{"id":"https://openalex.org/W2098419325","doi":"https://doi.org/10.1109/icassp.2002.5745022","title":"Visual speech feature extraction for improved speech recognition","display_name":"Visual speech feature extraction for improved speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2098419325","doi":"https://doi.org/10.1109/icassp.2002.5745022","mag":"2098419325"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745022","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/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":true,"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","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","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/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":[]}]},{"author_position":"last","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":false,"raw_author_name":"C. C. Broun","raw_affiliation_strings":["Motorola Human Interface Labs, Tempe, Arizona, USA","Motorola Human Interface Labs, Tempe, Arizona 85284, USA"],"affiliations":[{"raw_affiliation_string":"Motorola Human Interface Labs, Tempe, Arizona, 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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064140731"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.3191,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.75791275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"II","last_page":"1993"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9840999841690063,"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/computer-science","display_name":"Computer science","score":0.7994814515113831},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7928733229637146},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.590122640132904},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48922252655029297},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48658859729766846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4786716401576996},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45772939920425415},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4378530979156494},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42977291345596313},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.426057368516922},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41869181394577026},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38583987951278687},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1048818826675415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7994814515113831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7928733229637146},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.590122640132904},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48922252655029297},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48658859729766846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4786716401576996},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45772939920425415},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4378530979156494},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42977291345596313},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.426057368516922},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41869181394577026},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38583987951278687},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1048818826675415},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/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.2002.5745022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745022","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-1264","is_oa":false,"landing_page_url":"https://digitalcommons.calpoly.edu/eeng_fac/264","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W1929897159","https://openalex.org/W2021279213","https://openalex.org/W2106844098","https://openalex.org/W2108492645","https://openalex.org/W2133906911","https://openalex.org/W2142518644","https://openalex.org/W2487271655","https://openalex.org/W6681081894"],"related_works":["https://openalex.org/W1560125148","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2556771176"],"abstract_inverted_index":{"Mainstream":[0],"automatic":[1],"speech":[2,47,99,112,140],"recognition":[3,126,155,194],"has":[4],"focused":[5],"almost":[6],"exclusively":[7],"on":[8,153],"the":[9,20,24,29,59,73,93,137,145,154,160,167,170,173,179],"acoustic":[10,74,82],"signal.":[11],"The":[12],"performance":[13,180],"of":[14,26,42,95,133,139,147,150,172],"these":[15],"systems":[16],"degrades":[17],"considerably":[18],"in":[19,23,49,72,85,98,118,187],"real":[21],"world":[22],"presence":[25],"noise.":[27],"On":[28],"other":[30],"hand,":[31],"most":[32],"human":[33],"listeners,":[34],"both":[35,188],"hearing-impaired":[36],"and":[37,76,109,130,175,191],"normal":[38],"hearing,":[39],"make":[40],"use":[41],"visual":[43,60,96,111,134,151],"information":[44,66,97,168],"to":[45,57,64,128],"improve":[46,178],"perception":[48],"acoustically":[50],"hostile":[51],"environments.":[52,87],"Motivated":[53],"by":[54],"humans'":[55],"ability":[56],"lipread,":[58],"component":[61],"is":[62,68],"considered":[63],"yield":[65],"that":[67,159],"not":[69],"always":[70],"present":[71,103],"signal":[75],"enables":[77],"improved":[78],"accuracy":[79],"over":[80,181],"totally":[81],"systems,":[83],"especially":[84],"noisy":[86],"In":[88],"this":[89],"paper,":[90],"we":[91],"investigate":[92],"usefulness":[94],"recognition.":[100,141],"We":[101,122,142,157],"first":[102],"a":[104,115,125],"method":[105],"for":[106,136],"automatically":[107],"locating":[108],"extracting":[110],"features":[113,152,164,186],"from":[114],"talking":[116],"person":[117],"color":[119],"video":[120],"sequences.":[121],"then":[123],"develop":[124],"engine":[127],"train":[129],"recognize":[131],"sequences":[132],"parameters":[135],"purpose":[138],"particularly":[143],"explore":[144],"impact":[146],"various":[148],"combinations":[149],"accuracy.":[156],"conclude":[158],"inner":[161],"lip":[162],"contour":[163,184],"together":[165],"with":[166],"about":[169],"visibility":[171],"tongue":[174],"teeth":[176],"significantly":[177],"using":[182],"outer":[183],"only":[185],"speaker":[189,192],"dependent":[190],"independent":[193],"tasks.":[195]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}