{"id":"https://openalex.org/W2935162632","doi":"https://doi.org/10.1109/jstsp.2019.2909479","title":"Comparison and Analysis of SampleCNN Architectures for Audio Classification","display_name":"Comparison and Analysis of SampleCNN Architectures for Audio Classification","publication_year":2019,"publication_date":"2019-04-04","ids":{"openalex":"https://openalex.org/W2935162632","doi":"https://doi.org/10.1109/jstsp.2019.2909479","mag":"2935162632"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2019.2909479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2909479","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5041721732","display_name":"Taejun Kim","orcid":"https://orcid.org/0000-0002-9312-535X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Taejun Kim","raw_affiliation_strings":["Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049268304","display_name":"Jongpil Lee","orcid":"https://orcid.org/0000-0002-1126-0081"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongpil Lee","raw_affiliation_strings":["Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041721732"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":8.8822,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.98432066,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"13","issue":"2","first_page":"285","last_page":"297"},"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/T13996","display_name":"Diverse Musicological Studies","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9934999942779541,"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/computer-science","display_name":"Computer science","score":0.8071678876876831},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7407076954841614},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5849175453186035},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5674104690551758},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5615189075469971},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.47892674803733826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4588713049888611},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4587341845035553},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4270618259906769},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4234403371810913},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.22132667899131775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10041102766990662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071678876876831},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7407076954841614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5849175453186035},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5674104690551758},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5615189075469971},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.47892674803733826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4588713049888611},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4587341845035553},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4270618259906769},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4234403371810913},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.22132667899131775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10041102766990662},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2019.2909479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2909479","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4341594390","display_name":null,"funder_award_id":"2015R1C1A1A02036962","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W78356000","https://openalex.org/W854541894","https://openalex.org/W1666984270","https://openalex.org/W1686810756","https://openalex.org/W1995562189","https://openalex.org/W2017399882","https://openalex.org/W2045135321","https://openalex.org/W2059652044","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2127870748","https://openalex.org/W2132037657","https://openalex.org/W2133285226","https://openalex.org/W2168249605","https://openalex.org/W2194775991","https://openalex.org/W2242773987","https://openalex.org/W2293255527","https://openalex.org/W2302255633","https://openalex.org/W2398826216","https://openalex.org/W2414894569","https://openalex.org/W2437181147","https://openalex.org/W2508048623","https://openalex.org/W2509065397","https://openalex.org/W2519091744","https://openalex.org/W2520160253","https://openalex.org/W2526050071","https://openalex.org/W2529337537","https://openalex.org/W2541674938","https://openalex.org/W2559688696","https://openalex.org/W2584032004","https://openalex.org/W2592168896","https://openalex.org/W2593179621","https://openalex.org/W2593451766","https://openalex.org/W2618530766","https://openalex.org/W2745969942","https://openalex.org/W2751116311","https://openalex.org/W2752782242","https://openalex.org/W2767858146","https://openalex.org/W2774097455","https://openalex.org/W2775505379","https://openalex.org/W2777662428","https://openalex.org/W2794150026","https://openalex.org/W2797583228","https://openalex.org/W2888641632","https://openalex.org/W2889495247","https://openalex.org/W2905804369","https://openalex.org/W2916979304","https://openalex.org/W2963232038","https://openalex.org/W2963446712","https://openalex.org/W2963451564","https://openalex.org/W2963669405","https://openalex.org/W2963723765","https://openalex.org/W2964137095","https://openalex.org/W2964218314","https://openalex.org/W3027908062","https://openalex.org/W3098357269","https://openalex.org/W3105202226","https://openalex.org/W4229494842","https://openalex.org/W6603161775","https://openalex.org/W6623517193","https://openalex.org/W6637061625","https://openalex.org/W6637373629","https://openalex.org/W6678969435","https://openalex.org/W6689262250","https://openalex.org/W6690394000","https://openalex.org/W6698183232","https://openalex.org/W6712560600","https://openalex.org/W6715395060","https://openalex.org/W6727336983","https://openalex.org/W6729059855","https://openalex.org/W6730401039","https://openalex.org/W6732429163","https://openalex.org/W6734751391","https://openalex.org/W6743647910","https://openalex.org/W6745878906","https://openalex.org/W6746683323","https://openalex.org/W6747331233","https://openalex.org/W6747381837","https://openalex.org/W6750665317"],"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/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W4360764600"],"abstract_inverted_index":{"End-to-end":[0],"learning":[1],"with":[2,69,140,178],"convolutional":[3],"neural":[4],"networks":[5,100],"(CNNs)":[6],"has":[7,42,50],"become":[8],"a":[9],"standard":[10],"approach":[11],"in":[12,16,55,77,162,196,208],"image":[13],"classification.":[14],"However,":[15],"audio":[17,80,145],"classification,":[18],"CNN-based":[19],"models":[20,121],"that":[21,107,169,185,205,222],"use":[22],"time-frequency":[23],"representations":[24],"as":[25],"input":[26],"are":[27],"still":[28],"popular.":[29],"A":[30],"recently":[31],"proposed":[32],"CNN":[33,71],"architecture":[34,49],"called":[35],"SampleCNN":[36,64,91],"takes":[37,186],"raw":[38,187],"waveforms":[39,188],"directly":[40,189],"and":[41,72,84,101,203],"very":[43],"small":[44,141],"sizes":[45],"of":[46,126,160,226],"filters.":[47],"The":[48,104],"proven":[51],"to":[52,92,122,135,144,173,214],"be":[53,174,191],"effective":[54,113],"music":[56,197],"classification":[57],"tasks.":[58],"In":[59],"this":[60,201],"paper,":[61],"we":[62,89,117,130,151],"scrutinize":[63],"further":[65,202],"by":[66,156],"comparing":[67],"it":[68],"spectrogram-based":[70],"changing":[73],"the":[74,108,119,127,138,153,158,170,182,206,209,215],"subsampling":[75],"operation":[76],"three":[78],"different":[79,148,164,224],"domains:":[81],"music,":[82],"speech,":[83],"acoustic":[85,220],"scene":[86],"sound.":[87],"Also,":[88],"extend":[90],"more":[93],"advanced":[94],"versions":[95],"using":[96],"components":[97],"from":[98,147],"residual":[99],"squeeze-and-excitation":[102,109,154],"networks.":[103],"results":[105],"show":[106,204],"block":[110,155],"is":[111,212,218],"particularly":[112,195],"among":[114],"them.":[115],"Furthermore,":[116],"analyze":[118],"trained":[120],"provide":[123],"better":[124],"understanding":[125],"architectures.":[128],"First,":[129],"visualize":[131],"hierarchically":[132],"learned":[133],"features":[134],"see":[136],"how":[137],"filters":[139],"granularity":[142],"adapt":[143],"signals":[146],"domains.":[149],"Second,":[150],"observe":[152],"plotting":[157],"distribution":[159],"excitation":[161,171,207],"several":[163],"ways.":[165],"This":[166],"analysis":[167],"shows":[168],"tends":[172],"increasingly":[175],"class":[176,193],"specific":[177],"increasing":[179],"depth":[180],"but":[181],"first":[183,210],"layer":[184,211],"can":[190],"highly":[192],"specific,":[194],"data.":[198],"We":[199],"examine":[200],"sensitive":[213],"loudness,":[216],"which":[217],"an":[219],"characteristic":[221],"distinguishes":[223],"genres":[225],"music.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}