{"id":"https://openalex.org/W2165622798","doi":"https://doi.org/10.1109/icassp.2006.1661325","title":"Feature Extraction From Talking Mouths for Video-Based Bi-Modal Speaker Verification","display_name":"Feature Extraction From Talking Mouths for Video-Based Bi-Modal Speaker Verification","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2165622798","doi":"https://doi.org/10.1109/icassp.2006.1661325","mag":"2165622798"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1661325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661325","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/A5026707467","display_name":"Hua Ouyang","orcid":"https://orcid.org/0009-0001-4259-5132"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hua Ouyang","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110217764","display_name":"W.N. Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"W.N. Chan","raw_affiliation_strings":["Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9916999936103821,"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/T13289","display_name":"Infant Health and Development","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7953445315361023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7874787449836731},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6531273126602173},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.526362955570221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49043747782707214},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.45522579550743103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45289579033851624},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.432519793510437},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4128657877445221},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4107586145401001}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7953445315361023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874787449836731},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6531273126602173},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.526362955570221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49043747782707214},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.45522579550743103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45289579033851624},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.432519793510437},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4128657877445221},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4107586145401001},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1661325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661325","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W138760483","https://openalex.org/W1527240141","https://openalex.org/W1532222477","https://openalex.org/W1830938247","https://openalex.org/W1989702938","https://openalex.org/W1995230685","https://openalex.org/W2041823554","https://openalex.org/W2068723942","https://openalex.org/W2079844951","https://openalex.org/W2104462292","https://openalex.org/W2106930486","https://openalex.org/W2112173139","https://openalex.org/W2121647436","https://openalex.org/W2125698722","https://openalex.org/W2127651741","https://openalex.org/W2129244720","https://openalex.org/W2155151128","https://openalex.org/W2799061466","https://openalex.org/W4230946174","https://openalex.org/W6631618440","https://openalex.org/W6638622520","https://openalex.org/W6675625917","https://openalex.org/W6679118701"],"related_works":["https://openalex.org/W2066003895","https://openalex.org/W2537963312","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1974473538","https://openalex.org/W2020010749","https://openalex.org/W2164899521","https://openalex.org/W1982853263"],"abstract_inverted_index":{"As":[0],"the":[1,33,52,59,84,92,120,131],"low-cost":[2],"video":[3,54,122],"transmission":[4],"becomes":[5],"popular,":[6],"video-based":[7],"bi-modal":[8,118],"(audio":[9],"and":[10,104],"visual)":[11],"authentication":[12],"has":[13],"great":[14],"potential":[15],"in":[16,99],"various":[17],"applications":[18],"that":[19,91],"require":[20],"access":[21],"control":[22],"over":[23,51],"handheld":[24],"terminals.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29],"propose":[30],"to":[31,79,126,130],"use":[32],"averaged":[34],"mouth":[35,49],"image":[36],"(AMI)":[37],"for":[38],"speaker":[39],"verification.":[40],"The":[41,75,87],"AMI":[42,60,76,93],"is":[43,77],"computed":[44],"by":[45],"averaging":[46],"properly":[47],"aligned":[48],"images":[50],"whole":[53],"sequence.":[55],"Despite":[56],"its":[57],"simplicity,":[58],"not":[61,115],"only":[62],"contains":[63],"appearance":[64],"information":[65],"but":[66],"also":[67],"describes":[68],"stylistic":[69],"articulation":[70],"gestures":[71],"of":[72,107],"individual":[73],"speakers.":[74],"found":[78,125],"be":[80,127],"fairly":[81],"invariant":[82],"against":[83],"spoken":[85],"content.":[86],"experimental":[88],"results":[89],"show":[90],"based":[94],"features":[95,123,133],"are":[96,114,124],"very":[97],"effective":[98],"discriminating":[100],"speaking":[101],"persons.":[102],"Explicit":[103],"precise":[105],"extraction":[106],"lip":[108],"contours":[109],"or":[110],"other":[111],"feature":[112],"points":[113],"required.":[116],"For":[117],"verification,":[119],"proposed":[121],"highly":[128],"complementary":[129],"audio":[132]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
