{"id":"https://openalex.org/W2108492645","doi":"https://doi.org/10.1155/s1110865702206137","title":"Automatic Speechreading with Applications to Human-Computer Interfaces","display_name":"Automatic Speechreading with Applications to Human-Computer Interfaces","publication_year":2002,"publication_date":"2002-11-28","ids":{"openalex":"https://openalex.org/W2108492645","doi":"https://doi.org/10.1155/s1110865702206137","mag":"2108492645"},"language":"en","primary_location":{"id":"doi:10.1155/s1110865702206137","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865702206137","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865702206137","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865702206137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101826189","display_name":"Xiaozheng Zhang","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":true,"raw_author_name":"Xiaozheng Zhang","raw_affiliation_strings":["Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, 30332-0250, USA","Center for Signal and Image Processing, Georgia Inst. of Technology, Atlanta, GA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, 30332-0250, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Inst. of Technology, Atlanta, GA#TAB#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049279499","display_name":"Charles C. Broun","orcid":null},"institutions":[{"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"]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles C. Broun","raw_affiliation_strings":["Motorola Human Interface Lab, Tempe, AZ, 85284, USA","Motorola Human Interface Lab, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"Motorola Human Interface Lab, Tempe, AZ, 85284, USA","institution_ids":["https://openalex.org/I1333370159","https://openalex.org/I2802964274"]},{"raw_affiliation_string":"Motorola Human Interface Lab, Tempe, AZ","institution_ids":["https://openalex.org/I1333370159","https://openalex.org/I2802964274"]}]},{"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":"Russell M. Mersereau","raw_affiliation_strings":["Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, 30332-0250, USA","Center for Signal and Image Processing, Georgia Inst. of Technology, Atlanta, GA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, 30332-0250, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Inst. of Technology, Atlanta, GA#TAB#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112196915","display_name":"Mark A. Clements","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":"Mark A. Clements","raw_affiliation_strings":["Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, 30332-0250, USA","Center for Signal and Image Processing, Georgia Inst. of Technology, Atlanta, GA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, 30332-0250, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Inst. of Technology, Atlanta, GA#TAB#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101826189"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":{"value":1140,"currency":"GBP","value_usd":1398},"apc_paid":{"value":1140,"currency":"GBP","value_usd":1398},"fwci":4.3338,"has_fulltext":true,"cited_by_count":78,"citation_normalized_percentile":{"value":0.95286243,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2002","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9919000267982483,"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":0.8761553764343262},{"id":"https://openalex.org/keywords/speechreading","display_name":"Speechreading","score":0.8533710837364197},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.568189799785614},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5601518750190735},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4930362403392792},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49286818504333496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4707746207714081},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4341393709182739},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42195558547973633},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35208237171173096},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08957734704017639}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8761553764343262},{"id":"https://openalex.org/C2910309083","wikidata":"https://www.wikidata.org/wiki/Q1069953","display_name":"Speechreading","level":2,"score":0.8533710837364197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.568189799785614},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5601518750190735},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4930362403392792},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49286818504333496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4707746207714081},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4341393709182739},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42195558547973633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35208237171173096},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08957734704017639},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/s1110865702206137","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865702206137","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865702206137","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:digitalcommons.calpoly.edu:eeng_fac-1263","is_oa":true,"landing_page_url":"https://digitalcommons.calpoly.edu/eeng_fac/263","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical Engineering","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1155/s1110865702206137","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865702206137","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865702206137","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2108492645.pdf","grobid_xml":"https://content.openalex.org/works/W2108492645.grobid-xml"},"referenced_works_count":88,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W85976583","https://openalex.org/W782650245","https://openalex.org/W1492120597","https://openalex.org/W1503267292","https://openalex.org/W1507784379","https://openalex.org/W1527240141","https://openalex.org/W1529401398","https://openalex.org/W1549662771","https://openalex.org/W1549965231","https://openalex.org/W1554544485","https://openalex.org/W1559276497","https://openalex.org/W1560013842","https://openalex.org/W1576996184","https://openalex.org/W1581684448","https://openalex.org/W1810525912","https://openalex.org/W1929897159","https://openalex.org/W1969938578","https://openalex.org/W1975259674","https://openalex.org/W1982916799","https://openalex.org/W1997418877","https://openalex.org/W1998936286","https://openalex.org/W2004315210","https://openalex.org/W2014621385","https://openalex.org/W2019635781","https://openalex.org/W2020278873","https://openalex.org/W2020999234","https://openalex.org/W2021279213","https://openalex.org/W2032243055","https://openalex.org/W2042732685","https://openalex.org/W2058542017","https://openalex.org/W2067807322","https://openalex.org/W2071396781","https://openalex.org/W2074392786","https://openalex.org/W2078545638","https://openalex.org/W2086699924","https://openalex.org/W2093772147","https://openalex.org/W2096651761","https://openalex.org/W2098419325","https://openalex.org/W2104095591","https://openalex.org/W2106137268","https://openalex.org/W2111429641","https://openalex.org/W2113786253","https://openalex.org/W2115689562","https://openalex.org/W2120942276","https://openalex.org/W2121486117","https://openalex.org/W2125848778","https://openalex.org/W2128233565","https://openalex.org/W2132297779","https://openalex.org/W2133059825","https://openalex.org/W2133906911","https://openalex.org/W2145620878","https://openalex.org/W2148173335","https://openalex.org/W2151043030","https://openalex.org/W2151096985","https://openalex.org/W2153493250","https://openalex.org/W2153746365","https://openalex.org/W2157190406","https://openalex.org/W2163945819","https://openalex.org/W2164450870","https://openalex.org/W2400120711","https://openalex.org/W2481376636","https://openalex.org/W2487271655","https://openalex.org/W2798121865","https://openalex.org/W2798909945","https://openalex.org/W3000615308","https://openalex.org/W3099202502","https://openalex.org/W3141836680","https://openalex.org/W3169507310","https://openalex.org/W3179102351","https://openalex.org/W4238694810","https://openalex.org/W4239123348","https://openalex.org/W4244018879","https://openalex.org/W4249533638","https://openalex.org/W4252770108","https://openalex.org/W6631618440","https://openalex.org/W6633362792","https://openalex.org/W6650283169","https://openalex.org/W6675770446","https://openalex.org/W6677096434","https://openalex.org/W6678953819","https://openalex.org/W6680096826","https://openalex.org/W6681533019","https://openalex.org/W6683897304","https://openalex.org/W6684209796","https://openalex.org/W6785273600","https://openalex.org/W6798175302","https://openalex.org/W7073696389"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2488941600","https://openalex.org/W22517275"],"abstract_inverted_index":{"There":[0],"has":[1],"been":[2],"growing":[3],"interest":[4],"in":[5,37,50,64,164],"introducing":[6],"speech":[7,62,113,168,172],"as":[8],"a":[9,71,108,119,152,165,197],"new":[10,72],"modality":[11],"into":[12,118],"the":[13,19,24,38,58,77,88,134,138,143,146,186],"human-computer":[14],"interface":[15],"(HCI).":[16],"Motivated":[17],"by":[18,80,91],"multimodal":[20],"nature":[21],"of":[22,60,94,111,145,199],"speech,":[23],"visual":[25,61,112,125,154,187],"component":[26],"is":[27,33,189],"considered":[28],"to":[29,129],"yield":[30],"information":[31,63,85,99,188],"that":[32,161,185],"not":[34],"always":[35],"present":[36,123],"acoustic":[39,200],"signal":[40,169],"and":[41,83,86,97,115,142,148,174],"enables":[42],"improved":[43],"system":[44],"performance":[45,127,195],"over":[46,196],"acoustic-only":[47],"methods,":[48],"especially":[49],"noisy":[51],"environments.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,157],"investigate":[57],"usefulness":[59],"HCI":[65],"related":[66],"applications.":[67],"We":[68,105,122],"first":[69],"introduce":[70],"algorithm":[73],"for":[74,192],"automatically":[75],"locating":[76],"mouth":[78],"region":[79,90],"using":[81,151],"color":[82,96],"motion":[84],"segmenting":[87],"lip":[89,139],"making":[92],"use":[93],"both":[95],"edge":[98],"based":[100,180],"on":[101,133,181],"Markov":[102],"random":[103],"fields.":[104],"then":[106],"derive":[107],"relevant":[109],"set":[110],"parameters":[114],"incorporate":[116],"them":[117],"recognition":[120,135,173,194],"engine.":[121],"various":[124],"feature":[126,155],"comparisons":[128],"explore":[130],"their":[131],"impact":[132],"accuracy,":[136],"including":[137],"inner":[140],"contour":[141],"visibility":[144],"tongue":[147],"teeth.":[149],"By":[150],"common":[153],"set,":[156],"demonstrate":[158,184],"two":[159,182],"applications":[160],"exploit":[162],"speechreading":[163],"joint":[166],"audio-visual":[167],"processing":[170],"task:":[171],"speaker":[175],"verification.":[176],"The":[177],"experimental":[178],"results":[179],"databases":[183],"highly":[190],"effective":[191],"improving":[193],"variety":[198],"noise":[201],"levels.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}