{"id":"https://openalex.org/W2953763392","doi":"https://doi.org/10.1186/s13636-019-0155-y","title":"Music detection from broadcast contents using convolutional neural networks with a Mel-scale kernel","display_name":"Music detection from broadcast contents using convolutional neural networks with a Mel-scale kernel","publication_year":2019,"publication_date":"2019-06-26","ids":{"openalex":"https://openalex.org/W2953763392","doi":"https://doi.org/10.1186/s13636-019-0155-y","mag":"2953763392"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-019-0155-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-019-0155-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0155-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0155-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041497526","display_name":"Byeong-Yong Jang","orcid":null},"institutions":[{"id":"https://openalex.org/I163753206","display_name":"Chungbuk National University","ror":"https://ror.org/02wnxgj78","country_code":"KR","type":"education","lineage":["https://openalex.org/I163753206"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Byeong-Yong Jang","raw_affiliation_strings":["School of Electronics Engineering, Chungbuk National University, Cheongju, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics Engineering, Chungbuk National University, Cheongju, South Korea","institution_ids":["https://openalex.org/I163753206"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012083888","display_name":"Woon-Haeng Heo","orcid":null},"institutions":[{"id":"https://openalex.org/I163753206","display_name":"Chungbuk National University","ror":"https://ror.org/02wnxgj78","country_code":"KR","type":"education","lineage":["https://openalex.org/I163753206"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woon-Haeng Heo","raw_affiliation_strings":["School of Electronics Engineering, Chungbuk National University, Cheongju, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics Engineering, Chungbuk National University, Cheongju, South Korea","institution_ids":["https://openalex.org/I163753206"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349772","display_name":"Jung-Hyun Kim","orcid":"https://orcid.org/0000-0002-9500-1537"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-Hyun Kim","raw_affiliation_strings":["ETRI (Electronics and Telecommunications Research Institute), Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI (Electronics and Telecommunications Research Institute), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000031464","display_name":"Oh\u2010Wook Kwon","orcid":"https://orcid.org/0000-0002-5301-126X"},"institutions":[{"id":"https://openalex.org/I163753206","display_name":"Chungbuk National University","ror":"https://ror.org/02wnxgj78","country_code":"KR","type":"education","lineage":["https://openalex.org/I163753206"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Oh-Wook Kwon","raw_affiliation_strings":["School of Electronics Engineering, Chungbuk National University, Cheongju, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-5301-126X","affiliations":[{"raw_affiliation_string":"School of Electronics Engineering, Chungbuk National University, Cheongju, South Korea","institution_ids":["https://openalex.org/I163753206"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041497526"],"corresponding_institution_ids":["https://openalex.org/I163753206"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.6713,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90946753,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"2019","issue":"1","first_page":null,"last_page":null},"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":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9936000108718872,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7412911653518677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7021294832229614},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.621850848197937},{"id":"https://openalex.org/keywords/broadcasting","display_name":"Broadcasting (networking)","score":0.5585858821868896},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5086830258369446},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.45343390107154846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4372478127479553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4350525736808777},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3610406517982483},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3433544337749481},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09125819802284241},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08864632248878479},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08326613903045654}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7412911653518677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7021294832229614},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.621850848197937},{"id":"https://openalex.org/C110157686","wikidata":"https://www.wikidata.org/wiki/Q922122","display_name":"Broadcasting (networking)","level":2,"score":0.5585858821868896},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5086830258369446},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.45343390107154846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4372478127479553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4350525736808777},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3610406517982483},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3433544337749481},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09125819802284241},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08864632248878479},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08326613903045654},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-019-0155-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-019-0155-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0155-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e2c0e3ab9d1f482c911485be849b7387","is_oa":true,"landing_page_url":"https://doaj.org/article/e2c0e3ab9d1f482c911485be849b7387","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2019, Iss 1, Pp 1-12 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-019-0155-y","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-019-0155-y","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0155-y","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6693565195","display_name":null,"funder_award_id":"2018-micro-9500","funder_id":"https://openalex.org/F4320322006","funder_display_name":"Ministry of Culture, Sports and Tourism"}],"funders":[{"id":"https://openalex.org/F4320322006","display_name":"Ministry of Culture, Sports and Tourism","ror":"https://ror.org/02fkk6k65"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953763392.pdf","grobid_xml":"https://content.openalex.org/works/W2953763392.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W62719046","https://openalex.org/W180242331","https://openalex.org/W752647049","https://openalex.org/W1875231349","https://openalex.org/W1969154851","https://openalex.org/W2052666245","https://openalex.org/W2064675550","https://openalex.org/W2133049755","https://openalex.org/W2142171915","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2157331557","https://openalex.org/W2166481862","https://openalex.org/W2187012839","https://openalex.org/W2207975468","https://openalex.org/W2219249508","https://openalex.org/W2414894569","https://openalex.org/W2568529987","https://openalex.org/W2774707525","https://openalex.org/W2800448574","https://openalex.org/W2899551440","https://openalex.org/W3145668479","https://openalex.org/W4251502187","https://openalex.org/W4398958419","https://openalex.org/W6600719526","https://openalex.org/W6688816777"],"related_works":["https://openalex.org/W4239286941","https://openalex.org/W2088845016","https://openalex.org/W589102260","https://openalex.org/W1966421350","https://openalex.org/W1868434454","https://openalex.org/W4366985237","https://openalex.org/W4367365565","https://openalex.org/W2128396103","https://openalex.org/W4367299891","https://openalex.org/W2810569973"],"abstract_inverted_index":{"We":[0,73],"propose":[1],"a":[2,17,47,170],"new":[3],"method":[4,131],"for":[5,102,151,156],"music":[6,24,99,161],"detection":[7,22,162],"from":[8,29,149],"broadcasting":[9],"contents":[10],"using":[11,173],"the":[12,30,62,66,70,87,138,142,146],"convolutional":[13,41,48,88],"neural":[14,42],"networks":[15],"with":[16,50,177],"Mel-scale":[18,60],"kernel.":[19],"In":[20],"this":[21],"task,":[23],"segments":[25],"should":[26],"be":[27],"annotated":[28],"broadcast":[31,79,95,121],"data,":[32],"where":[33],"music,":[34],"speech,":[35],"and":[36,65,90,116,126,145],"noise":[37],"are":[38,120],"mixed.":[39],"The":[40,59,104,129],"network":[43,89],"is":[44,53],"composed":[45],"of":[46,77,83,93,98,100,108],"layer":[49],"kernel":[51,63,71],"that":[52,119],"trained":[54],"to":[55,85,154,168],"extract":[56],"robust":[57],"features.":[58],"changes":[61],"size,":[64],"backpropagation":[67],"algorithm":[68],"trains":[69],"shape.":[72],"used":[74],"52":[75],"h":[76,82,92],"mixed":[78],"data":[80,96,106,153],"(25":[81],"music)":[84],"train":[86],"24":[91],"collected":[94],"(ratio":[97],"50\u201376%)":[101],"testing.":[103],"test":[105],"consisted":[107],"various":[109],"genres":[110],"(drama,":[111],"documentary,":[112],"news,":[113],"kids,":[114],"reality,":[115],"so":[117],"on)":[118],"in":[122,136],"British":[123,152],"English,":[124],"Spanish,":[125],"Korean":[127,157],"languages.":[128],"proposed":[130],"consistently":[132],"showed":[133],"better":[134],"performance":[135],"all":[137],"three":[139],"languages":[140],"than":[141],"baseline":[143],"system,":[144],"F-score":[147],"ranged":[148],"86.5%":[150],"95.9%":[155],"drama":[158],"data.":[159],"Our":[160],"system":[163],"takes":[164],"about":[165],"28":[166],"s":[167],"process":[169],"1-min":[171],"signal":[172],"only":[174],"one":[175],"CPU":[176],"4":[178],"cores.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
