{"id":"https://openalex.org/W3118915657","doi":"https://doi.org/10.1145/3444370.3444569","title":"Convolutional Neural Network based Timbre Classification","display_name":"Convolutional Neural Network based Timbre Classification","publication_year":2020,"publication_date":"2020-12-04","ids":{"openalex":"https://openalex.org/W3118915657","doi":"https://doi.org/10.1145/3444370.3444569","mag":"3118915657"},"language":"en","primary_location":{"id":"doi:10.1145/3444370.3444569","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3444370.3444569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Cyberspace Innovation of Advanced Technologies","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/A5044475740","display_name":"Yinyu Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinyu Lyu","raw_affiliation_strings":["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114832420","display_name":"Chenwei Liu","orcid":"https://orcid.org/0009-0009-7683-665X"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenwei Liu","raw_affiliation_strings":["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072794436","display_name":"Hao Tan","orcid":"https://orcid.org/0000-0003-1153-2726"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Tan","raw_affiliation_strings":["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049832804","display_name":"Rui Xie","orcid":"https://orcid.org/0000-0001-9769-8131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Xie","raw_affiliation_strings":["Guangzhou Quwan Network Technology Co., Ltd, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Guangzhou Quwan Network Technology Co., Ltd, Guangzhou, Guangdong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047533842","display_name":"Keke Tang","orcid":"https://orcid.org/0000-0003-0377-1022"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keke Tang","raw_affiliation_strings":["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070856186","display_name":"Zhaoquan Gu","orcid":"https://orcid.org/0000-0001-7546-852X"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoquan Gu","raw_affiliation_strings":["Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China"],"affiliations":[{"raw_affiliation_string":"Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I37987034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044475740"],"corresponding_institution_ids":["https://openalex.org/I37987034"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16853193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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":0.9976999759674072,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8695893883705139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7921435832977295},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7564780712127686},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7288398742675781},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6292981505393982},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6174256801605225},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6042279005050659},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5920621156692505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5816400647163391},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5597565770149231},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5215080380439758},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.421328604221344},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41448843479156494}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8695893883705139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921435832977295},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7564780712127686},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7288398742675781},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6292981505393982},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6174256801605225},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6042279005050659},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5920621156692505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5816400647163391},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5597565770149231},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5215080380439758},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.421328604221344},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41448843479156494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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:10.1145/3444370.3444569","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3444370.3444569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Cyberspace Innovation of Advanced Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1583001605","https://openalex.org/W1686810756","https://openalex.org/W1832693441","https://openalex.org/W1975929202","https://openalex.org/W2052666245","https://openalex.org/W2125324924","https://openalex.org/W2148154194","https://openalex.org/W2157331557","https://openalex.org/W2180612164","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2296283641","https://openalex.org/W2640329709","https://openalex.org/W2765860599","https://openalex.org/W2889065492","https://openalex.org/W2937047963","https://openalex.org/W2963232038","https://openalex.org/W2963625095","https://openalex.org/W2963626623","https://openalex.org/W2988194011","https://openalex.org/W2997617958","https://openalex.org/W3004704879","https://openalex.org/W3026797990","https://openalex.org/W3035736465","https://openalex.org/W3040265205"],"related_works":["https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W2095030957","https://openalex.org/W2066827917","https://openalex.org/W4210742324"],"abstract_inverted_index":{"Artificial":[0],"intelligent":[1],"technologies":[2],"have":[3,17],"been":[4,18],"widely":[5],"adopted":[6,81],"in":[7,20,32,163],"image":[8],"classification,":[9],"natural":[10],"language":[11],"processing,":[12],"etc.":[13],"However,":[14],"few":[15],"works":[16],"conducted":[19],"timbre":[21,29,56,149],"classification":[22,30,138],"of":[23,28,35,57,106,150],"human":[24,58,118,151],"voice.":[25,59],"The":[26,94],"challenges":[27],"lay":[31],"the":[33,55,62,83,89,99,128,148,164],"difficulty":[34],"audio":[36],"denoising":[37],"and":[38,77,85],"feature":[39,68,92],"applicability.":[40],"In":[41],"this":[42,141,155],"paper,":[43],"we":[44,87,153],"propose":[45],"a":[46,117,143,160],"convolutional":[47],"neural":[48],"network":[49,96],"(CNN)":[50],"based":[51],"method":[52,134],"to":[53,69,146],"classify":[54,98,147],"We":[60],"utilize":[61],"Mel":[63],"Frequency":[64],"Cepstral":[65],"Coefficient":[66],"(MFCC)":[67],"better":[70],"represent":[71],"each":[72],"voice":[73,100,105,119,126],"segment.":[74],"Classic":[75],"denoise":[76],"purify":[78],"methods":[79],"are":[80],"for":[82,91,159],"preprocessing,":[84],"then":[86],"use":[88],"CNN":[90],"fusion.":[93],"proposed":[95],"could":[97,135,157],"into":[101],"eight":[102],"categories,":[103],"including":[104],"middle-aged":[107,111],"women,":[108],"young":[109,113],"girls,":[110],"men,":[112],"boys.":[114],"Based":[115],"on":[116],"dataset":[120],"which":[121],"contains":[122],"more":[123],"than":[124],"10,000":[125],"segments,":[127],"experiment":[129],"results":[130],"show":[131],"that":[132],"our":[133],"achieve":[136],"63.5%":[137],"accuracy.":[139],"As":[140],"is":[142],"new":[144],"direction":[145],"voice,":[152],"hope":[154],"paper":[156],"stand":[158],"pioneering":[161],"work":[162],"field.":[165]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}