid Pooling with Convolutional Neural Networks","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2922137896","doi":"https://doi.org/10.1109/icosc.2019.8665547","mag":"2922137896"},"language":"en","primary_location":{"id":"doi:10.1109/icosc.2019.8665547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icosc.2019.8665547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 13th International Conference on Semantic Computing (ICSC)","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/A5057223767","display_name":"Ahmet Melih Ba\u015fbu\u011f","orcid":"https://orcid.org/0000-0002-4950-335X"},"institutions":[{"id":"https://openalex.org/I188740104","display_name":"Ba\u015fkent University","ror":"https://ror.org/02v9bqx10","country_code":"TR","type":"education","lineage":["https://openalex.org/I188740104"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Ahmet Melih Basbug","raw_affiliation_strings":["Department of Computer Engineering, Baskent University, Ankara, TURKEY"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Baskent University, Ankara, TURKEY","institution_ids":["https://openalex.org/I188740104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034079324","display_name":"Mustafa Sert","orcid":"https://orcid.org/0000-0002-7056-4245"},"institutions":[{"id":"https://openalex.org/I188740104","display_name":"Ba\u015fkent University","ror":"https://ror.org/02v9bqx10","country_code":"TR","type":"education","lineage":["https://openalex.org/I188740104"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mustafa Sert","raw_affiliation_strings":["Department of Computer Engineering, Baskent University, Ankara, TURKEY"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Baskent University, Ankara, TURKEY","institution_ids":["https://openalex.org/I188740104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057223767"],"corresponding_institution_ids":["https://openalex.org/I188740104"],"apc_list":null,"apc_paid":null,"fwci":2.4879,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.89775377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"128","last_page":"131"},"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":0.9991999864578247,"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":0.9908000230789185,"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/pooling","display_name":"Pooling","score":0.8500290513038635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8260839581489563},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8143100738525391},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7182639241218567},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6947433352470398},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6672831773757935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6409352421760559},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5649654269218445},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5581291913986206},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5343659520149231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4518529772758484},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4267534017562866},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09026798605918884}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8500290513038635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260839581489563},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8143100738525391},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7182639241218567},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6947433352470398},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6672831773757935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6409352421760559},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5649654269218445},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5581291913986206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5343659520149231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4518529772758484},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4267534017562866},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09026798605918884},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icosc.2019.8665547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icosc.2019.8665547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 13th International Conference on Semantic Computing (ICSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1968935646","https://openalex.org/W1972567154","https://openalex.org/W2006546815","https://openalex.org/W2032156461","https://openalex.org/W2056067759","https://openalex.org/W2109255472","https://openalex.org/W2150565997","https://openalex.org/W2162915993","https://openalex.org/W2165007993","https://openalex.org/W2735072998","https://openalex.org/W2768083292","https://openalex.org/W2787600432","https://openalex.org/W2851547775","https://openalex.org/W2963162200","https://openalex.org/W2964121744","https://openalex.org/W3103385400","https://openalex.org/W3210141620","https://openalex.org/W3210683364","https://openalex.org/W4295723153","https://openalex.org/W4393487040","https://openalex.org/W6631190155","https://openalex.org/W6652149581","https://openalex.org/W6682227246","https://openalex.org/W6746507118","https://openalex.org/W6752516136","https://openalex.org/W6980901144"],"related_works":["https://openalex.org/W2022849497","https://openalex.org/W3081299480","https://openalex.org/W2407190427","https://openalex.org/W2919210741","https://openalex.org/W2907584218","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W4322096758","https://openalex.org/W4360764600","https://openalex.org/W2555630001"],"abstract_inverted_index":{"Automatic":[0],"understanding":[1],"of":[2,24,40,67,99,123],"audio":[3,69,107,117],"events":[4],"and":[5,19,43,48,71,113,119],"acoustic":[6,25,64,132],"scenes":[7,26],"has":[8],"been":[9],"an":[10],"active":[11],"research":[12],"topic":[13],"for":[14],"researchers":[15],"from":[16,96],"signal":[17,70],"processing":[18],"machine":[20],"learning":[21],"communities.":[22],"Recognition":[23],"in":[27],"the":[28,38,63,100,121,129,140,145,149],"real":[29],"life":[30],"scenarios":[31],"is":[32],"a":[33,73],"challenging":[34],"task":[35],"due":[36],"to":[37,53,85,91,115],"diversity":[39],"environmental":[41],"sounds":[42],"uncontrolled":[44],"environments.":[45],"Efficient":[46],"methods":[47],"feature":[49,147],"representations":[50],"are":[51],"needed":[52],"cope":[54],"with":[55,144],"these":[56],"challenges.":[57],"In":[58],"this":[59],"study,":[60],"we":[61],"address":[62],"scene":[65,133],"classification":[66,150],"raw":[68],"propose":[72],"cascaded":[74],"CNN":[75],"architecture":[76,127,143],"that":[77],"uses":[78],"spatial":[79,87],"pyramid":[80,88],"pooling":[81],"(SPP,":[82],"also":[83],"referred":[84],"as":[86],"matching)":[89],"method":[90],"aggregate":[92],"local":[93],"features":[94],"coming":[95],"convolutional":[97],"layers":[98],"CNN.":[101],"We":[102],"use":[103],"three":[104],"well":[105],"known":[106],"features,":[108],"namely":[109],"MFCC,":[110],"Mel":[111],"Energy,":[112],"spectrogram":[114,146],"represent":[116],"content":[118],"evaluate":[120],"effectiveness":[122],"our":[124],"proposed":[125,141],"CNN-SPP":[126,142],"on":[128],"DCASE":[130],"2018":[131],"performance":[134],"dataset.":[135],"Our":[136],"results":[137],"show":[138],"that,":[139],"improves":[148],"accuracy.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}