{"id":"https://openalex.org/W2117593491","doi":"https://doi.org/10.1142/s1793351x10000985","title":"ROBUST MULTIMODAL PERSON RECOGNITION USING LOW-COMPLEXITY AUDIO-VISUAL FEATURE FUSION APPROACHES","display_name":"ROBUST MULTIMODAL PERSON RECOGNITION USING LOW-COMPLEXITY AUDIO-VISUAL FEATURE FUSION APPROACHES","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2117593491","doi":"https://doi.org/10.1142/s1793351x10000985","mag":"2117593491"},"language":"en","primary_location":{"id":"doi:10.1142/s1793351x10000985","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x10000985","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-7108","issn":["1793-7108","1793-351X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"},"type":"article","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/A5109564748","display_name":"Dhaval N. Shah","orcid":null},"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":"DHAVAL SHAH","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106859201","display_name":"Kyu J. Han","orcid":null},"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":"KYU J. HAN","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","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":"SHRIKANTH S. NARAYANAN","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory (SAIL), Ming Hsieh Department of Electrical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089, 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":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.13340935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"04","issue":"02","first_page":"155","last_page":"179"},"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":0.9973999857902527,"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/T12740","display_name":"Gait Recognition and Analysis","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8845913410186768},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6005441546440125},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5829265117645264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5650800466537476},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5643580555915833},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5261994004249573},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42821845412254333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3856324553489685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33710977435112}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8845913410186768},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6005441546440125},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5829265117645264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5650800466537476},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5643580555915833},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5261994004249573},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42821845412254333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3856324553489685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33710977435112},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1793351x10000985","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793351x10000985","pdf_url":null,"source":{"id":"https://openalex.org/S4210201727","display_name":"International Journal of Semantic Computing","issn_l":"1793-7108","issn":["1793-7108","1793-351X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Semantic Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W18031388","https://openalex.org/W57796367","https://openalex.org/W198823512","https://openalex.org/W1544978329","https://openalex.org/W1558945660","https://openalex.org/W1602485673","https://openalex.org/W1639795441","https://openalex.org/W1664547674","https://openalex.org/W1974783905","https://openalex.org/W1988910659","https://openalex.org/W2014621385","https://openalex.org/W2024677982","https://openalex.org/W2034749103","https://openalex.org/W2049633694","https://openalex.org/W2068723942","https://openalex.org/W2069883713","https://openalex.org/W2072380605","https://openalex.org/W2075409220","https://openalex.org/W2094214226","https://openalex.org/W2101294471","https://openalex.org/W2119970915","https://openalex.org/W2125537957","https://openalex.org/W2129244720","https://openalex.org/W2137225299","https://openalex.org/W2140959843","https://openalex.org/W2149516292","https://openalex.org/W2158275940","https://openalex.org/W2170941890","https://openalex.org/W3097096317","https://openalex.org/W3127686677","https://openalex.org/W3129711340","https://openalex.org/W4229926969","https://openalex.org/W4230579564","https://openalex.org/W4240729944","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W1967477266","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2914603036","https://openalex.org/W2158882055"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"first":[4],"show":[5,70,154],"the":[6,24,33,52,60,67,72,97,118],"importance":[7],"of":[8,35,54,96,165],"face-voice":[9],"correlation":[10,25],"for":[11,101,104],"audio-visual":[12,27,43],"person":[13],"recognition.":[14],"We":[15,111,152],"propose":[16,129],"a":[17,37,55,78,105,124,139],"simple":[18,106],"multimodal":[19,74,144],"fusion":[20,75,98],"technique":[21,99],"which":[22,45,134],"preserves":[23],"between":[26],"features":[28,50],"during":[29],"speech":[30],"and":[31,42,48,59,87,138,168],"evaluate":[32],"performance":[34,162],"such":[36],"system":[38],"against":[39,91],"audio-only,":[40],"video-only,":[41],"systems":[44],"use":[46],"audio":[47],"visual":[49],"neglecting":[51],"interdependency":[53],"person's":[56],"spoken":[57],"utterance":[58],"associated":[61,116],"facial":[62],"movements.":[63],"Experiments":[64],"performed":[65],"on":[66],"VidTIMIT":[68],"dataset":[69],"that":[71,155],"proposed":[73,120],"scheme":[76],"has":[77,149],"lower":[79],"error":[80],"rate":[81],"than":[82],"all":[83],"other":[84],"comparison":[85],"conditions":[86],"is":[88],"more":[89,136],"robust":[90],"replay":[92],"attacks.":[93],"The":[94],"simplicity":[95],"allows":[100],"low-complexity":[102],"designs":[103,133,159],"low-cost":[107],"real-time":[108],"DSP":[109],"implementation.":[110],"then":[112],"discuss":[113],"some":[114],"problems":[115],"with":[117],"previously":[119],"design":[121],"and,":[122],"as":[123],"solution":[125],"to":[126,142],"those":[127],"problems,":[128],"two":[130],"novel":[131,157],"classifier":[132,158],"provide":[135],"flexibility":[137],"convenient":[140],"way":[141],"represent":[143],"data":[145],"where":[146],"each":[147],"modality":[148],"different":[150],"characteristics.":[151],"also":[153],"these":[156],"offer":[160],"superior":[161],"in":[163],"terms":[164],"both":[166],"accuracy":[167],"robustness.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}