{"id":"https://openalex.org/W2796101164","doi":"https://doi.org/10.1109/jas.2018.7511066","title":"Deep Scalogram Representations for Acoustic Scene Classification","display_name":"Deep Scalogram Representations for Acoustic Scene Classification","publication_year":2018,"publication_date":"2018-04-05","ids":{"openalex":"https://openalex.org/W2796101164","doi":"https://doi.org/10.1109/jas.2018.7511066","mag":"2796101164"},"language":"en","primary_location":{"id":"doi:10.1109/jas.2018.7511066","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jas.2018.7511066","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570654/8332135/08332139.pdf","source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/CAA Journal of Automatica Sinica","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6570654/8332135/08332139.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063262277","display_name":"Zhao Ren","orcid":"https://orcid.org/0000-0003-0707-5016"},"institutions":[{"id":"https://openalex.org/I119916105","display_name":"Augsburg University","ror":"https://ror.org/057ewhh68","country_code":"US","type":"education","lineage":["https://openalex.org/I119916105"]},{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE","US"],"is_corresponding":true,"raw_author_name":"Zhao Ren","raw_affiliation_strings":["University of Augsburg, Germany","Universitat Augsburg, Augsburg, Bayern, DE"],"affiliations":[{"raw_affiliation_string":"University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Universitat Augsburg, Augsburg, Bayern, DE","institution_ids":["https://openalex.org/I119916105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032971738","display_name":"Kun Qian","orcid":"https://orcid.org/0000-0002-1918-6453"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kun Qian","raw_affiliation_strings":["Technische Universitat Munchen, Germany, and also with University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Technische Universitat Munchen, Germany, and also with University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036056631","display_name":"Zixing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zixing Zhang","raw_affiliation_strings":["Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072343742","display_name":"Vedhas Pandit","orcid":"https://orcid.org/0000-0002-1983-8140"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Vedhas Pandit","raw_affiliation_strings":["University of Augsburg, Germany","Imperial College London, London, London, GB"],"affiliations":[{"raw_affiliation_string":"University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Imperial College London, London, London, GB","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030891676","display_name":"Alice Baird","orcid":"https://orcid.org/0000-0002-7003-5650"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I119916105","display_name":"Augsburg University","ror":"https://ror.org/057ewhh68","country_code":"US","type":"education","lineage":["https://openalex.org/I119916105"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Alice Baird","raw_affiliation_strings":["University of Augsburg, Germany","Universitat Augsburg, Augsburg, Bayern, DE"],"affiliations":[{"raw_affiliation_string":"University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Universitat Augsburg, Augsburg, Bayern, DE","institution_ids":["https://openalex.org/I119916105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Imperial College London, UK, and also with University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Imperial College London, UK, and also with University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836","https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063262277"],"corresponding_institution_ids":["https://openalex.org/I119916105","https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":11.7729,"has_fulltext":true,"cited_by_count":122,"citation_normalized_percentile":{"value":0.99018078,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"5","issue":"3","first_page":"662","last_page":"669"},"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":0.9980000257492065,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9878000020980835,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9698321223258972},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6593993902206421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6497830748558044},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6353492736816406},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6009092330932617},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5580134987831116},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4943547248840332},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47044649720191956},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4698839485645294},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32157087326049805}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9698321223258972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6593993902206421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6497830748558044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6353492736816406},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6009092330932617},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5580134987831116},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4943547248840332},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47044649720191956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4698839485645294},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32157087326049805},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jas.2018.7511066","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jas.2018.7511066","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570654/8332135/08332139.pdf","source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/CAA Journal of Automatica Sinica","raw_type":"journal-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:43856","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/43856/43856.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/jas.2018.7511066","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jas.2018.7511066","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570654/8332135/08332139.pdf","source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/CAA Journal of Automatica Sinica","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2300736770","display_name":null,"funder_award_id":"(CSC)","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2796101164.pdf","grobid_xml":"https://content.openalex.org/works/W2796101164.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W581956982","https://openalex.org/W1580375566","https://openalex.org/W1686810756","https://openalex.org/W1802825888","https://openalex.org/W1924770834","https://openalex.org/W1963882359","https://openalex.org/W1996021349","https://openalex.org/W2012296273","https://openalex.org/W2042390666","https://openalex.org/W2064675550","https://openalex.org/W2080271204","https://openalex.org/W2090777335","https://openalex.org/W2092728879","https://openalex.org/W2099471712","https://openalex.org/W2117539524","https://openalex.org/W2131774270","https://openalex.org/W2133564696","https://openalex.org/W2144005487","https://openalex.org/W2145487065","https://openalex.org/W2163605009","https://openalex.org/W2165698076","https://openalex.org/W2396415881","https://openalex.org/W2470673105","https://openalex.org/W2526050071","https://openalex.org/W2536920793","https://openalex.org/W2538918575","https://openalex.org/W2566935005","https://openalex.org/W2607377556","https://openalex.org/W2734479159","https://openalex.org/W2735006420","https://openalex.org/W2735814390","https://openalex.org/W2746419079","https://openalex.org/W2753943679","https://openalex.org/W2754582354","https://openalex.org/W2755288226","https://openalex.org/W2755577605","https://openalex.org/W2761083049","https://openalex.org/W2772185488","https://openalex.org/W2773048923","https://openalex.org/W2775505379","https://openalex.org/W2953066166","https://openalex.org/W2964308564","https://openalex.org/W3096437212","https://openalex.org/W4251576337","https://openalex.org/W4320013936","https://openalex.org/W4394643672","https://openalex.org/W6741411642","https://openalex.org/W6780493881","https://openalex.org/W6980901144","https://openalex.org/W6997293705","https://openalex.org/W7023426766","https://openalex.org/W7043259713","https://openalex.org/W7046541945"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W3090555870","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3170224572","https://openalex.org/W2899027234","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Spectrogram":[0],"representations":[1],"of":[2,25,39,137,146,158,202],"acoustic":[3,10,57,132],"scenes":[4,58],"have":[5],"achieved":[6],"competitive":[7],"performance":[8],"for":[9,35],"scene":[11,133],"classification.":[12],"Yet,":[13],"the":[14,37,55,69,81,127,131,153,171,174,182,189,204],"spectrogram":[15,172],"alone":[16],"does":[17],"not":[18],"take":[19],"into":[20,59,75,92],"account":[21],"a":[22,85,102,107,119,210],"substantial":[23],"amount":[24],"time-frequency":[26],"information.":[27],"In":[28],"this":[29],"study,":[30],"we":[31],"present":[32],"an":[33,47,156,179],"approach":[34,51,129],"exploring":[36],"benefits":[38],"deep":[40],"scalogram":[41],"representations,":[42],"extracted":[43,83,197],"in":[44],"segments":[45],"from":[46,84,112,161],"audio":[48],"stream.":[49],"The":[50],"presented":[52],"firstly":[53],"transforms":[54],"segmented":[56],"bump":[60,175,198],"and":[61,106,144,149,173],"morse":[62],"scalograms,":[63],"as":[64,66],"well":[65],"spectrograms;":[67],"secondly,":[68],"spectrograms":[70],"or":[71],"scalograms":[72,199],"are":[73,90,99,116,200],"sent":[74],"pre-trained":[76],"convolutional":[77],"neural":[78,96,165],"networks;":[79],"thirdly,":[80],"features":[82],"subsequent":[86],"fully":[87],"connected":[88],"layer":[89,105],"fed":[91],"(bidirectional)":[93],"gated":[94,163],"recurrent":[95,164],"networks,":[97],"which":[98,177],"followed":[100],"by":[101,118,188],"single":[103],"highway":[104],"softmax":[108],"layer;":[109],"finally,":[110],"predictions":[111],"these":[113],"three":[114],"systems":[115],"fused":[117],"margin":[120],"sampling":[121],"value":[122],"strategy.":[123],"We":[124],"then":[125],"evaluate":[126],"proposed":[128],"using":[130],"classification":[134,205],"data":[135],"set":[136],"2017":[138,191],"IEEE":[139],"AASP":[140],"Challenge":[141],"on":[142,181],"Detection":[143],"Classification":[145],"Acoustic":[147],"Scenes":[148],"Events":[150],"(DCASE).":[151],"On":[152],"evaluation":[154],"set,":[155],"accuracy":[157],"64.0":[159],"%":[160,184],"bidirectional":[162],"networks":[166],"is":[167,178],"obtained":[168],"when":[169,207],"fusing":[170,208],"scalogram,":[176],"improvement":[180],"61.0":[183],"baseline":[185],"result":[186,194],"provided":[187],"DCASE":[190],"organisers.":[192],"This":[193],"shows":[195],"that":[196],"capable":[201],"improving":[203],"accuracy,":[206],"with":[209],"spectrogram-based":[211],"system.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}