{"id":"https://openalex.org/W4246960037","doi":"https://doi.org/10.1109/icme.2003.1221373","title":"Joint audio-video processing for biometric speaker identification","display_name":"Joint audio-video processing for biometric speaker identification","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W4246960037","doi":"https://doi.org/10.1109/icme.2003.1221373"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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/A5086699766","display_name":"A. Kanak","orcid":null},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"A. Kanak","raw_affiliation_strings":["Multimedia, Vision and Graphics Laboratory, College of Engineering, Ko\u00e7 University, Sariyer, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Laboratory, College of Engineering, Ko\u00e7 University, Sariyer, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001499951","display_name":"E. Erzin","orcid":null},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"E. Erzin","raw_affiliation_strings":["Multimedia, Vision and Graphics Laboratory, College of Engineering, Ko\u00e7 University, Sariyer, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Laboratory, College of Engineering, Ko\u00e7 University, Sariyer, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040657146","display_name":"Y. Yemez","orcid":null},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Y. Yemez","raw_affiliation_strings":["Multimedia, Vision and Graphics Laboratory, College of Engineering, Ko\u00e7 University, Sariyer, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Laboratory, College of Engineering, Ko\u00e7 University, Sariyer, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067030479","display_name":"A.M. Tekalp","orcid":null},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"A.M. Tekalp","raw_affiliation_strings":["Multimedia, Vision and Graphics Laboratory, College of Engineering, Ko\u00e7 University, Sariyer, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Laboratory, College of Engineering, Ko\u00e7 University, Sariyer, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1351752"],"apc_list":null,"apc_paid":null,"fwci":0.7661,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.73822171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"III","last_page":"561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.813892662525177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7997199892997742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7977274656295776},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6959692239761353},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6528786420822144},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5980185270309448},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.5627819895744324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5249150395393372},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5017955303192139},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4986443519592285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4656698405742645},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4645872414112091},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4133601188659668},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08699876070022583}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.813892662525177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7997199892997742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7977274656295776},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6959692239761353},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6528786420822144},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5980185270309448},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.5627819895744324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5249150395393372},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5017955303192139},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4986443519592285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4656698405742645},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4645872414112091},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4133601188659668},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08699876070022583},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/icme.2003.1221373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1948754462","https://openalex.org/W2075306129","https://openalex.org/W2125838338","https://openalex.org/W2127884747","https://openalex.org/W2129244720","https://openalex.org/W2138451337","https://openalex.org/W2149950657","https://openalex.org/W2157190406","https://openalex.org/W3000615308","https://openalex.org/W4234146557","https://openalex.org/W6759258252"],"related_works":["https://openalex.org/W2606551632","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W2749720872","https://openalex.org/W2186375278","https://openalex.org/W2793748347","https://openalex.org/W4229940372","https://openalex.org/W4250904811","https://openalex.org/W2104528589","https://openalex.org/W2155047054"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,41,101],"bimodal":[6],"audio-visual":[7],"speaker":[8],"identification":[9,107],"system.":[10,108],"The":[11,23,63,90],"objective":[12],"is":[13],"to":[14,69,97],"improve":[15],"the":[16,29,45,71,74,86,117],"recognition":[17],"performance":[18],"over":[19],"conventional":[20],"unimodal":[21],"schemes.":[22],"proposed":[24],"system":[25,118],"exploits":[26],"not":[27],"only":[28],"temporal":[30],"and":[31,37,77,99],"spatial":[32],"correlations":[33],"existing":[34],"in":[35],"speech":[36,75,88],"video":[38,56],"signals":[39],"of":[40,73,85,116],"speaker,":[42],"but":[43],"also":[44,112],"cross-correlation":[46],"between":[47],"these":[48],"two":[49],"modalities.":[50],"Lip":[51],"images":[52],"extracted":[53],"for":[54,114],"each":[55],"frame":[57],"are":[58,67,95,111],"transformed":[59],"onto":[60],"an":[61],"eigenspace.":[62],"obtained":[64],"eigenlip":[65],"coefficients":[66,83],"interpolated":[68],"match":[70],"rate":[72],"signal":[76],"fused":[78],"with":[79],"mel":[80],"frequency":[81],"cepstral":[82],"(MFCC)":[84],"corresponding":[87],"signal.":[89],"resulting":[91],"joint":[92],"feature":[93],"vectors":[94],"used":[96],"train":[98],"test":[100],"hidden":[102],"Markov":[103],"model":[104],"(HMM)":[105],"based":[106],"Experimental":[109],"results":[110],"included":[113],"demonstration":[115],"performance.":[119]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}