{"id":"https://openalex.org/W2109449312","doi":"https://doi.org/10.1109/icassp.2003.1202376","title":"Joint audio-video processing for biometric speaker identification","display_name":"Joint audio-video processing for biometric speaker identification","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W2109449312","doi":"https://doi.org/10.1109/icassp.2003.1202376","mag":"2109449312"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202376","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5070214407","display_name":"Alper Kanak","orcid":"https://orcid.org/0000-0003-2541-7753"},"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, Ko\u00e7 University, Istanbul, Turkey","[Multimedia, Vision and Graphics Lab, Koc University, Istanbul, TURKEY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Laboratory, Ko\u00e7 University, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]},{"raw_affiliation_string":"[Multimedia, Vision and Graphics Lab, Koc University, Istanbul, TURKEY]","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064993025","display_name":"Engin Erzin","orcid":"https://orcid.org/0000-0002-2715-2368"},"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, Ko\u00e7 University, Istanbul, Turkey","[Multimedia, Vision and Graphics Lab, Koc University, Istanbul, TURKEY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Laboratory, Ko\u00e7 University, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]},{"raw_affiliation_string":"[Multimedia, Vision and Graphics Lab, Koc University, Istanbul, TURKEY]","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074744284","display_name":"Y. Yemez","orcid":"https://orcid.org/0000-0002-7515-3138"},"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, Ko\u00e7 University, Istanbul, Turkey","[Multimedia, Vision and Graphics Lab, Koc University, Istanbul, TURKEY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Laboratory, Ko\u00e7 University, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]},{"raw_affiliation_string":"[Multimedia, Vision and Graphics Lab, Koc University, Istanbul, TURKEY]","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034648478","display_name":"A. Murat Tekalp","orcid":"https://orcid.org/0000-0003-1465-8121"},"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, Ko\u00e7 University, Istanbul, Turkey","[Multimedia, Vision and Graphics Lab, Koc University, Istanbul, TURKEY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Laboratory, Ko\u00e7 University, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]},{"raw_affiliation_string":"[Multimedia, Vision and Graphics Lab, Koc University, 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":3.1789,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.93000779,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"377"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8171009421348572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7970010042190552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7931234836578369},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7082066535949707},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6749885082244873},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.584228515625},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.5831641554832458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5399788022041321},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.522361159324646},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4956618547439575},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48472902178764343},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4520275294780731},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.42326945066452026},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4150257408618927},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08431339263916016}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8171009421348572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7970010042190552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931234836578369},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7082066535949707},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6749885082244873},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.584228515625},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.5831641554832458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5399788022041321},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.522361159324646},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4956618547439575},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48472902178764343},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4520275294780731},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.42326945066452026},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4150257408618927},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08431339263916016},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1202376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202376","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":12,"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/W2912341770","https://openalex.org/W3000615308","https://openalex.org/W4234146557","https://openalex.org/W6759258252"],"related_works":["https://openalex.org/W2902887112","https://openalex.org/W2606551632","https://openalex.org/W3119288895","https://openalex.org/W1507610450","https://openalex.org/W2126085626","https://openalex.org/W2185075503","https://openalex.org/W2749720872","https://openalex.org/W2131673591","https://openalex.org/W2104528589","https://openalex.org/W2101922478"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,39,99],"bimodal":[3],"audio-visual":[4],"speaker":[5],"identification":[6,105],"system.":[7,106],"The":[8,20,61,88],"objective":[9],"is":[10],"to":[11,67,95,111],"improve":[12],"the":[13,26,33,43,69,72,84,113],"recognition":[14],"performance":[15],"over":[16],"conventional":[17],"unimodal":[18],"schemes.":[19],"proposed":[21],"system":[22,114],"exploits":[23],"not":[24],"only":[25],"temporal":[27],"and":[28,35,75,97],"spatial":[29],"correlations":[30],"existing":[31],"in":[32],"speech":[34,73,86],"video":[36,54],"signals":[37],"of":[38,71,83],"speaker,":[40],"but":[41],"also":[42],"cross-correlation":[44],"between":[45],"these":[46],"two":[47],"modalities.":[48],"Lip":[49],"images":[50],"extracted":[51],"from":[52],"each":[53],"frame":[55],"are":[56,65,93,109],"transformed":[57],"onto":[58],"an":[59],"eigenspace.":[60],"obtained":[62],"eigenlip":[63],"coefficients":[64,81],"interpolated":[66],"match":[68],"rate":[70],"signal":[74],"fused":[76],"with":[77],"Mel":[78],"frequency":[79],"cepstral":[80],"(MFCC)":[82],"corresponding":[85],"signal.":[87],"resulting":[89],"joint":[90],"feature":[91],"vectors":[92],"used":[94],"train":[96],"test":[98],"hidden":[100],"Markov":[101],"model":[102],"(HMM)":[103],"based":[104],"Experimental":[107],"results":[108],"included":[110],"demonstrate":[112],"performance.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}