{"id":"https://openalex.org/W2994720385","doi":"https://doi.org/10.23919/spa.2019.8936709","title":"Automatic labeling of traffic sound recordings using autoencoder-derived features","display_name":"Automatic labeling of traffic sound recordings using autoencoder-derived features","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2994720385","doi":"https://doi.org/10.23919/spa.2019.8936709","mag":"2994720385"},"language":"en","primary_location":{"id":"doi:10.23919/spa.2019.8936709","is_oa":false,"landing_page_url":"https://doi.org/10.23919/spa.2019.8936709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024105413","display_name":"Adam Kurowski","orcid":"https://orcid.org/0000-0002-5132-3016"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Adam Kurowski","raw_affiliation_strings":["Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079397804","display_name":"Andrzej Czy\u017cewski","orcid":"https://orcid.org/0000-0001-9159-8658"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Andrzej Czyzewski","raw_affiliation_strings":["Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022629545","display_name":"Szymon Zaporowski","orcid":"https://orcid.org/0000-0003-0814-1097"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Szymon Zaporowski","raw_affiliation_strings":["Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169333911"],"apc_list":null,"apc_paid":null,"fwci":0.5735,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63078099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"38","last_page":"43"},"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":0.9973999857902527,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/autoencoder","display_name":"Autoencoder","score":0.9676114320755005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7130483388900757},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6918284893035889},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6750321984291077},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6576086282730103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6342291831970215},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6263005137443542},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6048345565795898},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5483612418174744},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5339319705963135},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4815376400947571},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4200245141983032},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.27205967903137207},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0645405650138855}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9676114320755005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7130483388900757},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6918284893035889},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6750321984291077},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6576086282730103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6342291831970215},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6263005137443542},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6048345565795898},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5483612418174744},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5339319705963135},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4815376400947571},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4200245141983032},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27205967903137207},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0645405650138855},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/spa.2019.8936709","is_oa":false,"landing_page_url":"https://doi.org/10.23919/spa.2019.8936709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"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":15,"referenced_works":["https://openalex.org/W82771173","https://openalex.org/W1631913055","https://openalex.org/W1992278063","https://openalex.org/W2038484192","https://openalex.org/W2167277498","https://openalex.org/W2191779130","https://openalex.org/W2290318471","https://openalex.org/W2405774341","https://openalex.org/W2510346432","https://openalex.org/W2557283755","https://openalex.org/W2883041062","https://openalex.org/W2952624574","https://openalex.org/W3098507037","https://openalex.org/W6696830301","https://openalex.org/W6980901144"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601"],"abstract_inverted_index":{"An":[0],"approach":[1],"to":[2,87],"detection":[3,22,178],"of":[4,15,18,68,73,89,106,126,129,139,169,173,179],"events":[5,21],"occurring":[6],"in":[7,171],"road":[8,20,57],"traffic":[9],"using":[10],"autoencoders":[11],"is":[12,58,75],"presented.":[13],"Extensions":[14],"existing":[16],"algorithms":[17],"acoustic":[19,48],"employing":[23],"Mel":[24],"Frequency":[25],"Cepstral":[26],"Coefficients":[27],"combined":[28],"with":[29,122],"classifiers":[30,170],"based":[31],"on":[32,103],"k":[33],"nearest":[34],"neighbors,":[35],"Support":[36],"Vector":[37],"Machines,":[38],"and":[39,62,119,181],"random":[40],"forests":[41],"are":[42],"used.":[43],"In":[44,111],"our":[45,112],"research,":[46,113],"the":[47,52,56,71,78,104,134,158,167],"signal":[49],"gathered":[50],"from":[51],"microphone":[53],"placed":[54],"near":[55],"split":[59],"into":[60,64],"frames":[61],"converted":[63],"a":[65,84,123],"2-dimensional":[66],"form":[67],"Mel-cepstrogram.":[69],"Next,":[70],"sequence":[72],"mel-cepstrograms":[74],"processed":[76,90],"by":[77,157],"autoencoder":[79,118,159],"neural":[80,160],"network,":[81],"which":[82,99],"assigns":[83],"unique":[85],"embedding":[86],"each":[88],"mel-cepstrograms.":[91],"The":[92],"embeddings":[93],"may":[94,162],"be":[95,101,163],"treated":[96,143],"as":[97,144,177],"features":[98,140],"can":[100],"fed":[102],"input":[105,146],"other":[107],"machine":[108],"learning-based":[109],"classifiers.":[110,150],"we":[114],"prepared":[115],"such":[116,176],"an":[117,145],"compared":[120],"it":[121],"standard":[124],"solution":[125],"parameterization":[127],"consisting":[128],"averaging":[130],"MFCC":[131],"throughout":[132],"all":[133],"analyzed":[135],"frames.":[136],"Both":[137],"types":[138,149],"were":[141],"then":[142],"for":[147,165],"selected":[148],"It":[151],"was":[152],"found,":[153],"that":[154],"parameters":[155],"derived":[156],"network":[161],"useful":[164],"improving":[166],"performance":[168],"case":[172],"problematic":[174],"classes":[175],"single":[180],"multiple":[182],"vehicles":[183],"passes.":[184]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}