{"id":"https://openalex.org/W1972567154","doi":"https://doi.org/10.1109/mlsp.2015.7324337","title":"Environmental sound classification with convolutional neural networks","display_name":"Environmental sound classification with convolutional neural networks","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W1972567154","doi":"https://doi.org/10.1109/mlsp.2015.7324337","mag":"1972567154"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2015.7324337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5073629051","display_name":"Karol J. Piczak","orcid":"https://orcid.org/0000-0002-6115-0833"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Karol J. Piczak","raw_affiliation_strings":["Institute of Electronic Systems, Warsaw University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronic Systems, Warsaw University of Technology","institution_ids":["https://openalex.org/I108403487"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073629051"],"corresponding_institution_ids":["https://openalex.org/I108403487"],"apc_list":null,"apc_paid":null,"fwci":34.1961,"has_fulltext":false,"cited_by_count":896,"citation_normalized_percentile":{"value":0.99833113,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"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":0.9983999729156494,"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":0.9882000088691711,"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":0.8463788032531738},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.8125756978988647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7768337726593018},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7604775428771973},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6366121172904968},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5477092862129211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5267863869667053},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4968858063220978},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.49395495653152466},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4731888771057129},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38478076457977295}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8463788032531738},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8125756978988647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768337726593018},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7604775428771973},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6366121172904968},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5477092862129211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5267863869667053},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4968858063220978},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49395495653152466},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4731888771057129},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38478076457977295},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2015.7324337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2015.7324337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W330298975","https://openalex.org/W648910355","https://openalex.org/W1496704041","https://openalex.org/W1827297289","https://openalex.org/W1872489089","https://openalex.org/W1904365287","https://openalex.org/W1921523184","https://openalex.org/W1984541135","https://openalex.org/W1995562189","https://openalex.org/W2020290924","https://openalex.org/W2036242736","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2101926813","https://openalex.org/W2103235956","https://openalex.org/W2107789863","https://openalex.org/W2108069432","https://openalex.org/W2108563286","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2116456623","https://openalex.org/W2117539524","https://openalex.org/W2137028279","https://openalex.org/W2141125852","https://openalex.org/W2147800946","https://openalex.org/W2150341604","https://openalex.org/W2155273149","https://openalex.org/W2156387975","https://openalex.org/W2162741153","https://openalex.org/W2163605009","https://openalex.org/W2167510172","https://openalex.org/W2188183693","https://openalex.org/W2240580723","https://openalex.org/W2313745396","https://openalex.org/W2398456099","https://openalex.org/W2400753342","https://openalex.org/W2557283755","https://openalex.org/W2953301748","https://openalex.org/W2962820688","https://openalex.org/W2963399116","https://openalex.org/W3103385400","https://openalex.org/W4293460823","https://openalex.org/W6638685980","https://openalex.org/W6639260565","https://openalex.org/W6640036494","https://openalex.org/W6640185926","https://openalex.org/W6676071220","https://openalex.org/W6677651945","https://openalex.org/W6677681515","https://openalex.org/W6682889407","https://openalex.org/W6684191040","https://openalex.org/W6690079499","https://openalex.org/W6712469065","https://openalex.org/W6713457403"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870"],"abstract_inverted_index":{"This":[0],"paper":[1],"evaluates":[2],"the":[3,49],"potential":[4],"of":[5,14,21,39,48,57],"convolutional":[6,23],"neural":[7],"networks":[8],"in":[9],"classifying":[10],"short":[11],"audio":[12,40],"clips":[13],"environmental":[15,58],"sounds.":[16],"A":[17],"deep":[18],"model":[19,63],"consisting":[20],"2":[22,28],"layers":[24,31],"with":[25,44],"max-pooling":[26],"and":[27,59,72],"fully":[29],"connected":[30],"is":[32,51],"trained":[33],"on":[34,53,68],"a":[35],"low":[36],"level":[37],"representation":[38],"data":[41],"(segmented":[42],"spectrograms)":[43],"deltas.":[45],"The":[46,62],"accuracy":[47],"network":[50],"evaluated":[52],"3":[54],"public":[55],"datasets":[56],"urban":[60],"recordings.":[61],"outperforms":[64],"baseline":[65],"implementations":[66],"relying":[67],"mel-frequency":[69],"cepstral":[70],"coefficients":[71],"achieves":[73],"results":[74],"comparable":[75],"to":[76],"other":[77],"state-of-the-art":[78],"approaches.":[79]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":77},{"year":2024,"cited_by_count":75},{"year":2023,"cited_by_count":86},{"year":2022,"cited_by_count":108},{"year":2021,"cited_by_count":145},{"year":2020,"cited_by_count":135},{"year":2019,"cited_by_count":134},{"year":2018,"cited_by_count":67},{"year":2017,"cited_by_count":43},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}