{"id":"https://openalex.org/W2153823022","doi":"https://doi.org/10.1109/icassp.2003.1200095","title":"Audiovisual-based adaptive speaker identification","display_name":"Audiovisual-based adaptive speaker identification","publication_year":2004,"publication_date":"2004-01-24","ids":{"openalex":"https://openalex.org/W2153823022","doi":"https://doi.org/10.1109/icassp.2003.1200095","mag":"2153823022"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1200095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1200095","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/A5100358931","display_name":"Ying Li","orcid":"https://orcid.org/0000-0001-5036-2550"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Narayanan","raw_affiliation_strings":["Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001082656","display_name":"C.\u2010C. Jay Kuo","orcid":"https://orcid.org/0000-0001-9474-5035"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.-C.J. Kuo","raw_affiliation_strings":["Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Media Systems Center and Department of Electrical Engineering, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.7782,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69715083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"812"},"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8115249276161194},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7481963634490967},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6264525055885315},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5622424483299255},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5255535840988159},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5042566061019897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4750801920890808},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.43986764550209045},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4284823536872864},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3764382302761078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115249276161194},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7481963634490967},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6264525055885315},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5622424483299255},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5255535840988159},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5042566061019897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4750801920890808},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.43986764550209045},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4284823536872864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3764382302761078},{"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/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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1200095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1200095","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.135.7835","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.7835","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sail.usc.edu/publications/icassp03-yingli.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W1968600455","https://openalex.org/W1996262499","https://openalex.org/W2072726793","https://openalex.org/W2098559774","https://openalex.org/W2120212892","https://openalex.org/W2156648741","https://openalex.org/W2169516439","https://openalex.org/W2172149383","https://openalex.org/W4232925460","https://openalex.org/W6628911050"],"related_works":["https://openalex.org/W4234190324","https://openalex.org/W2126085626","https://openalex.org/W2545131480","https://openalex.org/W1973693762","https://openalex.org/W208363076","https://openalex.org/W4230495983","https://openalex.org/W2087341511","https://openalex.org/W2887000230","https://openalex.org/W2141917278","https://openalex.org/W2162533796"],"abstract_inverted_index":{"An":[0,96],"adaptive":[1,118],"speaker":[2,119],"identification":[3,100,120],"system":[4,69],"is":[5,29,43],"presented":[6],"in":[7,15],"this":[8],"paper,":[9],"which":[10],"aims":[11],"to":[12,32,45,72,90],"recognize":[13,46],"speakers":[14,34],"feature":[16],"films":[17],"by":[18,88],"exploiting":[19],"both":[20],"audio":[21,27],"and":[22,52],"visual":[23,41],"cues.":[24],"Specifically,":[25],"the":[26,40,86,115],"source":[28,42],"first":[30],"analyzed":[31],"identify":[33],"using":[35,49],"a":[36,64,111],"likelihood-based":[37],"approach.":[38,121],"Meanwhile,":[39],"parsed":[44],"talking":[47],"faces":[48],"face":[50],"detection/recognition":[51],"mouth":[53],"tracking":[54],"techniques.":[55],"These":[56],"two":[57,106],"information":[58],"sources":[59],"are":[60],"then":[61],"integrated":[62],"under":[63],"probabilistic":[65],"framework":[66],"for":[67,74,114],"improved":[68],"performance.":[70],"Moreover,":[71],"account":[73],"speakers'":[75],"voice":[76],"variations":[77],"along":[78],"time,":[79],"we":[80],"update":[81],"their":[82,91],"acoustic":[83],"models":[84],"on":[85,105],"fly":[87],"adapting":[89],"newly":[92],"contributed":[93],"speech":[94],"data.":[95],"average":[97],"of":[98],"80%":[99],"accuracy":[101],"has":[102],"been":[103],"achieved":[104],"test":[107],"movies.":[108],"This":[109],"shows":[110],"promising":[112],"future":[113],"proposed":[116],"audiovisual-based":[117]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}