{"id":"https://openalex.org/W2973284423","doi":"https://doi.org/10.15439/2019f185","title":"Urban Sound Classification using Long Short-Term Memory Neural Network","display_name":"Urban Sound Classification using Long Short-Term Memory Neural Network","publication_year":2019,"publication_date":"2019-09-20","ids":{"openalex":"https://openalex.org/W2973284423","doi":"https://doi.org/10.15439/2019f185","mag":"2973284423"},"language":"en","primary_location":{"id":"doi:10.15439/2019f185","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2019f185","pdf_url":"https://annals-csis.org/proceedings/2019/drp/pdf/185.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/proceedings/2019/drp/pdf/185.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031570429","display_name":"Iurii Lezhenin","orcid":"https://orcid.org/0000-0002-4737-7249"},"institutions":[{"id":"https://openalex.org/I212220629","display_name":"Peter the Great St. Petersburg Polytechnic University","ror":"https://ror.org/02x91aj62","country_code":"RU","type":"education","lineage":["https://openalex.org/I212220629"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Iurii Lezhenin","raw_affiliation_strings":["Institute of Computer Science and Technology Peter the Great St.Petersburg Polytechnic University St.Petersburg, 195251, Russia"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology Peter the Great St.Petersburg Polytechnic University St.Petersburg, 195251, Russia","institution_ids":["https://openalex.org/I212220629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054409979","display_name":"Natalia Bogach","orcid":"https://orcid.org/0000-0001-6563-6040"},"institutions":[{"id":"https://openalex.org/I212220629","display_name":"Peter the Great St. Petersburg Polytechnic University","ror":"https://ror.org/02x91aj62","country_code":"RU","type":"education","lineage":["https://openalex.org/I212220629"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Natalia Bogach","raw_affiliation_strings":["Institute of Computer Science and Technology Peter the Great St.Petersburg Polytechnic University St.Petersburg, 195251, Russia"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology Peter the Great St.Petersburg Polytechnic University St.Petersburg, 195251, Russia","institution_ids":["https://openalex.org/I212220629"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009805261","display_name":"Evgeny Pyshkin","orcid":"https://orcid.org/0000-0002-7923-7988"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Evgeny Pyshkin","raw_affiliation_strings":["Software Engineering Lab University of Aizu Aizu-Wakamatsu, 965-8580, Japan"],"affiliations":[{"raw_affiliation_string":"Software Engineering Lab University of Aizu Aizu-Wakamatsu, 965-8580, Japan","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031570429"],"corresponding_institution_ids":["https://openalex.org/I212220629"],"apc_list":null,"apc_paid":null,"fwci":8.9044,"has_fulltext":true,"cited_by_count":84,"citation_normalized_percentile":{"value":0.98616874,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"18","issue":null,"first_page":"57","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9855999946594238,"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/spectrogram","display_name":"Spectrogram","score":0.9379110932350159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7899305820465088},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6360782980918884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5478578805923462},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5281676650047302},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5268921852111816},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5127366781234741},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4977755844593048},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.46845555305480957},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4550240635871887},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44442254304885864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3315945267677307}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9379110932350159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899305820465088},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6360782980918884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5478578805923462},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5281676650047302},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5268921852111816},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5127366781234741},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4977755844593048},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.46845555305480957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4550240635871887},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44442254304885864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3315945267677307},{"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.15439/2019f185","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2019f185","pdf_url":"https://annals-csis.org/proceedings/2019/drp/pdf/185.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:be173799a2694ffea491e2f1ff88ce22","is_oa":true,"landing_page_url":"https://doaj.org/article/be173799a2694ffea491e2f1ff88ce22","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 18, Pp 57-60 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.15439/2019f185","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2019f185","pdf_url":"https://annals-csis.org/proceedings/2019/drp/pdf/185.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G5256887504","display_name":null,"funder_award_id":"Japan Society for the Promotion of Science (JSPS)","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7752643416","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8442905581","display_name":"Advancing interfaces and algorithms used in traveler-centric information systems supporting geographical, cultural and historical perspectives","funder_award_id":"17K00509","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2973284423.pdf","grobid_xml":"https://content.openalex.org/works/W2973284423.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1496704041","https://openalex.org/W1566256432","https://openalex.org/W1923404803","https://openalex.org/W1972567154","https://openalex.org/W1986315484","https://openalex.org/W2008415856","https://openalex.org/W2038484192","https://openalex.org/W2088850873","https://openalex.org/W2130640900","https://openalex.org/W2135342008","https://openalex.org/W2137561966","https://openalex.org/W2140647972","https://openalex.org/W2143612262","https://openalex.org/W2294797155","https://openalex.org/W2397464754","https://openalex.org/W2400753342","https://openalex.org/W2403438050","https://openalex.org/W2407005679","https://openalex.org/W2730437450","https://openalex.org/W2739301753","https://openalex.org/W2751841560","https://openalex.org/W2901273913","https://openalex.org/W2902444285","https://openalex.org/W2912027173","https://openalex.org/W2962785008","https://openalex.org/W3016001898","https://openalex.org/W3098357269","https://openalex.org/W3171487505","https://openalex.org/W4288400169"],"related_works":["https://openalex.org/W2912153778","https://openalex.org/W4387163678","https://openalex.org/W4288108708","https://openalex.org/W2973430807","https://openalex.org/W4385280324","https://openalex.org/W2890685186","https://openalex.org/W2984436043","https://openalex.org/W4390245176","https://openalex.org/W2912831041","https://openalex.org/W3173606726"],"abstract_inverted_index":{"Environmental":[0],"sound":[1,51],"classification":[2,30],"has":[3],"received":[4],"more":[5,94],"attention":[6],"in":[7],"recent":[8],"years.":[9],"Analysis":[10],"of":[11,17,24,89],"environmental":[12],"sounds":[13],"is":[14,55,68,80,93],"difficult":[15],"because":[16],"its":[18],"unstructured":[19],"nature.":[20],"However,":[21],"the":[22,29,76,83,99],"presence":[23],"strong":[25],"spectro-temporal":[26],"patterns":[27],"makes":[28],"possible.":[31],"Since":[32],"LSTM":[33,47,84],"neural":[34],"networks":[35],"are":[36],"efficient":[37],"at":[38],"learning":[39],"temporal":[40],"dependencies":[41],"we":[42],"propose":[43],"and":[44,73,92,96],"examine":[45],"a":[46,87],"model":[48,54,85],"for":[49],"urban":[50],"classification.":[52],"The":[53,65],"trained":[56],"on":[57],"magnitude":[58],"mel-spectrograms":[59],"extracted":[60],"from":[61],"UrbanSound8K":[62],"dataset":[63],"audio.":[64],"proposed":[66],"network":[67],"evaluated":[69],"using":[70],"5-fold":[71],"cross-validation":[72],"compared":[74],"with":[75],"baseline":[77],"CNN.":[78,100],"It":[79],"shown":[81],"that":[82],"outperforms":[86],"set":[88],"existing":[90],"solutions":[91],"accurate":[95],"confident":[97],"than":[98]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}