{"id":"https://openalex.org/W2116787917","doi":"https://doi.org/10.1109/icassp.2006.1660095","title":"Multimodal Speaker Identification Using Canonical Correlation Analysis","display_name":"Multimodal Speaker Identification Using Canonical Correlation Analysis","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2116787917","doi":"https://doi.org/10.1109/icassp.2006.1660095","mag":"2116787917"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5015357395","display_name":"Mehmet Emre Sargin","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":"M.E. Sargin","raw_affiliation_strings":["Multimedia, Vision and Graphics Laboratory, Ko\u00e7 University, Istanbul, Turkey","Multimedia, Vision and Graphics Laboratory, College of Engineering, Koc University, Sariyer, Istanbul, 34450, Turkey. msargin@ku.edu.tr"],"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 Laboratory, College of Engineering, Koc University, Sariyer, Istanbul, 34450, Turkey. msargin@ku.edu.tr","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","Lab. of Multimedia, Vision & Graphics, Koc Univ., Istanbul"],"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":"Lab. of Multimedia, Vision & Graphics, Koc Univ., Istanbul","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","Lab. of Multimedia, Vision & Graphics, Koc Univ., Istanbul"],"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":"Lab. of Multimedia, Vision & Graphics, Koc Univ., Istanbul","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","Lab. of Multimedia, Vision & Graphics, Koc Univ., Istanbul"],"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":"Lab. of Multimedia, Vision & Graphics, Koc Univ., Istanbul","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":3.4735,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.9355882,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"613"},"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":0.9969000220298767,"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":0.9922999739646912,"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/modalities","display_name":"Modalities","score":0.9015772938728333},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.7965494394302368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6650866866111755},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6477999687194824},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6285786628723145},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5441031455993652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5400335192680359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5267738103866577},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4998950958251953},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46099475026130676},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4531524181365967},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4312569200992584},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1756022572517395}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.9015772938728333},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.7965494394302368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6650866866111755},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6477999687194824},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6285786628723145},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5441031455993652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5400335192680359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5267738103866577},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4998950958251953},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46099475026130676},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4531524181365967},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4312569200992584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1756022572517395},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1660095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1607881722","https://openalex.org/W2025341678","https://openalex.org/W2068723942","https://openalex.org/W2075306129","https://openalex.org/W2085669808","https://openalex.org/W2096391593","https://openalex.org/W2112026651","https://openalex.org/W2129244720","https://openalex.org/W2138451337","https://openalex.org/W2157085398","https://openalex.org/W2167709189","https://openalex.org/W4237723258","https://openalex.org/W6636328081"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2004831463","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,26,127],"explore":[4],"the":[5,13,28,53,75,82,93,134,143,147,163,169,172,175],"use":[6],"of":[7,15,103,119,146,155,168,174],"canonical":[8],"correlation":[9],"analysis":[10,132],"to":[11,64,141,161],"improve":[12],"performance":[14,173],"multimodal":[16],"recognition":[17],"systems":[18],"that":[19,122],"involve":[20],"multiple":[21],"correlated":[22,144],"modalities.":[23],"More":[24],"specifically,":[25],"consider":[27],"audiovisual":[29],"speaker":[30],"identification":[31,46],"problem,":[32],"where":[33],"speech":[34],"and":[35,80,114,136,149,157],"lip":[36,115,137],"texture":[37,116],"(or":[38],"intensity)":[39],"modalities":[40,77,104,110,138],"are":[41,78,86,105,123,178],"fused":[42],"in":[43,73],"an":[44,152],"open-set":[45],"framework.":[47],"Our":[48],"motivation":[49],"is":[50,61,70],"based":[51],"on":[52,92,133],"following":[54],"observation.":[55],"The":[56,166],"late":[57,158],"integration":[58,90,159],"strategy,":[59],"which":[60],"also":[62,117,179],"referred":[63],"as":[65,112,140],"decision":[66],"or":[67],"opinion":[68],"fusion,":[69],"effective":[71],"especially":[72],"case":[74],"contributing":[76],"uncorrelated":[79],"thus":[81],"resulting":[83],"partial":[84],"decisions":[85],"statistically":[87],"independent.":[88,125],"Early":[89],"techniques":[91,160],"other":[94],"hand":[95],"can":[96],"be":[97],"favored":[98],"only":[99],"if":[100],"a":[101,130],"couple":[102],"highly":[106],"correlated.":[107],"However,":[108],"coupled":[109],"such":[111],"audio":[113,135],"consist":[118],"some":[120],"components":[121],"mutually":[124],"Thus":[126],"first":[128],"perform":[129],"cross-correlation":[131],"so":[139],"extract":[142],"part":[145],"information,":[148],"then":[150],"employ":[151],"optimal":[153],"combination":[154],"early":[156],"fuse":[162],"extracted":[164],"features.":[165],"results":[167],"experiments":[170],"testing":[171],"proposed":[176],"system":[177],"provided":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}