{"id":"https://openalex.org/W1488912948","doi":"https://doi.org/10.1109/siu.2012.6204782","title":"Catalog-based single-channel speech-music separation for automatic speech recognition","display_name":"Catalog-based single-channel speech-music separation for automatic speech recognition","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W1488912948","doi":"https://doi.org/10.1109/siu.2012.6204782","mag":"1488912948"},"language":"en","primary_location":{"id":"doi:10.1109/siu.2012.6204782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204782","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":"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/A5006515267","display_name":"Cemil Demir","orcid":"https://orcid.org/0000-0002-6365-0196"},"institutions":[{"id":"https://openalex.org/I198068145","display_name":"Scientific and Technological Research Council of Turkey","ror":"https://ror.org/04w9kkr77","country_code":"TR","type":"government","lineage":["https://openalex.org/I198068145"]},{"id":"https://openalex.org/I4210126406","display_name":"Xuzhou Construction Machinery Group (China)","ror":"https://ror.org/02y5rmj89","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126406"]}],"countries":["CN","TR"],"is_corresponding":true,"raw_author_name":"Cemil Demir","raw_affiliation_strings":["TÜBİTAK-BİLGEM, Kocaeli, Türkiye","[TUBITAK BILGEM, Kocaeli, Turkey]"],"affiliations":[{"raw_affiliation_string":"TÜBİTAK-BİLGEM, Kocaeli, Türkiye","institution_ids":["https://openalex.org/I4210126406"]},{"raw_affiliation_string":"[TUBITAK BILGEM, Kocaeli, Turkey]","institution_ids":["https://openalex.org/I198068145"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mehmet U\u011fur Do\u011fan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126406","display_name":"Xuzhou Construction Machinery Group (China)","ror":"https://ror.org/02y5rmj89","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126406"]},{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["CN","TR"],"is_corresponding":false,"raw_author_name":"Mehmet U\u011fur Do\u011fan","raw_affiliation_strings":["TÜBİTAK-BİLGEM, Kocaeli, Türkiye","Comput. Eng. Dept., Bogazici Univ., Istanbul, Turkey#TAB#"],"affiliations":[{"raw_affiliation_string":"TÜBİTAK-BİLGEM, Kocaeli, Türkiye","institution_ids":["https://openalex.org/I4210126406"]},{"raw_affiliation_string":"Comput. Eng. Dept., Bogazici Univ., Istanbul, Turkey#TAB#","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064633247","display_name":"Ali Taylan Cemgil","orcid":"https://orcid.org/0000-0003-4463-8455"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]},{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["DE","TR"],"is_corresponding":false,"raw_author_name":"A. Taylan Cemgil","raw_affiliation_strings":["Bilgisayar Mühendisliği, Boğaziçi Üniversitesi, İstanbul, Türkiye","[Electrical and Electronics Engineering Department, Bo\u011fazi\u00e7i University, Istanbul, Turkey]"],"affiliations":[{"raw_affiliation_string":"Bilgisayar Mühendisliği, Boğaziçi Üniversitesi, İstanbul, Türkiye","institution_ids":["https://openalex.org/I2799978770"]},{"raw_affiliation_string":"[Electrical and Electronics Engineering Department, Bo\u011fazi\u00e7i University, Istanbul, Turkey]","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Murat Sara\u00e7lar","raw_affiliation_strings":["Elektrik-Elektronik Mühendisliği, Boğaziçi Üniversitesi, İstanbul,Türkiye"],"affiliations":[{"raw_affiliation_string":"Elektrik-Elektronik Mühendisliği, Boğaziçi Üniversitesi, İstanbul,Türkiye","institution_ids":["https://openalex.org/I2799978770"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5006515267"],"corresponding_institution_ids":["https://openalex.org/I198068145","https://openalex.org/I4210126406"],"apc_list":null,"apc_paid":null,"fwci":0.4964,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63591402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"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":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/T10860","display_name":"Speech 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/T11309","display_name":"Music 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/T11447","display_name":"Blind Source Separation Techniques","score":0.9994000196456909,"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/spectrogram","display_name":"Spectrogram","score":0.9221755266189575},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8098554015159607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622615098953247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7569031715393066},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5734334588050842},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5676953196525574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4609570801258087},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.44879403710365295},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4314725995063782},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.42665165662765503},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42636823654174805},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42578452825546265},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3116629123687744}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9221755266189575},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8098554015159607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622615098953247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7569031715393066},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5734334588050842},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5676953196525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4609570801258087},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.44879403710365295},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4314725995063782},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.42665165662765503},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42636823654174805},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42578452825546265},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3116629123687744},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/siu.2012.6204782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204782","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"},{"id":"mag:1488912948","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/eusipco/eusipco2011.html#DemirCS11","pdf_url":null,"source":{"id":"https://openalex.org/S4306418373","display_name":"European Signal Processing Conference","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"European Signal Processing Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W76921649","https://openalex.org/W146976060","https://openalex.org/W196049401","https://openalex.org/W1902027874","https://openalex.org/W1963823700","https://openalex.org/W1963835294","https://openalex.org/W1982169181","https://openalex.org/W2008900415","https://openalex.org/W2017836379","https://openalex.org/W2031696998","https://openalex.org/W2117150818","https://openalex.org/W2134807719","https://openalex.org/W2150415460","https://openalex.org/W2152457943","https://openalex.org/W2152753389","https://openalex.org/W2164162335","https://openalex.org/W6606052675","https://openalex.org/W6607486085","https://openalex.org/W6677513291","https://openalex.org/W6713393696"],"related_works":["https://openalex.org/W1988401578","https://openalex.org/W2403025337","https://openalex.org/W2042419400","https://openalex.org/W2544241817","https://openalex.org/W2097405701","https://openalex.org/W146976060","https://openalex.org/W1505251852","https://openalex.org/W127429363","https://openalex.org/W2532540590","https://openalex.org/W2016363830","https://openalex.org/W3012315587","https://openalex.org/W1972312031","https://openalex.org/W2439535961","https://openalex.org/W2006780816","https://openalex.org/W1566375193","https://openalex.org/W2030283329","https://openalex.org/W1495978384","https://openalex.org/W1498717522","https://openalex.org/W2156482987","https://openalex.org/W2112699988"],"abstract_inverted_index":{"In":[0,30,77,125],"this":[1,78,126],"study,":[2,127],"single-channel":[3],"speech":[4,13,21,52,59],"source":[5],"separation":[6,150,155],"is":[7,86],"carried":[8],"out":[9],"to":[10,157],"separate":[11],"the":[12,15,20,31,41,50,58,69,83,92,95,98,103,109,112,117,122,135,145,149],"from":[14],"background":[16,42,84],"music,":[17,43],"which":[18],"degrades":[19],"recognition":[22],"performance":[23,104,110,151],"especially":[24],"in":[25,97,144],"broadcast":[26],"news":[27],"transcription":[28],"systems.":[29],"proposed":[32],"method,":[33],"assuming":[34],"that":[35,82,130],"we":[36,44,80,128],"know":[37],"a":[38,46,62,73],"catalog":[39],"of":[40,94,105,111,121],"developed":[45],"generative":[47],"model":[48,67],"for":[49],"superposed":[51],"and":[53,68,90,152],"music":[54,70,85,99],"spectrograms.":[55],"We":[56,101],"represent":[57],"spectrogram":[60,71],"by":[61,72,88],"Non-negative":[63],"Matrix":[64],"Factorization":[65],"(NMF)":[66],"conditional":[74],"Mixture":[75],"Model.":[76],"model,":[79],"assume":[81],"generated":[87],"repeating":[89],"changing":[91],"gain":[93,118,146],"jingle":[96],"catalog.":[100],"compare":[102],"our":[106],"system":[107],"with":[108],"traditional":[113,131],"NMF":[114,132,158],"model.We":[115],"address":[116],"estimation":[119,147],"problem":[120],"catalog-based":[123],"method.":[124,137],"showed":[129],"method":[133],"outperforms":[134],"catalogbased":[136],"However,":[138],"using":[139],"Gamma":[140],"Markov":[141],"Chain":[142],"(GMC)":[143],"improves":[148],"yields":[153],"better":[154],"compared":[156],"model.":[159]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}