{"id":"https://openalex.org/W1494544065","doi":"https://doi.org/10.1109/icip.2003.1247167","title":"Multimodal speaker identification with audio-video processing","display_name":"Multimodal speaker identification with audio-video processing","publication_year":2004,"publication_date":"2004-06-03","ids":{"openalex":"https://openalex.org/W1494544065","doi":"https://doi.org/10.1109/icip.2003.1247167","mag":"1494544065"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2003.1247167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2003.1247167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/1270865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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","College of Engineering, Koc University, Istanbul, Turkey#TAB#"],"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":"College of Engineering, Koc University, Istanbul, Turkey#TAB#","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"middle","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","College of Engineering, Koc University, Istanbul, Turkey#TAB#"],"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":"College of Engineering, Koc University, Istanbul, Turkey#TAB#","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","College of Engineering, Koc University, Istanbul, Turkey#TAB#"],"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":"College of Engineering, Koc University, Istanbul, Turkey#TAB#","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","College of Engineering, Koc University, Istanbul, Turkey#TAB#"],"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":"College of Engineering, Koc University, Istanbul, Turkey#TAB#","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":2.5939,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90575812,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"III","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9900000095367432,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9848999977111816,"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":0.7958860397338867},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7207177877426147},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7049157023429871},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6704226732254028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6666540503501892},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5585273504257202},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5521626472473145},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.53304523229599},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5154793858528137},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47251567244529724},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.45914149284362793},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.4560627043247223},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.44231584668159485},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43453115224838257},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.43012258410453796},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08875313401222229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958860397338867},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7207177877426147},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7049157023429871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6704226732254028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6666540503501892},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5585273504257202},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5521626472473145},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.53304523229599},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5154793858528137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47251567244529724},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.45914149284362793},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.4560627043247223},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.44231584668159485},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43453115224838257},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.43012258410453796},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08875313401222229},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip.2003.1247167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2003.1247167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:1270865","is_oa":true,"landing_page_url":"https://zenodo.org/record/1270865","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:1270865","is_oa":true,"landing_page_url":"https://zenodo.org/record/1270865","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"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/W2109449312","https://openalex.org/W2118877769","https://openalex.org/W2125838338","https://openalex.org/W2127884747","https://openalex.org/W2129244720","https://openalex.org/W2138451337","https://openalex.org/W2912341770","https://openalex.org/W4234146557","https://openalex.org/W6677548441","https://openalex.org/W6759258252"],"related_works":["https://openalex.org/W4246349004","https://openalex.org/W2181871477","https://openalex.org/W2061163896","https://openalex.org/W2432604435","https://openalex.org/W2511460115","https://openalex.org/W2089229568","https://openalex.org/W2019490789","https://openalex.org/W3088722891","https://openalex.org/W3119288895","https://openalex.org/W2185075503"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,31,61,65,113],"multimodal":[6],"audio-visual":[7],"speaker":[8],"identification":[9,119],"system.":[10,120],"The":[11,23,70,102],"objective":[12],"is":[13,48],"to":[14,81,109,132],"improve":[15],"the":[16,27,75,83,86,98,133,145],"recognition":[17],"performance":[18],"over":[19],"conventional":[20],"unimodal":[21],"schemes.":[22],"proposed":[24],"system":[25,134,146],"decomposes":[26],"information":[28],"existing":[29],"in":[30,51,64,127],"video":[32],"stream":[33,77],"into":[34],"three":[35],"components:":[36],"speech,":[37],"face":[38],"texture":[39,122],"and":[40,57,89,111,130],"lip":[41],"motion.":[42],"Lip":[43],"motion":[44],"between":[45],"successive":[46],"frames":[47],"first":[49],"computed":[50],"terms":[52],"of":[53,85,97,144],"optical":[54],"flow":[55],"vectors":[56,72,106],"then":[58,79],"encoded":[59],"as":[60],"feature":[62,71,105],"vector":[63],"magnitude":[66],"direction":[67],"histogram":[68],"domain.":[69],"obtained":[73],"along":[74],"whole":[76],"are":[78,107,124,139],"interpolated":[80],"match":[82],"rate":[84],"speech":[87,100],"signal":[88],"fused":[90],"with":[91],"mel":[92],"frequency":[93],"cepstral":[94],"coefficients":[95],"(MFCC)":[96],"corresponding":[99],"signal.":[101],"resulting":[103],"joint":[104],"used":[108],"train":[110],"test":[112],"Hidden":[114],"Markov":[115],"Model":[116],"(HMM)":[117],"based":[118],"Face":[121],"images":[123],"treated":[125],"separately":[126],"eigenface":[128],"domain":[129],"integrated":[131],"through":[135],"decision-fusion.":[136],"Experimental":[137],"results":[138],"also":[140],"included":[141],"for":[142],"demonstration":[143],"performance.":[147]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
