{"id":"https://openalex.org/W2052407284","doi":"https://doi.org/10.1109/siu.2012.6204616","title":"Classification of audios containing speech and music","display_name":"Classification of audios containing speech and music","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W2052407284","doi":"https://doi.org/10.1109/siu.2012.6204616","mag":"2052407284"},"language":"en","primary_location":{"id":"doi:10.1109/siu.2012.6204616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","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/A5057085782","display_name":"Erkam Uzun","orcid":"https://orcid.org/0000-0001-5185-7723"},"institutions":[{"id":"https://openalex.org/I13236232","display_name":"TOBB University of Economics and Technology","ror":"https://ror.org/03ewx7v96","country_code":"TR","type":"education","lineage":["https://openalex.org/I13236232"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Erkam Uzun","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, TOBB Ekonomi ve Teknoloji \u00dcniversitesi","Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, TOBB Ekonomi ve Teknoloji \u00dcniversitesi, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, TOBB Ekonomi ve Teknoloji \u00dcniversitesi","institution_ids":["https://openalex.org/I13236232"]},{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, TOBB Ekonomi ve Teknoloji \u00dcniversitesi, Turkey","institution_ids":["https://openalex.org/I13236232"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086101517","display_name":"H\u00fcsrev Taha Sencar","orcid":"https://orcid.org/0000-0001-6910-6194"},"institutions":[{"id":"https://openalex.org/I13236232","display_name":"TOBB University of Economics and Technology","ror":"https://ror.org/03ewx7v96","country_code":"TR","type":"education","lineage":["https://openalex.org/I13236232"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Husrev Taha Sencar","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, TOBB Ekonomi ve Teknoloji \u00dcniversitesi, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, TOBB Ekonomi ve Teknoloji \u00dcniversitesi, Turkey","institution_ids":["https://openalex.org/I13236232"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I13236232"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"103","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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":0.7720624208450317},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7306172847747803},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5837361812591553},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5522413849830627},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4909072518348694},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4721781313419342},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4410955011844635},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4154214859008789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38586336374282837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720624208450317},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7306172847747803},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5837361812591553},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5522413849830627},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4909072518348694},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4721781313419342},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4410955011844635},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4154214859008789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38586336374282837},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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:10.1109/siu.2012.6204616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5099999904632568},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W59771946","https://openalex.org/W110296819","https://openalex.org/W131293899","https://openalex.org/W2038860710","https://openalex.org/W2128838222","https://openalex.org/W2137089646","https://openalex.org/W2145756175","https://openalex.org/W2163181067","https://openalex.org/W2170624490","https://openalex.org/W6604454234","https://openalex.org/W6605236737","https://openalex.org/W6679311584"],"related_works":["https://openalex.org/W1911859126","https://openalex.org/W2120730869","https://openalex.org/W1569721167","https://openalex.org/W2166699153","https://openalex.org/W2384738070","https://openalex.org/W2065633372","https://openalex.org/W2735200146","https://openalex.org/W2109142991","https://openalex.org/W2023208959","https://openalex.org/W2056404380"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2],"automated":[3],"technique":[4],"that":[5,47],"uses":[6],"perceptual":[7],"and":[8,17,52,58,61,89,108],"non-perceptual":[9],"audio":[10,24,31,69,110],"quality":[11,25,70,73],"measures":[12,26,74],"for":[13,28],"discrimination":[14],"of":[15,30,36,43,96],"speech":[16,51,88],"music":[18,53,90],"signals":[19,54],"with":[20,80,107],"high":[21],"accuracy.":[22],"Deployed":[23],"used":[27,77],"characterization":[29],"are":[32,75],"obtained":[33],"via":[34],"de-noising":[35,48],"the":[37,44,68,94,97],"original":[38],"audio.":[39],"The":[40],"underlying":[41],"idea":[42],"approach":[45],"is":[46],"operation":[49],"affects":[50],"in":[55,78],"a":[56,81],"different":[57,105],"consistent":[59],"manner":[60],"these":[62],"differences":[63],"can":[64],"be":[65],"captured":[66],"by":[67],"metrics.":[71],"Obtained":[72],"then":[76],"conjunction":[79],"machine":[82],"learning":[83],"classifier":[84],"to":[85],"statistically":[86],"model":[87],"signals.":[91],"To":[92],"determine":[93],"accuracy":[95],"proposed":[98],"method,":[99],"tests":[100],"have":[101],"been":[102],"performed":[103],"on":[104],"datasets":[106],"without":[109],"compression.":[111]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}