{"id":"https://openalex.org/W2943951031","doi":"https://doi.org/10.1109/iscslp.2018.8706712","title":"An Investigation of Transfer Learning Mechanism for Acoustic Scene Classification","display_name":"An Investigation of Transfer Learning Mechanism for Acoustic Scene Classification","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2943951031","doi":"https://doi.org/10.1109/iscslp.2018.8706712","mag":"2943951031"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5103235094","display_name":"Hengshun Zhou","orcid":"https://orcid.org/0000-0001-7878-6531"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengshun Zhou","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781916","display_name":"Xue Bai","orcid":"https://orcid.org/0000-0001-9717-846X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Bai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6648,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71779661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"404","last_page":"408"},"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":0.9997000098228455,"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":0.9854000210762024,"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/transfer-of-learning","display_name":"Transfer of learning","score":0.8500661253929138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8166709542274475},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7570086717605591},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.756572961807251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6437040567398071},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6153368353843689},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5483832359313965},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5232897400856018},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.522476077079773},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.47980764508247375},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4744775593280792},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44914063811302185},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4380568265914917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.407377153635025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40182143449783325},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3565974235534668}],"concepts":[{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.8500661253929138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166709542274475},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7570086717605591},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.756572961807251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6437040567398071},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6153368353843689},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5483832359313965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5232897400856018},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.522476077079773},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.47980764508247375},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4744775593280792},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44914063811302185},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4380568265914917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.407377153635025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40182143449783325},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3565974235534668},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1964538581","https://openalex.org/W2103235956","https://openalex.org/W2117539524","https://openalex.org/W2137343183","https://openalex.org/W2165409492","https://openalex.org/W2194775991","https://openalex.org/W2315268655","https://openalex.org/W2561557072","https://openalex.org/W2566935005","https://openalex.org/W2747664154","https://openalex.org/W2804935296","https://openalex.org/W2963451564","https://openalex.org/W6637373629","https://openalex.org/W6752381671"],"related_works":["https://openalex.org/W2589961920","https://openalex.org/W3176438653","https://openalex.org/W2981628807","https://openalex.org/W3012393889","https://openalex.org/W4379875147","https://openalex.org/W3189091156","https://openalex.org/W3014041368","https://openalex.org/W4386087993","https://openalex.org/W4285815841","https://openalex.org/W2786391746"],"abstract_inverted_index":{"One":[0,110],"main":[1],"challenge":[2],"for":[3],"acoustic":[4,17],"scene":[5],"classification":[6,62,97,143,181],"(ASC)":[7],"is":[8,115,187],"there":[9],"are":[10,25,131],"remarkable":[11],"overlaps":[12],"and":[13,106,176],"similarities":[14],"between":[15,93],"different":[16,35,96,158],"scenes.":[18],"However,":[19],"the":[20,39,52,55,60,88,100,116,119,127,134,141,148,154,161,165,180,194,200],"most":[21],"existing":[22],"ASC":[23,167],"tasks":[24,77,98],"always":[26],"lack":[27],"of":[28,54,70,90,102,118,183],"adequate":[29],"training":[30,71,80,177],"data":[31,72,81,178],"to":[32,73,137,164,191,199],"well":[33],"distinguish":[34],"classes,":[36],"especially":[37],"in":[38,83,140,197],"deep":[40],"learning":[41,57,92,150],"approaches,":[42],"such":[43],"as":[44,126],"using":[45,206],"convolutional":[46],"neural":[47],"network":[48],"(CNN).":[49],"Motivated":[50],"by":[51,152,171],"success":[53],"transfer":[56,91,149],"mechanism":[58,151],"from":[59,160,189],"image":[61,104,142],"task":[63,163],"(e.g.,":[64],"ImageNet)":[65],"with":[66,78,99,157],"a":[67],"large":[68],"amount":[69],"other":[74],"computer":[75],"vision":[76],"less":[79],"[1],":[82],"this":[84,114],"study":[85],"we":[86,146],"investigate":[87],"possibility":[89],"two":[94],"quite":[95],"inputs":[101],"2D":[103,128],"signals":[105],"1D":[107],"audio":[108,120,208],"signals.":[109],"strong":[111],"motivation":[112],"behind":[113],"spectrograms":[117],"signal":[121],"can":[122],"be":[123],"also":[124],"considered":[125],"images":[129],"which":[130],"potentially":[132],"have":[133],"similar":[135],"structures":[136],"those":[138],"samples":[139],"task.":[144],"Specifically,":[145],"conduct":[147],"adopting":[153],"pre-trained":[155],"CNNs":[156],"architectures":[159],"ImageNet":[162],"DCASE2018":[166],"subtask":[168],"A.":[169],"Furthermore,":[170],"leveraging":[172],"more":[173],"input":[174],"channels":[175],"fragments,":[179],"accuracy":[182],"our":[184],"proposed":[185],"system":[186,204],"increased":[188],"59.7%":[190],"77.8%":[192],"on":[193],"evaluation":[195],"set,":[196],"comparison":[198],"officially":[201],"provided":[202],"CNN":[203],"trained":[205],"only":[207],"data.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}