{"id":"https://openalex.org/W2980689481","doi":"https://doi.org/10.1109/tmm.2019.2947199","title":"Acoustic Scene Clustering Using Joint Optimization of Deep Embedding Learning and Clustering Iteration","display_name":"Acoustic Scene Clustering Using Joint Optimization of Deep Embedding Learning and Clustering Iteration","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2980689481","doi":"https://doi.org/10.1109/tmm.2019.2947199","mag":"2980689481"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2947199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2947199","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-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/A5070863631","display_name":"Yanxiong Li","orcid":"https://orcid.org/0000-0003-4362-1125"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxiong Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4362-1125","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055957682","display_name":"Mingle Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingle Liu","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008484510","display_name":"Wucheng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wucheng Wang","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385420","display_name":"Yuhan Zhang","orcid":"https://orcid.org/0000-0002-4345-7938"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Zhang","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102706072","display_name":"Qianhua He","orcid":"https://orcid.org/0000-0002-9079-4566"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianhua He","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":2.454,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.90147474,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"22","issue":"6","first_page":"1385","last_page":"1394"},"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":0.9994000196456909,"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":0.992900013923645,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8550825715065002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8196484446525574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6892344951629639},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.652683436870575},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6155855655670166},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5167031288146973},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5055453777313232},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4593309760093689},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4255264401435852},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4254888892173767}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8550825715065002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8196484446525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6892344951629639},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.652683436870575},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6155855655670166},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5167031288146973},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5055453777313232},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4593309760093689},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4255264401435852},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4254888892173767},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2019.2947199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2947199","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2229356822","display_name":null,"funder_award_id":"6191101306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G243040613","display_name":"\u975e\u73b0\u573a\u8bf4\u8bdd\u4eba\u8ba4\u8bc1\u8bed\u97f3\u771f\u5b9e\u6027\u68c0\u6d4b\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61571192","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2680521080","display_name":null,"funder_award_id":"6191101570","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3994375257","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u590d\u6742\u97f3\u9891\u8bf4\u8bdd\u4eba\u5206\u6790\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"61771200","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8241351501","display_name":null,"funder_award_id":"6191101514","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323059","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W330298975","https://openalex.org/W1498436455","https://openalex.org/W1844944916","https://openalex.org/W2049304293","https://openalex.org/W2053913299","https://openalex.org/W2069323107","https://openalex.org/W2081074144","https://openalex.org/W2086384421","https://openalex.org/W2095147901","https://openalex.org/W2097922870","https://openalex.org/W2103235956","https://openalex.org/W2119577488","https://openalex.org/W2126337883","https://openalex.org/W2127218421","https://openalex.org/W2509065397","https://openalex.org/W2511956680","https://openalex.org/W2569249728","https://openalex.org/W2571520038","https://openalex.org/W2592168896","https://openalex.org/W2617002574","https://openalex.org/W2617512665","https://openalex.org/W2619623002","https://openalex.org/W2769732779","https://openalex.org/W2775505379","https://openalex.org/W2775794021","https://openalex.org/W2799400564","https://openalex.org/W2820243394","https://openalex.org/W2890718983","https://openalex.org/W2895776009","https://openalex.org/W2896862445","https://openalex.org/W2902873133","https://openalex.org/W2903185874","https://openalex.org/W2913795158","https://openalex.org/W2921763313","https://openalex.org/W2962852342","https://openalex.org/W3098357269","https://openalex.org/W3105202226","https://openalex.org/W4256161595","https://openalex.org/W6678914141","https://openalex.org/W6747331233","https://openalex.org/W6758876586","https://openalex.org/W6760395818","https://openalex.org/W6980901144","https://openalex.org/W7046541945"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4375867731","https://openalex.org/W2037549926","https://openalex.org/W4226493464","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3048601286","https://openalex.org/W2965925734","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Recent":[0],"efforts":[1],"have":[2,19],"been":[3,20],"made":[4],"on":[5,22],"acoustic":[6,23,46,67],"scene":[7,24,33,47,68],"classification":[8],"in":[9,143],"the":[10,38,42,73,82,85,103,107,136,146,151,156],"audio":[11,39],"signal":[12],"processing":[13],"community.":[14],"In":[15,59,81,154],"contrast,":[16],"few":[17],"studies":[18],"conducted":[21],"clustering,":[25],"which":[26],"is":[27,88,93,106],"a":[28,49,64,89,96,114],"newly":[29],"emerging":[30],"problem.":[31],"Acoustic":[32],"clustering":[34,69,79,104,110,152],"aims":[35],"at":[36],"merging":[37],"recordings":[40],"of":[41,45,75,145],"same":[43],"class":[44],"into":[48],"single":[50],"cluster":[51],"without":[52],"using":[53],"prior":[54],"information":[55,149],"and":[56,78,120,127,150],"training":[57],"classifiers.":[58],"this":[60],"study,":[61],"we":[62],"propose":[63],"method":[65,138],"for":[66,118],"that":[70,92,135],"jointly":[71],"optimizes":[72],"procedures":[74],"feature":[76,87],"learning":[77],"iteration.":[80],"proposed":[83,137],"method,":[84],"learned":[86],"deep":[90,97,157],"embedding":[91,158],"extracted":[94],"from":[95],"convolutional":[98],"neural":[99],"network":[100],"(CNN),":[101],"while":[102],"algorithm":[105],"agglomerative":[108],"hierarchical":[109],"(AHC).":[111],"We":[112],"formulate":[113],"unified":[115],"loss":[116],"function":[117],"integrating":[119],"optimizing":[121],"these":[122],"two":[123],"procedures.":[124],"Various":[125],"features":[126],"methods":[128,142],"are":[129],"compared.":[130],"The":[131],"experimental":[132],"results":[133],"demonstrate":[134],"outperforms":[139,159],"other":[140],"unsupervised":[141],"terms":[144],"normalized":[147],"mutual":[148],"accuracy.":[153],"addition,":[155],"many":[160],"state-of-the-art":[161],"features.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}