{"id":"https://openalex.org/W2103620269","doi":"https://doi.org/10.1142/s1469026811003045","title":"VISUAL SPEECH RECOGNITION USING OPTICAL FLOW AND SUPPORT VECTOR MACHINES","display_name":"VISUAL SPEECH RECOGNITION USING OPTICAL FLOW AND SUPPORT VECTOR MACHINES","publication_year":2011,"publication_date":"2011-06-01","ids":{"openalex":"https://openalex.org/W2103620269","doi":"https://doi.org/10.1142/s1469026811003045","mag":"2103620269"},"language":"en","primary_location":{"id":"doi:10.1142/s1469026811003045","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1469026811003045","pdf_url":null,"source":{"id":"https://openalex.org/S206936884","display_name":"International Journal of Computational Intelligence and Applications","issn_l":"1469-0268","issn":["1469-0268","1757-5885"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Visual_speech_recognition_using_optical_flow_and_support_vector_machines/27479118","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023403648","display_name":"Ayaz A. Shaikh","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"AYAZ A. SHAIKH","raw_affiliation_strings":["School of Electrical and Computer Engineering and Health Innovations Research Institute RMIT University, Vic 3001, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering and Health Innovations Research Institute RMIT University, Vic 3001, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328491","display_name":"Dinesh Kumar","orcid":"https://orcid.org/0000-0003-3602-4023"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"DINESH K. KUMAR","raw_affiliation_strings":["School of Electrical and Computer Engineering and Health Innovations Research Institute RMIT University, Vic 3001, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering and Health Innovations Research Institute RMIT University, Vic 3001, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077902462","display_name":"Jayavardhana Gubbi","orcid":"https://orcid.org/0000-0001-5833-1898"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"JAYAVARDHANA GUBBI","raw_affiliation_strings":["ISSNIP, Department of Electrical and Electronic Engineering, The University of Melbourne, Vic 3010, Australia"],"affiliations":[{"raw_affiliation_string":"ISSNIP, Department of Electrical and Electronic Engineering, The University of Melbourne, Vic 3010, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023403648"],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.67943798,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"10","issue":"02","first_page":"167","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9086700081825256},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.753013014793396},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5897493362426758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5806339979171753},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5763100385665894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5420897603034973},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49537932872772217},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.492532342672348},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.47234880924224854},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.46074238419532776},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4333832561969757},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.4283774793148041},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.4276719093322754},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33529794216156006},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24549105763435364},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20948010683059692},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.13018754124641418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9086700081825256},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.753013014793396},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5897493362426758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5806339979171753},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5763100385665894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5420897603034973},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49537932872772217},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.492532342672348},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.47234880924224854},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.46074238419532776},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4333832561969757},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.4283774793148041},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.4276719093322754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33529794216156006},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24549105763435364},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20948010683059692},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.13018754124641418},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1142/s1469026811003045","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1469026811003045","pdf_url":null,"source":{"id":"https://openalex.org/S206936884","display_name":"International Journal of Computational Intelligence and Applications","issn_l":"1469-0268","issn":["1469-0268","1757-5885"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computational Intelligence and Applications","raw_type":"journal-article"},{"id":"pmh:oai:alma.61RMIT_INST:11247826230001341","is_oa":false,"landing_page_url":"http://doi.org/10.1142/S1469026811003045","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27479118","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Visual_speech_recognition_using_optical_flow_and_support_vector_machines/27479118","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27479118","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Visual_speech_recognition_using_optical_flow_and_support_vector_machines/27479118","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329623","display_name":"Mehran University of Engineering and Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W12212407","https://openalex.org/W1506639196","https://openalex.org/W1549662771","https://openalex.org/W1578285471","https://openalex.org/W1820427070","https://openalex.org/W1867429401","https://openalex.org/W1869391892","https://openalex.org/W1894664571","https://openalex.org/W1978799052","https://openalex.org/W2004143321","https://openalex.org/W2016067832","https://openalex.org/W2048479862","https://openalex.org/W2083792893","https://openalex.org/W2096391593","https://openalex.org/W2099168818","https://openalex.org/W2100315781","https://openalex.org/W2106174780","https://openalex.org/W2106284211","https://openalex.org/W2108492645","https://openalex.org/W2113814270","https://openalex.org/W2132529238","https://openalex.org/W2142075667","https://openalex.org/W2153635508","https://openalex.org/W2154504070","https://openalex.org/W2155765376","https://openalex.org/W2157269037","https://openalex.org/W2161827960","https://openalex.org/W2162435945","https://openalex.org/W2171246813","https://openalex.org/W2538311892","https://openalex.org/W2751023760","https://openalex.org/W2913192828","https://openalex.org/W4239751208","https://openalex.org/W4244769743","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2747895175","https://openalex.org/W2946583009","https://openalex.org/W2614669534","https://openalex.org/W2104406636","https://openalex.org/W2115788596","https://openalex.org/W2105512057","https://openalex.org/W4252625449","https://openalex.org/W2741028958","https://openalex.org/W3131201603","https://openalex.org/W2107754411"],"abstract_inverted_index":{"A":[0],"lip-reading":[1],"technique":[2,20,67],"that":[3,151],"identifies":[4],"visemes":[5,113],"from":[6,115],"visual":[7],"data":[8],"only":[9],"and":[10,32,51,76,118,124,131,164,192],"without":[11],"evaluating":[12],"the":[13,27,74,77,83,93,119,137,146,148,152],"corresponding":[14,98],"acoustic":[15],"signals":[16],"is":[17,21,43,155],"presented.":[18],"The":[19,41,104],"based":[22,196],"on":[23,108],"vertical":[24],"components":[25],"of":[26,54,63,79,82,97,111,139,169,174,194],"optical":[28],"flow":[29],"(OF)":[30],"analysis":[31],"these":[33],"are":[34,57],"classified":[35],"using":[36,122],"support":[37],"vector":[38],"machines":[39],"(SVM).":[40],"OF":[42],"decomposed":[44],"into":[45],"multiple":[46],"non-overlapping":[47],"fixed":[48],"scale":[49],"blocks":[50],"statistical":[52],"features":[53],"each":[55],"block":[56],"computed":[58],"for":[59,129,166,183],"successive":[60,102],"video":[61],"frames":[62],"an":[64,80],"utterance.":[65],"This":[66],"performs":[68],"automatic":[69],"temporal":[70],"segmentation":[71],"(i.e.,":[72],"determining":[73],"start":[75],"end":[78],"utterance)":[81],"utterances,":[84],"achieved":[85],"by":[86],"pair-wise":[87],"pixel":[88],"comparison":[89],"method,":[90],"which":[91],"evaluates":[92],"differences":[94],"in":[95,100,145,199],"intensity":[96],"pixels":[99],"two":[101],"frames.":[103],"experiments":[105],"were":[106],"conducted":[107],"a":[109,176],"database":[110],"14":[112,170],"taken":[114],"seven":[116],"subjects":[117],"accuracy":[120],"tested":[121],"five":[123],"ten":[125],"fold":[126],"cross":[127],"validation":[128],"binary":[130],"multiclass":[132],"SVM":[133],"respectively":[134],"to":[135,158],"determine":[136],"impact":[138],"subject":[140],"variations.":[141],"Unlike":[142],"other":[143],"systems":[144],"literature,":[147],"results":[149],"indicate":[150],"proposed":[153],"method":[154],"more":[156],"robust":[157],"inter-subject":[159],"variations":[160],"with":[161],"high":[162],"sensitivity":[163],"specificity":[165],"12":[167],"out":[168],"visemes.":[171],"Potential":[172],"applications":[173],"such":[175],"system":[177],"include":[178],"human":[179],"computer":[180,197],"interface":[181],"(HCI)":[182],"mobility-impaired":[184],"users,":[185],"lip":[186],"reading":[187],"mobile":[188],"phones,":[189],"in-vehicle":[190],"systems,":[191],"improvement":[193],"speech":[195],"control":[198],"noisy":[200],"environment.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"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"}