{"id":"https://openalex.org/W2938001259","doi":"https://doi.org/10.1109/icassp.2019.8683000","title":"Kullback\u2013Leibler Divergence Frequency Warping Scale for Acoustic Scene Classification Using Convolutional Neural Network","display_name":"Kullback\u2013Leibler Divergence Frequency Warping Scale for Acoustic Scene Classification Using Convolutional Neural Network","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938001259","doi":"https://doi.org/10.1109/icassp.2019.8683000","mag":"2938001259"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102859655","display_name":"Yuhong Yang","orcid":"https://orcid.org/0000-0003-3001-7957"},"institutions":[{"id":"https://openalex.org/I4210157323","display_name":"South China Institute of Collaborative Innovation","ror":"https://ror.org/04jnpk588","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210157323","https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhong Yang","raw_affiliation_strings":["Collaborative Innovation Center of Geospatial Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Geospatial Technology, China","institution_ids":["https://openalex.org/I4210157323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029591050","display_name":"Huiyu Zhang","orcid":"https://orcid.org/0000-0002-8958-3155"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiyu Zhang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041664453","display_name":"Weiping Tu","orcid":"https://orcid.org/0000-0002-6933-3298"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Tu","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074448137","display_name":"Haojun Ai","orcid":"https://orcid.org/0000-0002-4172-5070"},"institutions":[{"id":"https://openalex.org/I4210157323","display_name":"South China Institute of Collaborative Innovation","ror":"https://ror.org/04jnpk588","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210157323","https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojun Ai","raw_affiliation_strings":["Collaborative Innovation Center of Geospatial Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Geospatial Technology, China","institution_ids":["https://openalex.org/I4210157323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112612023","display_name":"Linjun Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linjun Cai","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087726516","display_name":"Ruimin Hu","orcid":"https://orcid.org/0000-0002-0290-5757"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruimin Hu","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090837004","display_name":"Fei Xiang","orcid":"https://orcid.org/0000-0003-3644-7114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Xiang","raw_affiliation_strings":["Xiaomi, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.669,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84381277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"840","last_page":"844"},"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":0.9990000128746033,"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":0.9865999817848206,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7475795745849609},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.72194904088974},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.7105963230133057},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6417751908302307},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5284965634346008},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5047658681869507},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.48979687690734863},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48927566409111023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.476576566696167},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46900343894958496},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40371012687683105},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08292990922927856},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0768379271030426}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7475795745849609},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.72194904088974},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.7105963230133057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6417751908302307},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5284965634346008},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5047658681869507},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.48979687690734863},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48927566409111023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.476576566696167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46900343894958496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40371012687683105},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08292990922927856},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0768379271030426},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683000","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W1992720861","https://openalex.org/W2076608692","https://openalex.org/W2096980176","https://openalex.org/W2125389028","https://openalex.org/W2137561966","https://openalex.org/W2434741482","https://openalex.org/W2619623002","https://openalex.org/W2695712842","https://openalex.org/W2799400564","https://openalex.org/W2897927800","https://openalex.org/W2963226019","https://openalex.org/W3103934323","https://openalex.org/W6678815747","https://openalex.org/W6980901144"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2229352698","https://openalex.org/W2105321464","https://openalex.org/W2887774187","https://openalex.org/W2388220555"],"abstract_inverted_index":{"Most":[0],"of":[1,29],"current":[2],"best":[3],"performing":[4],"Acoustic":[5],"Scene":[6],"Classification":[7],"(ASC)":[8],"systems":[9],"utilize":[10],"Mel":[11,19,116],"scale":[12,20,80,97,117],"spectrograms":[13,98],"with":[14,32,99],"Convolutional":[15],"Neural":[16],"Networks":[17],"(CNNs).":[18],"is":[21,102],"a":[22,76,127],"common":[23],"way":[24],"to":[25,39,54,137],"suit":[26],"frequency":[27,35,41,48,56,78],"warping":[28,79],"human":[30],"ears,":[31],"strict":[33],"decreasing":[34],"resolution":[36],"on":[37,104,119,145],"low":[38],"high":[40,55],"range.":[42],"However,":[43],"we":[44,73,113,124],"find":[45],"that":[46,75,112],"significant":[47],"bins":[49],"are":[50],"located":[51],"at":[52],"mid":[53],"range":[57],"for":[58,81,134],"some":[59],"acoustic":[60],"scenes,":[61],"such":[62],"as":[63],"travelling":[64],"by":[65],"bus,":[66],"tram":[67],"or":[68],"train.":[69],"In":[70,122],"this":[71],"paper,":[72],"show":[74,111],"better":[77],"ASC":[82,107],"can":[83],"be":[84],"automatically":[85],"learned":[86],"from":[87],"raw":[88],"spectrograms,":[89],"using":[90],"Kullback-Leibler":[91],"(KL)":[92],"divergence":[93],"scale.":[94],"Our":[95],"KL":[96],"CNN":[100],"method":[101,118],"evaluated":[103],"two":[105],"public":[106],"datasets.":[108,121],"The":[109],"results":[110],"outperform":[114],"the":[115],"both":[120],"addition,":[123],"also":[125],"employ":[126],"Conditional":[128],"Generative":[129],"Adversarial":[130],"Nets":[131],"(Conditional-GAN)":[132],"model":[133],"data":[135],"augmentation,":[136],"prevent":[138],"overfitting":[139],"problem":[140],"and":[141],"allow":[142],"further":[143],"improvements":[144],"ASC.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
