{"id":"https://openalex.org/W3012522686","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023314","title":"Mixture of CNN Experts from Multiple Acoustic Feature Domain for Music Genre Classification","display_name":"Mixture of CNN Experts from Multiple Acoustic Feature Domain for Music Genre Classification","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012522686","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023314","mag":"3012522686"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5052533101","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-3233-0907"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yang Yi","raw_affiliation_strings":["National Taiwan University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603153","display_name":"Kuan\u2010Yu Chen","orcid":"https://orcid.org/0000-0002-6036-2199"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Yu Chen","raw_affiliation_strings":["National Taiwan University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112041866","display_name":"Hung\u2010Yan Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yan Gu","raw_affiliation_strings":["National Taiwan University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":1.1469,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79322207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1250","last_page":"1255"},"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":0.9987000226974487,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9940999746322632,"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":0.9001554846763611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7663872241973877},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6080927848815918},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5583072304725647},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5526559352874756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.480966717004776},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4682624936103821},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4437616765499115},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4406394362449646},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42056334018707275},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4200291633605957},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4165481626987457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39064040780067444},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3865067660808563}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9001554846763611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663872241973877},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6080927848815918},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5583072304725647},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5526559352874756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.480966717004776},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4682624936103821},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4437616765499115},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4406394362449646},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42056334018707275},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4200291633605957},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4165481626987457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39064040780067444},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3865067660808563},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1561135842","https://openalex.org/W1587265085","https://openalex.org/W1997120337","https://openalex.org/W2012296273","https://openalex.org/W2040710738","https://openalex.org/W2056680352","https://openalex.org/W2108945853","https://openalex.org/W2113968275","https://openalex.org/W2128196382","https://openalex.org/W2133824856","https://openalex.org/W2144383041","https://openalex.org/W2191779130","https://openalex.org/W2293255527","https://openalex.org/W2293626685","https://openalex.org/W2461724944","https://openalex.org/W2573191521","https://openalex.org/W2580221632","https://openalex.org/W2592168896","https://openalex.org/W2604959036","https://openalex.org/W2747932385","https://openalex.org/W2756184659","https://openalex.org/W2765325162","https://openalex.org/W2891628540","https://openalex.org/W2962904371","https://openalex.org/W2963232038","https://openalex.org/W2963451564","https://openalex.org/W2963550089","https://openalex.org/W2963707325","https://openalex.org/W3105202226","https://openalex.org/W4300957348","https://openalex.org/W6633727632","https://openalex.org/W6676520711","https://openalex.org/W6678901678","https://openalex.org/W6687152286","https://openalex.org/W6696747389","https://openalex.org/W6719125919","https://openalex.org/W6732495866","https://openalex.org/W6732646663","https://openalex.org/W6736327223","https://openalex.org/W6744511850","https://openalex.org/W6745586488","https://openalex.org/W6785932716"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W3135448569"],"abstract_inverted_index":{"In":[0,65,165],"the":[1,18,70,88,121,145,148,188,192,203,214,217,230,253],"field":[2],"of":[3,15,72,78,84,95,103,113,216],"music":[4,19,30,61,85,161],"information":[5,16],"retrieval":[6],"(MIR),":[7],"audio":[8],"spectrogram":[9,50],"can":[10,116,200,235],"carry":[11],"a":[12,25,101,111,135,155,159,166,195,248],"great":[13],"deal":[14],"about":[17],"content":[20],"so":[21],"as":[22,60,130],"to":[23,44,74,80,141,153,162,212,246,252],"be":[24,117,163],"robust":[26],"visual":[27],"representation":[28],"for":[29,87,158,187,206],"signal.":[31],"Recently,":[32],"many":[33],"research":[34,73],"literatures":[35],"show":[36],"that":[37,229],"convolutional":[38],"neural":[39,136],"network":[40],"(CNN)":[41],"has":[42,244],"ability":[43,245],"capture":[45],"indicative":[46],"acoustic":[47],"patterns":[48],"from":[49,147],"input,":[51],"and":[52,143,151],"make":[53],"remarkable":[54],"performance":[55,215],"on":[56],"MIR-related":[57],"tasks":[58],"such":[59],"genre":[62,86],"classification":[63,250],"(MGC).":[64],"this":[66,99,172],"paper,":[67,100],"we":[68,126,181],"continue":[69],"line":[71],"explore":[75],"different":[76,82],"types":[77],"spectrograms,":[79],"emphasize":[81],"characteristics":[83],"MGC":[89,114,189,218],"task.":[90,190],"To":[91],"jointly":[92],"leverage":[93],"all":[94],"these":[96],"features,":[97],"in":[98,171],"mixture":[102,137],"experts":[104],"(MoE)":[105],"system":[106],"is":[107,139,210,222],"proposed.":[108],"More":[109],"formally,":[110],"set":[112],"models":[115],"derived":[118],"by":[119],"using":[120],"various":[122],"spectrogram-based":[123,185],"statistics.":[124],"Then":[125],"treat":[127],"each":[128,207],"model":[129,138],"an":[131],"individual":[132,240],"expert.":[133],"Accordingly,":[134],"introduced":[140],"collect":[142],"compile":[144],"predictions":[146],"expert":[149,208,241],"models,":[150,242],"then":[152],"output":[154],"final":[156],"decision":[157],"given":[160],"predicted.":[164],"nutshell,":[167],"our":[168],"major":[169],"contributions":[170],"paper":[173],"are":[174],"at":[175,224],"least":[176],"twofold.":[177],"On":[178,191],"one":[179],"hand,":[180,194],"comprehensively":[182],"examine":[183],"several":[184],"features":[186],"other":[193],"neural-based":[196],"MoE":[197],"system,":[198,209],"which":[199],"dynamically":[201],"decide":[202],"weighting":[204],"factor":[205],"proposed":[211,231],"enhance":[213],"task11The":[219],"source":[220],"code":[221],"available":[223],"https://github.com/superlyy/apsipa_2019..":[225],"Experimental":[226],"results":[227,238],"demonstrate":[228],"framework":[232],"not":[233],"only":[234],"achieve":[236],"success":[237],"than":[239],"but":[243],"provide":[247],"comparable":[249],"accuracy":[251],"SOTA":[254],"systems.":[255]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}