{"id":"https://openalex.org/W3010803200","doi":"https://doi.org/10.1109/ialp48816.2019.9037692","title":"Acoustic Scene Classification Using Deep Convolutional Neural Network via Transfer Learning","display_name":"Acoustic Scene Classification Using Deep Convolutional Neural Network via Transfer Learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010803200","doi":"https://doi.org/10.1109/ialp48816.2019.9037692","mag":"3010803200"},"language":"en","primary_location":{"id":"doi:10.1109/ialp48816.2019.9037692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp48816.2019.9037692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Asian Language Processing (IALP)","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/A5101765984","display_name":"Min Ye","orcid":"https://orcid.org/0000-0003-3642-5388"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Ye","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016260066","display_name":"Hong Zhong","orcid":"https://orcid.org/0000-0002-0392-9734"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhong","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101526673","display_name":"Xiao Song","orcid":"https://orcid.org/0000-0001-6352-6542"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Song","raw_affiliation_strings":["PKU Shenzhen Institute, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PKU Shenzhen Institute, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110518840","display_name":"Shilei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shilei Huang","raw_affiliation_strings":["Shenzhen Raisound Technologies, Co., Ltd, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Raisound Technologies, Co., Ltd, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014070150","display_name":"Gang Cheng","orcid":"https://orcid.org/0000-0002-0462-3411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Cheng","raw_affiliation_strings":["PKU Shenzhen Institute, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PKU Shenzhen Institute, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"22"},"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":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9865999817848206,"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/overfitting","display_name":"Overfitting","score":0.9041563272476196},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.842116117477417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8098708391189575},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7464576959609985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7388089299201965},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6239290833473206},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5751352906227112},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.5661028623580933},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5376521348953247},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5090357661247253},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4259759783744812},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34396445751190186},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12529179453849792}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9041563272476196},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.842116117477417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098708391189575},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7464576959609985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7388089299201965},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6239290833473206},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5751352906227112},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.5661028623580933},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5376521348953247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5090357661247253},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4259759783744812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34396445751190186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12529179453849792},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp48816.2019.9037692","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp48816.2019.9037692","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2128641064","https://openalex.org/W2149933564","https://openalex.org/W2194775991","https://openalex.org/W2395579298","https://openalex.org/W2617869948","https://openalex.org/W2695712842","https://openalex.org/W2765407302","https://openalex.org/W2772293448","https://openalex.org/W2883935097","https://openalex.org/W2943951031","https://openalex.org/W2949117887","https://openalex.org/W2949935872","https://openalex.org/W2963351448","https://openalex.org/W2963420686","https://openalex.org/W2964121744","https://openalex.org/W4295723153","https://openalex.org/W4299518610","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6682132143","https://openalex.org/W6743731764","https://openalex.org/W6745136726","https://openalex.org/W6752516136","https://openalex.org/W6757751764"],"related_works":["https://openalex.org/W4295815739","https://openalex.org/W2915512385","https://openalex.org/W3196952692","https://openalex.org/W4328026323","https://openalex.org/W2984708981","https://openalex.org/W4390929683","https://openalex.org/W2755231872","https://openalex.org/W4300939921","https://openalex.org/W4205117943","https://openalex.org/W4383097772"],"abstract_inverted_index":{"We":[0],"use":[1],"deep":[2,21],"convolutional":[3],"neural":[4],"network":[5],"via":[6],"transfer":[7],"learning":[8,22,32],"for":[9],"Acoustic":[10,45,111],"Scene":[11],"Classification":[12],"(ASC).":[13],"For":[14],"this":[15],"purpose,":[16],"a":[17],"powerful":[18],"and":[19,96,101],"popular":[20],"architecture":[23],"-":[24],"Residual":[25],"Neural":[26],"Network":[27],"(Resnet)":[28],"is":[29,33,53,70],"adopted.":[30],"Transfer":[31],"used":[34,54],"to":[35,55,61,93],"fine-tune":[36],"the":[37,42,50,63,94,108],"pre-trained":[38],"Resnet":[39],"model":[40],"on":[41,73,107],"TUT":[43,109],"Urban":[44,110],"Scenes":[46,112],"2018":[47,104,113],"dataset.":[48,114],"Furthermore,":[49],"focal":[51],"loss":[52],"improve":[56],"overall":[57],"performance.":[58],"In":[59],"order":[60],"reduce":[62],"chance":[64],"of":[65,82,88,98],"overfitting,":[66],"data":[67],"augmentation":[68],"technique":[69],"applied":[71],"based":[72],"mixup.":[74],"Our":[75],"best":[76],"system":[77,106],"has":[78],"achieved":[79],"an":[80],"improvement":[81],"more":[83],"than":[84],"10%":[85],"in":[86],"terms":[87],"class-wise":[89],"accuracy":[90],"with":[91],"respect":[92],"Detection":[95],"classification":[97],"acoustic":[99],"scenes":[100],"events":[102],"(DCASE)":[103],"baseline":[105]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}