{"id":"https://openalex.org/W4402592916","doi":"https://doi.org/10.1109/icce-taiwan62264.2024.10674594","title":"Acoustic Scene Classification Using Perceptually Weighted Log Mel Spectrogram and Buttom-up Broadcast Neural Network","display_name":"Acoustic Scene Classification Using Perceptually Weighted Log Mel Spectrogram and Buttom-up Broadcast Neural Network","publication_year":2024,"publication_date":"2024-07-09","ids":{"openalex":"https://openalex.org/W4402592916","doi":"https://doi.org/10.1109/icce-taiwan62264.2024.10674594"},"language":"en","primary_location":{"id":"doi:10.1109/icce-taiwan62264.2024.10674594","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce-taiwan62264.2024.10674594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","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/A5098993598","display_name":"Riyad Ali Ahmad Abuirbaiha","orcid":null},"institutions":[{"id":"https://openalex.org/I59460038","display_name":"Chung Hua University","ror":"https://ror.org/01yzz0f51","country_code":"TW","type":"education","lineage":["https://openalex.org/I59460038"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Riyad Ali Ahmad Abuirbaiha","raw_affiliation_strings":["Chung Hua University,Ph.D. Program in Engineering Science,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"Chung Hua University,Ph.D. Program in Engineering Science,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I59460038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010660600","display_name":"Chang-Hsing Lee","orcid":"https://orcid.org/0000-0002-5761-421X"},"institutions":[{"id":"https://openalex.org/I12213908","display_name":"Ming Chi University of Technology","ror":"https://ror.org/04xgh4d03","country_code":"TW","type":"education","lineage":["https://openalex.org/I12213908"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chang-Hsing Lee","raw_affiliation_strings":["Ming Chi University of Technology,Bachelor Program in Industrial Artificial Intelligence,New Taipei City,Taiwan"],"affiliations":[{"raw_affiliation_string":"Ming Chi University of Technology,Bachelor Program in Industrial Artificial Intelligence,New Taipei City,Taiwan","institution_ids":["https://openalex.org/I12213908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111566930","display_name":"Cheng Chang Lien","orcid":null},"institutions":[{"id":"https://openalex.org/I59460038","display_name":"Chung Hua University","ror":"https://ror.org/01yzz0f51","country_code":"TW","type":"education","lineage":["https://openalex.org/I59460038"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng Chang Lien","raw_affiliation_strings":["Chung Hua University,Department of Computer Science and Information Engineering,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"Chung Hua University,Department of Computer Science and Information Engineering,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I59460038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5098993598"],"corresponding_institution_ids":["https://openalex.org/I59460038"],"apc_list":null,"apc_paid":null,"fwci":0.375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56558518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"643","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9391000270843506,"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":0.9391000270843506,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9340999722480774,"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/spectrogram","display_name":"Spectrogram","score":0.9352491497993469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7092998027801514},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6751748323440552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5576350092887878},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5382660627365112},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.524266242980957}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9352491497993469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092998027801514},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6751748323440552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5576350092887878},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5382660627365112},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.524266242980957}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce-taiwan62264.2024.10674594","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce-taiwan62264.2024.10674594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2979158918","https://openalex.org/W3039519447","https://openalex.org/W3040156878","https://openalex.org/W3097525302","https://openalex.org/W3124121033","https://openalex.org/W3131479716","https://openalex.org/W3159360372","https://openalex.org/W4318831574","https://openalex.org/W4387448621","https://openalex.org/W4390660297"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"The":[0,38],"study":[1],"explores":[2],"various":[3],"2D":[4,26,47],"feature":[5,27],"representations":[6,28],"including":[7],"spectrogram,":[8,10],"MFCC":[9],"log":[11,17],"Mel-spectrogram,":[12],"and":[13,60,66,76],"the":[14,50,64,72],"perceptual":[15],"weighted":[16],"Mel-spectrogram":[18],"(PW-LMSP)":[19],"for":[20],"acoustic":[21],"scene":[22],"classification":[23],"(ASC).":[24],"These":[25],"were":[29],"classified":[30],"using":[31],"a":[32],"bottom-up":[33],"broadcast":[34],"neural":[35],"network":[36],"(BBNN).":[37],"experimental":[39],"results":[40],"have":[41],"shown":[42],"that":[43],"PW-LMSP":[44],"outperforms":[45],"other":[46],"representations.":[48],"Further,":[49],"proposed":[51],"method":[52],"(PW-LMSP":[53],"with":[54],"BBNN)":[55],"achieves":[56],"accuracies":[57],"of":[58],"91.2%":[59],"91.6%":[61],"respectively":[62],"on":[63],"DCASE2018":[65,75],"DCASE2019":[67],"development":[68],"datasets,":[69],"outperforming":[70],"all":[71],"submissions":[73],"in":[74],"DCASE2019,":[77],"as":[78,80],"well":[79],"state-of-the-art":[81],"approaches.":[82]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
