{"id":"https://openalex.org/W2042419400","doi":"https://doi.org/10.1109/siu.2012.6204436","title":"Audio-visual speech recognition with background music using single-channel source separation","display_name":"Audio-visual speech recognition with background music using single-channel source separation","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W2042419400","doi":"https://doi.org/10.1109/siu.2012.6204436","mag":"2042419400"},"language":"en","primary_location":{"id":"doi:10.1109/siu.2012.6204436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204436","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/A5013467271","display_name":"Emad M. Grais","orcid":"https://orcid.org/0000-0002-6387-0981"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Emad M. Grais","raw_affiliation_strings":["Faculty of Engineering and Natural Sciences, Sabanci University, Tuzla, Istanbul, Turkey","Faculty of Engineering and Natural Sciences, Sabanc\u0131 University, Orhanl\u0131\u2010Tuzla, 34956 Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Natural Sciences, Sabanci University, Tuzla, Istanbul, Turkey","institution_ids":["https://openalex.org/I134235054"]},{"raw_affiliation_string":"Faculty of Engineering and Natural Sciences, Sabanc\u0131 University, Orhanl\u0131\u2010Tuzla, 34956 Istanbul, Turkey","institution_ids":["https://openalex.org/I134235054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085714936","display_name":"\u0130brahim Sayg\u0131n Topkaya","orcid":null},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ibrahim Saygin Topkaya","raw_affiliation_strings":["Faculty of Engineering and Natural Sciences, Sabanci University, Tuzla, Istanbul, Turkey","Faculty of Engineering and Natural Sciences, Sabanc\u0131 University, Orhanl\u0131\u2010Tuzla, 34956 Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Natural Sciences, Sabanci University, Tuzla, Istanbul, Turkey","institution_ids":["https://openalex.org/I134235054"]},{"raw_affiliation_string":"Faculty of Engineering and Natural Sciences, Sabanc\u0131 University, Orhanl\u0131\u2010Tuzla, 34956 Istanbul, Turkey","institution_ids":["https://openalex.org/I134235054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Faculty of Engineering and Natural Sciences, Sabanci University, Tuzla, Istanbul, Turkey","Faculty of Engineering and Natural Sciences, Sabanc\u0131 University, Orhanl\u0131\u2010Tuzla, 34956 Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Natural Sciences, Sabanci University, Tuzla, Istanbul, Turkey","institution_ids":["https://openalex.org/I134235054"]},{"raw_affiliation_string":"Faculty of Engineering and Natural Sciences, Sabanc\u0131 University, Orhanl\u0131\u2010Tuzla, 34956 Istanbul, Turkey","institution_ids":["https://openalex.org/I134235054"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I134235054"],"apc_list":null,"apc_paid":null,"fwci":1.708,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86199723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.996999979019165,"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/speech-recognition","display_name":"Speech recognition","score":0.838369607925415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8091135621070862},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.7140161991119385},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7037839293479919},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6255306005477905},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5433938503265381},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5200688242912292},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5175927877426147},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5123873353004456},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.48451799154281616},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42878925800323486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3959256112575531},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3529208302497864},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.29350513219833374}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.838369607925415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091135621070862},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.7140161991119385},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7037839293479919},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6255306005477905},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5433938503265381},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5200688242912292},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5175927877426147},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5123873353004456},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.48451799154281616},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42878925800323486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3959256112575531},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3529208302497864},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.29350513219833374},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/siu.2012.6204436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204436","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":"pmh:oai:research.sabanciuniv.edu:19010","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402254","display_name":"Sabanci University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I134235054","host_organization_name":"Sabanc\u0131 \u00dcniversitesi","host_organization_lineage":["https://openalex.org/I134235054"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.660.7602","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.660.7602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.sabanciuniv.edu/19010/1/siu2012.pdf","raw_type":"text"},{"id":"pmh:oai:alma.44SUR_INST:11139009500002346","is_oa":false,"landing_page_url":"https://openresearch.surrey.ac.uk/esploro/outputs/conferencePresentation/Audio-Visual-speech-recognition-with-background-music/99512725702346","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:epubs.surrey.ac.uk:840747","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/840747/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W185399533","https://openalex.org/W1633840029","https://openalex.org/W1978380426","https://openalex.org/W2073039128","https://openalex.org/W2102512156","https://openalex.org/W2105594594","https://openalex.org/W2121486117","https://openalex.org/W2135029798","https://openalex.org/W2146544734","https://openalex.org/W2168010845","https://openalex.org/W2980286501","https://openalex.org/W3140954725","https://openalex.org/W3143596294","https://openalex.org/W6674975915","https://openalex.org/W6680012447","https://openalex.org/W6768798221"],"related_works":["https://openalex.org/W2547262076","https://openalex.org/W2563421448","https://openalex.org/W2774154397","https://openalex.org/W1565566036","https://openalex.org/W2131711534","https://openalex.org/W2341426843","https://openalex.org/W1583620810","https://openalex.org/W1911859126","https://openalex.org/W642007152","https://openalex.org/W4387712795"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,94],"consider":[4],"audio-visual":[5,18,79,121],"speech":[6,19,35,61,72,80,122,135],"recognition":[7,20,81,98,111,123,136],"with":[8,39,106,113,124],"background":[9,65],"music.":[10],"The":[11],"proposed":[12,30],"algorithm":[13,31,45],"is":[14,37,55,74,83],"an":[15],"integration":[16],"of":[17,133],"and":[21,52,108],"single":[22],"channel":[23],"source":[24,125],"separation":[25,126],"(SCSS).":[26],"We":[27],"apply":[28],"the":[29,43,59,64,103,110,131,134],"to":[32,57,96],"recognize":[33],"spoken":[34],"that":[36,119],"mixed":[38],"music":[40,66],"signals.":[41],"First,":[42],"SCSS":[44,107],"based":[46],"on":[47],"nonnegative":[48],"matrix":[49],"factorization":[50],"(NMF)":[51],"spectral":[53,69],"masks":[54],"used":[56],"separate":[58],"audio":[60,73,104],"signal":[62,105],"from":[63,76],"in":[67,130],"magnitude":[68],"domain.":[70],"After":[71],"separated":[75],"music,":[77],"regular":[78],"(AVSR)":[82],"employed":[84],"using":[85],"multi-stream":[86],"hidden":[87],"Markov":[88],"models.":[89],"Employing":[90],"two":[91],"approaches":[92],"together,":[93],"try":[95],"improve":[97],"accuracy":[99,132],"by":[100],"both":[101],"processing":[102],"supporting":[109],"task":[112],"visual":[114],"information.":[115],"Experimental":[116],"results":[117],"show":[118],"combining":[120],"gives":[127],"remarkable":[128],"improvements":[129],"system.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}