{"id":"https://openalex.org/W2751038687","doi":"https://doi.org/10.1109/icme.2017.8019552","title":"Recognition and retrieval of sound events using sparse coding convolutional neural network","display_name":"Recognition and retrieval of sound events using sparse coding convolutional neural network","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2751038687","doi":"https://doi.org/10.1109/icme.2017.8019552","mag":"2751038687"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2017.8019552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","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/A5072470661","display_name":"Chien-Yao Wang","orcid":"https://orcid.org/0000-0002-2946-8972"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chien-Yao Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039165098","display_name":"Andri Santoso","orcid":"https://orcid.org/0000-0002-3899-750X"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Andri Santoso","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053300977","display_name":"Seksan Mathulaprangsan","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Seksan Mathulaprangsan","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043434615","display_name":"Chin-Chin Chiang","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chin-Chin Chiang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029325015","display_name":"Jia\u2010Ching Wang","orcid":"https://orcid.org/0000-0003-0024-6732"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Ching Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taiwan, R.O.C","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072470661"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":null,"apc_paid":null,"fwci":1.2945,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81687711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"65","issue":null,"first_page":"589","last_page":"594"},"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8350763320922852},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8301480412483215},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6394913792610168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.594563901424408},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5310051441192627},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.5267937779426575},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4602119028568268},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4527554512023926},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.428178071975708},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.425632506608963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8350763320922852},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8301480412483215},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6394913792610168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.594563901424408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5310051441192627},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.5267937779426575},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4602119028568268},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4527554512023926},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.428178071975708},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.425632506608963},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2017.8019552","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2017.8019552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W204268067","https://openalex.org/W1501987291","https://openalex.org/W1822987211","https://openalex.org/W1970578576","https://openalex.org/W1981087263","https://openalex.org/W2005122913","https://openalex.org/W2021228422","https://openalex.org/W2090431713","https://openalex.org/W2098654823","https://openalex.org/W2118230268","https://openalex.org/W2119662931","https://openalex.org/W2124867748","https://openalex.org/W2137561966","https://openalex.org/W2153937809","https://openalex.org/W2160335114","https://openalex.org/W2161755617","https://openalex.org/W2163605009","https://openalex.org/W2182578244","https://openalex.org/W2245569228","https://openalex.org/W2341412280","https://openalex.org/W6608313692","https://openalex.org/W6682665746","https://openalex.org/W6684191040","https://openalex.org/W6690610466"],"related_works":["https://openalex.org/W2962711843","https://openalex.org/W2563053664","https://openalex.org/W2766412668","https://openalex.org/W2766191760","https://openalex.org/W204268067","https://openalex.org/W2258484932","https://openalex.org/W2934488247","https://openalex.org/W2037496786","https://openalex.org/W3160973216","https://openalex.org/W3082776395","https://openalex.org/W2795280371","https://openalex.org/W2735072998","https://openalex.org/W1580467924","https://openalex.org/W2570821783","https://openalex.org/W2095288130","https://openalex.org/W3043911516","https://openalex.org/W2190635018","https://openalex.org/W2740402512","https://openalex.org/W2970085166","https://openalex.org/W2932768905"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,33],"novel":[4],"deep":[5],"convolutional":[6,13],"neural":[7,14],"network":[8,15],"(CNN),":[9],"called":[10],"sparse":[11],"coding":[12],"(SC-CNN),":[16],"to":[17,77],"address":[18],"the":[19,29,43,47,52,63,79,82,86,94,98,108,113,133,136,140,144],"problem":[20],"of":[21,32,81,119,143],"sound":[22,65,102,109],"event":[23,103,110],"recognition":[24,104,111],"and":[25,58,105,122,127],"retrieval":[26,134],"task.":[27],"Unlike":[28],"general":[30,145],"framework":[31,45],"CNN,":[34],"in":[35,51,101],"which":[36],"feature":[37],"learning":[38],"process":[39],"is":[40],"performed":[41],"hierarchically,":[42],"proposed":[44,83,95,114,137],"models":[46],"whole":[48],"memorizing":[49],"procedures":[50],"human":[53],"brain,":[54],"including":[55],"encoding,":[56],"storage,":[57],"recollection.":[59],"Sound":[60],"data":[61],"from":[62,71],"RWCP":[64],"scene":[66],"dataset":[67,74],"with":[68,85],"added":[69],"noise":[70,73,129],"NOISEX-92":[72],"are":[75],"used":[76],"compare":[78],"performance":[80],"system":[84,115,138],"state-of-the-art":[87,99],"baselines.":[88],"The":[89],"experimental":[90],"results":[91],"indicated":[92],"that":[93],"SC-CNN":[96],"outperformed":[97],"systems":[100],"retrieval.":[106],"In":[107,132],"task,":[112,135],"achieved":[116],"an":[117],"accuracy":[118],"94.6%,":[120],"100%":[121,123],"under":[124],"0db,":[125],"10db":[126],"clean":[128],"conditions,":[130],"respectively.":[131],"improves":[139],"mAP":[141],"rate":[142],"CNN":[146],"by":[147],"approximately":[148],"6%.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}