{"id":"https://openalex.org/W1969365714","doi":"https://doi.org/10.1109/icassp.2002.5743810","title":"Automatic speechreading with application to speaker verification","display_name":"Automatic speechreading with application to speaker verification","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1969365714","doi":"https://doi.org/10.1109/icassp.2002.5743810","mag":"1969365714"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743810","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-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/A5049279499","display_name":"Charles C. Broun","orcid":null},"institutions":[{"id":"https://openalex.org/I1333370159","display_name":"Motorola (United States)","ror":"https://ror.org/01hafxd32","country_code":"US","type":"company","lineage":["https://openalex.org/I1333370159"]},{"id":"https://openalex.org/I2802964274","display_name":"Interface (United States)","ror":"https://ror.org/04nvtmr42","country_code":"US","type":"company","lineage":["https://openalex.org/I2802964274"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"C. C. Broun","raw_affiliation_strings":["Motorola Human Interface Laboratories, Tempe, AZ, USA","Motorola Human Interface Labs, Tempe, Arizona 85284, USA"],"affiliations":[{"raw_affiliation_string":"Motorola Human Interface Laboratories, Tempe, AZ, USA","institution_ids":["https://openalex.org/I1333370159","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Motorola Human Interface Labs, Tempe, Arizona 85284, USA","institution_ids":["https://openalex.org/I1333370159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064140731","display_name":"X. Zhang","orcid":"https://orcid.org/0000-0003-4329-4435"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"X. Zhang","raw_affiliation_strings":["Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta 30332-0250, USA"],"affiliations":[{"raw_affiliation_string":"Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta 30332-0250, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110449498","display_name":"R.M. Mersereau","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. M. Mersereau","raw_affiliation_strings":["Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta 30332-0250, USA"],"affiliations":[{"raw_affiliation_string":"Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta 30332-0250, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039007664","display_name":"M. Clements","orcid":"https://orcid.org/0000-0001-7371-1012"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Clements","raw_affiliation_strings":["Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta 30332-0250, USA"],"affiliations":[{"raw_affiliation_string":"Center for Signal & Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta 30332-0250, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049279499"],"corresponding_institution_ids":["https://openalex.org/I1333370159","https://openalex.org/I2802964274"],"apc_list":null,"apc_paid":null,"fwci":2.9679,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.90761334,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":null,"first_page":"I","last_page":"685"},"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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/speechreading","display_name":"Speechreading","score":0.9586210250854492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8007644414901733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6901702880859375},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5347724556922913},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.526178240776062},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5207352638244629},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5095956325531006},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.45418301224708557},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3661697506904602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3441818654537201},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10208070278167725}],"concepts":[{"id":"https://openalex.org/C2910309083","wikidata":"https://www.wikidata.org/wiki/Q1069953","display_name":"Speechreading","level":2,"score":0.9586210250854492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007644414901733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6901702880859375},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5347724556922913},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.526178240776062},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5207352638244629},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5095956325531006},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45418301224708557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3661697506904602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3441818654537201},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10208070278167725},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5743810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743810","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcommons.calpoly.edu:eeng_fac-1265","is_oa":false,"landing_page_url":"https://digitalcommons.calpoly.edu/eeng_fac/265","pdf_url":null,"source":{"id":"https://openalex.org/S4377196328","display_name":"DigitalCommons - CalPoly (California State Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98947143","host_organization_name":"California State Polytechnic University","host_organization_lineage":["https://openalex.org/I98947143"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical Engineering","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1527240141","https://openalex.org/W2004315210","https://openalex.org/W2019763203","https://openalex.org/W2106844098","https://openalex.org/W2108492645","https://openalex.org/W2133059825","https://openalex.org/W6631618440"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Speech":[0],"not":[1],"only":[2],"conveys":[3],"the":[4,10,24,30,33,48,62,66,89],"linguistic":[5],"information,":[6],"but":[7],"also":[8,39],"characterizes":[9],"talker's":[11],"identity":[12],"and":[13,78,105],"therefore":[14],"can":[15],"be":[16],"used":[17],"in":[18,29,54,100,109],"personal":[19],"authentication.":[20],"While":[21],"most":[22],"of":[23,50,65,81],"speech":[25,37,52],"information":[26,96],"is":[27,97],"contained":[28],"acoustic":[31],"channel,":[32],"lip":[34],"movement":[35],"during":[36],"production":[38],"provides":[40],"useful":[41],"information.":[42],"In":[43],"this":[44],"paper":[45],"we":[46],"investigate":[47],"effectiveness":[49],"visual":[51,63,82,95],"features":[53],"a":[55,73],"speaker":[56,110],"veri\u00a3cation":[57,111],"task.":[58],"We":[59,70],"\u00a3rst":[60],"present":[61],"front-end":[64],"automatic":[67],"speechreading":[68],"system.":[69],"then":[71],"develop":[72],"recognition":[74],"engine":[75],"to":[76],"train":[77],"recognize":[79],"sequences":[80],"parameters.":[83],"The":[84],"experimental":[85],"results":[86],"based":[87],"on":[88],"XM2VTS":[90],"database":[91],"[I]":[92],"demonstrate":[93],"that":[94],"highly":[98],"effective":[99],"reducing":[101],"both":[102],"false":[103,106],"acceptance":[104],"rejection":[107],"rates":[108],"tasks.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}