{"id":"https://openalex.org/W2772728560","doi":"https://doi.org/10.1587/transinf.2017edl8132","title":"A Novel Discriminative Feature Extraction for Acoustic Scene Classification Using RNN Based Source Separation","display_name":"A Novel Discriminative Feature Extraction for Acoustic Scene Classification Using RNN Based Source Separation","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2772728560","doi":"https://doi.org/10.1587/transinf.2017edl8132","mag":"2772728560"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2017edl8132","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edl8132","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/12/E100.D_2017EDL8132/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/12/E100.D_2017EDL8132/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021831317","display_name":"Seongkyu Mun","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seongkyu MUN","raw_affiliation_strings":["Department of Visual Information Processing, Korea University"],"affiliations":[{"raw_affiliation_string":"Department of Visual Information Processing, Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suwon SHON","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory (CSAIL), MIT"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory (CSAIL), MIT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977970","display_name":"Wooil Kim","orcid":"https://orcid.org/0000-0002-3854-2783"},"institutions":[{"id":"https://openalex.org/I146429904","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935","country_code":"KR","type":"education","lineage":["https://openalex.org/I146429904"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wooil KIM","raw_affiliation_strings":["Dept. of Computer Science and Engineering, Incheon National University"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, Incheon National University","institution_ids":["https://openalex.org/I146429904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102000970","display_name":"David K. Han","orcid":"https://orcid.org/0000-0001-5055-5408"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"David K. HAN","raw_affiliation_strings":["School of Electrical Engineering, Korea University"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026204977","display_name":"Hanseok Ko","orcid":"https://orcid.org/0000-0002-8744-4514"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hanseok KO","raw_affiliation_strings":["Department of Visual Information Processing, Korea University","School of Electrical Engineering, Korea University"],"affiliations":[{"raw_affiliation_string":"Department of Visual Information Processing, Korea University","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Electrical Engineering, Korea University","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021831317"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":1.6811,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86025185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"E100.D","issue":"12","first_page":"3041","last_page":"3044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.989300012588501,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.9223495721817017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8372998833656311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6833240985870361},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6652615070343018},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6294636726379395},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.562584638595581},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.545769453048706},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.490624338388443},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44048571586608887},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41343069076538086},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35141605138778687},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3027321696281433},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05617550015449524}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9223495721817017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8372998833656311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6833240985870361},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6652615070343018},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6294636726379395},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.562584638595581},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.545769453048706},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.490624338388443},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44048571586608887},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41343069076538086},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35141605138778687},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3027321696281433},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05617550015449524},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2017edl8132","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edl8132","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/12/E100.D_2017EDL8132/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2017edl8132","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edl8132","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/12/E100.D_2017EDL8132/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3392305090","display_name":null,"funder_award_id":"-16-1-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G3591598716","display_name":null,"funder_award_id":"FA2386","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2772728560.pdf","grobid_xml":"https://content.openalex.org/works/W2772728560.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1846473900","https://openalex.org/W2031647436","https://openalex.org/W2161381512","https://openalex.org/W2187089797","https://openalex.org/W2509990657","https://openalex.org/W2517626051","https://openalex.org/W2566935005","https://openalex.org/W2593451766","https://openalex.org/W2695712842"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"Various":[0],"types":[1],"of":[2,22,34,143,153,179],"classifiers":[3,189],"and":[4,20,25],"feature":[5,77,172],"extraction":[6,78],"methods":[7],"for":[8,116,190],"acoustic":[9],"scene":[10],"classification":[11,122,176],"have":[12,39],"been":[13],"recently":[14],"proposed":[15,171],"in":[16,52,98],"the":[17,35,72,94,121,126,129,138,141,144,154,183,191],"IEEE":[18],"Detection":[19],"Classification":[21],"Acoustic":[23],"Scenes":[24],"Events":[26],"(DCASE)":[27],"2016":[28],"Challenge":[29],"Task":[30],"1.":[31],"The":[32,170],"results":[33],"final":[36],"evaluation,":[37],"however,":[38],"shown":[40],"that":[41,128],"even":[42,68],"top":[43],"10":[44],"ranked":[45],"teams,":[46,86],"showed":[47],"extremely":[48],"low":[49,95],"accuracy":[50],"performance":[51,90,96],"particular":[53],"class":[54,100,118,193],"pairs":[55],"with":[56],"similar":[57,99,192],"sounds.":[58],"Due":[59],"to":[60,66,106,120,149,161,182],"such":[61],"sound":[62,135],"classes":[63],"being":[64],"difficult":[65],"distinguish":[67],"by":[69,82],"human":[70],"ears,":[71],"conventional":[73,184],"deep":[74],"learning":[75],"based":[76,113],"methods,":[79],"as":[80,166],"used":[81],"most":[83],"DCASE":[84],"participating":[85],"are":[87],"considered":[88,148],"facing":[89],"limitations.":[91],"To":[92],"address":[93],"problem":[97],"pair":[101,194],"cases,":[102],"this":[103,158,163],"letter":[104,159],"proposes":[105,160],"employ":[107],"a":[108],"recurrent":[109],"neural":[110],"network":[111],"(RNN)":[112],"source":[114],"separation":[115],"each":[117],"prior":[119],"step.":[123],"Based":[124],"on":[125],"fact":[127],"system":[130],"can":[131,146],"effectively":[132],"extract":[133],"trained":[134,155],"components":[136],"using":[137],"RNN":[139,145],"structure,":[140],"mid-layer":[142,164],"be":[147],"capture":[150],"discriminative":[151,168],"information":[152,165],"class.":[156],"Therefore,":[157],"use":[162],"novel":[167],"features.":[169],"shows":[173],"an":[174],"average":[175],"rate":[177],"improvement":[178],"2.3%":[180],"compared":[181],"method,":[185],"which":[186],"uses":[187],"additional":[188],"issue.":[195]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}