{"id":"https://openalex.org/W3004586199","doi":"https://doi.org/10.3390/e22020183","title":"Robust Audio Content Classification Using Hybrid-Based SMD and Entropy-Based VAD","display_name":"Robust Audio Content Classification Using Hybrid-Based SMD and Entropy-Based VAD","publication_year":2020,"publication_date":"2020-02-06","ids":{"openalex":"https://openalex.org/W3004586199","doi":"https://doi.org/10.3390/e22020183","mag":"3004586199","pmid":"https://pubmed.ncbi.nlm.nih.gov/33285958"},"language":"en","primary_location":{"id":"doi:10.3390/e22020183","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e22020183","pdf_url":"https://www.mdpi.com/1099-4300/22/2/183/pdf","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/22/2/183/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033706944","display_name":"Kun-Ching Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I14140830","display_name":"Shih Chien University","ror":"https://ror.org/01c3hyk82","country_code":"TW","type":"education","lineage":["https://openalex.org/I14140830"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kun-Ching Wang","raw_affiliation_strings":["Department of Information Technology & Communication, Shih Chien University, No. 200, University Rd, Neimen Shiang, Kaohsiung 845, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-6478-7277","affiliations":[{"raw_affiliation_string":"Department of Information Technology & Communication, Shih Chien University, No. 200, University Rd, Neimen Shiang, Kaohsiung 845, Taiwan","institution_ids":["https://openalex.org/I14140830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5033706944"],"corresponding_institution_ids":["https://openalex.org/I14140830"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":1.2156,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.78514987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"22","issue":"2","first_page":"183","last_page":"183"},"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":0.9994999766349792,"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":0.9843000173568726,"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/computer-science","display_name":"Computer science","score":0.7598628997802734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.636482834815979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5903685092926025},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5566384792327881},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5511139631271362},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.533933162689209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49632006883621216},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46521735191345215},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4199378490447998},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.35923904180526733},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10700729489326477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598628997802734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.636482834815979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5903685092926025},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5566384792327881},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5511139631271362},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.533933162689209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49632006883621216},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46521735191345215},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4199378490447998},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.35923904180526733},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10700729489326477},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/e22020183","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e22020183","pdf_url":"https://www.mdpi.com/1099-4300/22/2/183/pdf","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:33285958","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33285958","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:bdf40359a69c499c80290210d20f25d4","is_oa":true,"landing_page_url":"https://doaj.org/article/bdf40359a69c499c80290210d20f25d4","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":"Entropy, Vol 22, Iss 2, p 183 (2020)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/22/2/183/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/e22020183","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7516611","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7516611","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e22020183","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e22020183","pdf_url":"https://www.mdpi.com/1099-4300/22/2/183/pdf","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3004586199.pdf"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W65148590","https://openalex.org/W145358992","https://openalex.org/W1505126044","https://openalex.org/W1517697860","https://openalex.org/W1519655822","https://openalex.org/W1540466161","https://openalex.org/W1565658805","https://openalex.org/W1600222083","https://openalex.org/W1600232100","https://openalex.org/W1780815862","https://openalex.org/W1799119298","https://openalex.org/W1861213619","https://openalex.org/W1966311970","https://openalex.org/W1970394202","https://openalex.org/W1985242443","https://openalex.org/W2009598409","https://openalex.org/W2010305198","https://openalex.org/W2015011382","https://openalex.org/W2020619593","https://openalex.org/W2027535990","https://openalex.org/W2028875692","https://openalex.org/W2034356580","https://openalex.org/W2041297902","https://openalex.org/W2043843997","https://openalex.org/W2047812872","https://openalex.org/W2049589395","https://openalex.org/W2057613716","https://openalex.org/W2060862437","https://openalex.org/W2062139369","https://openalex.org/W2062609023","https://openalex.org/W2073693905","https://openalex.org/W2077662469","https://openalex.org/W2086233697","https://openalex.org/W2090431713","https://openalex.org/W2091432990","https://openalex.org/W2093612963","https://openalex.org/W2097036989","https://openalex.org/W2098265087","https://openalex.org/W2106339924","https://openalex.org/W2111331420","https://openalex.org/W2113477260","https://openalex.org/W2119240702","https://openalex.org/W2121961612","https://openalex.org/W2124867748","https://openalex.org/W2126693545","https://openalex.org/W2128838222","https://openalex.org/W2129120544","https://openalex.org/W2131981197","https://openalex.org/W2133824856","https://openalex.org/W2135098570","https://openalex.org/W2136251662","https://openalex.org/W2137449599","https://openalex.org/W2139689188","https://openalex.org/W2141063921","https://openalex.org/W2144345993","https://openalex.org/W2148128296","https://openalex.org/W2149799225","https://openalex.org/W2150125142","https://openalex.org/W2159549127","https://openalex.org/W2160424608","https://openalex.org/W2168441989","https://openalex.org/W2181253919","https://openalex.org/W2295300449","https://openalex.org/W2305675433","https://openalex.org/W2406898624","https://openalex.org/W2514787611","https://openalex.org/W2528063314","https://openalex.org/W2545845972","https://openalex.org/W2563884242","https://openalex.org/W2568529987","https://openalex.org/W2754746744","https://openalex.org/W2766033778","https://openalex.org/W2780268584","https://openalex.org/W2794150026","https://openalex.org/W2919115771","https://openalex.org/W4246413347","https://openalex.org/W6602619388","https://openalex.org/W6634086901","https://openalex.org/W6678381582","https://openalex.org/W6681435915"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W1980100242","https://openalex.org/W2109142991","https://openalex.org/W1781713806","https://openalex.org/W2350061705"],"abstract_inverted_index":{"A":[0],"robust":[1],"approach":[2,49],"for":[3],"the":[4,36,42,111,118,121,137,140,158,194,203,207],"application":[5],"of":[6,51,86,120,130,139,209],"audio":[7,38,75,145,210],"content":[8,211],"classification":[9,119],"(ACC)":[10],"is":[11,66,82,108,115,132,146,169,177],"proposed":[12,204],"in":[13,17,35,183],"this":[14],"paper,":[15],"especially":[16],"variable":[18,185],"noise-level":[19,186],"conditions.":[20],"We":[21],"know":[22],"that":[23,157,202],"speech,":[24,151],"music,":[25],"and":[26,61,76,92,152,166,176,197],"background":[27],"noise":[28,77],"(also":[29],"called":[30],"silence)":[31],"are":[32,97],"usually":[33],"mixed":[34],"noisy":[37,74,144],"signal.":[39],"Based":[40],"on":[41],"findings,":[43],"we":[44],"propose":[45],"a":[46,101,127,184],"hierarchical":[47,159],"ACC":[48,141,160],"consisting":[50],"three":[52,173],"parts:":[53],"voice":[54],"activity":[55],"detection":[56],"(VAD),":[57],"speech/music":[58],"discrimination":[59],"(SMD),":[60],"post-processing.":[62],"First,":[63],"entropy-based":[64,167],"VAD":[65,168,195],"successfully":[67,147,170],"used":[68],"to":[69,134],"segment":[70],"input":[71,116],"signal":[72],"into":[73,117,149],"even":[78,182],"if":[79],"variable-noise":[80],"level":[81],"happening.":[83],"The":[84,105,143],"determinations":[85],"one-dimensional":[87],"(1D)-subband":[88],"energy":[89],"information":[90,95],"(1D-SEI)":[91],"2D-textural":[93],"image":[94],"(2D-TII)":[96],"then":[98],"formed":[99],"as":[100],"hybrid":[102,112,163,198],"feature":[103,113],"set.":[104],"hybrid-based":[106],"SMD":[107,165],"achieved":[109],"because":[110],"set":[114],"support":[122],"vector":[123],"machine":[124],"(SVM).":[125],"Finally,":[126],"rule-based":[128],"post-processing":[129],"segments":[131],"utilized":[133],"smoothly":[135],"determine":[136],"output":[138],"system.":[142],"classified":[148],"noise,":[150],"music.":[153],"Experimental":[154],"results":[155,192],"show":[156],"system":[161],"using":[162],"feature-based":[164],"evaluated":[171],"against":[172],"available":[174],"datasets":[175],"comparable":[178],"with":[179,193],"existing":[180],"methods":[181],"environment.":[187],"In":[188],"addition,":[189],"our":[190],"test":[191],"scheme":[196],"features":[199],"also":[200],"shows":[201],"architecture":[205],"increases":[206],"performance":[208],"discrimination.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}