{"id":"https://openalex.org/W2141711441","doi":"https://doi.org/10.1109/dicta.2007.4426769","title":"Visual Speech Recognition and Utterance Segmentation Based on Mouth Movement","display_name":"Visual Speech Recognition and Utterance Segmentation Based on Mouth Movement","publication_year":2007,"publication_date":"2007-12-01","ids":{"openalex":"https://openalex.org/W2141711441","doi":"https://doi.org/10.1109/dicta.2007.4426769","mag":"2141711441"},"language":"en","primary_location":{"id":"doi:10.1109/dicta.2007.4426769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2007.4426769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017838856","display_name":"Wai Chee Yau","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":"Wai Chee Yau","raw_affiliation_strings":["School of Electrical and Computer Engineering, RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052423276","display_name":"Hans Weghorn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hans Weghorn","raw_affiliation_strings":["Information Technology, BA-University of Cooperative Education, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"Information Technology, BA-University of Cooperative Education, Stuttgart, Germany","institution_ids":[]}]},{"author_position":"last","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 Kant Kumar","raw_affiliation_strings":["School of Electrical and Computer Engineering, RMIT University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017838856"],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.17226116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"7","last_page":"14"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9952999949455261,"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":0.8253710269927979},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7338748574256897},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6889219284057617},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6559085845947266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5562915205955505},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5200324058532715},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5177649259567261},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4919302463531494},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4234592020511627},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39462876319885254},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36680591106414795},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.3535962700843811}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253710269927979},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7338748574256897},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6889219284057617},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6559085845947266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562915205955505},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5200324058532715},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5177649259567261},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4919302463531494},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4234592020511627},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39462876319885254},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36680591106414795},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3535962700843811},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/dicta.2007.4426769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta.2007.4426769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma61RMIT.INST:11248120320001341","is_oa":false,"landing_page_url":"https://researchrepository.rmit.edu.au/esploro/outputs/conferenceProceeding/Visual-speech-recognition-and-utterance-segmentation/9921863488601341","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:researchbank.rmit.edu.au:rmit:1570","is_oa":false,"landing_page_url":"http://researchbank.rmit.edu.au/view/rmit:1570","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":"Conference Paper"},{"id":"pmh:oai:alma.61RMIT_INST:11248120320001341","is_oa":false,"landing_page_url":"http://doi.org/10.1109/DICTA.2007.4426769","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/27352614","is_oa":true,"landing_page_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27352614","is_oa":true,"landing_page_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W13119895","https://openalex.org/W121610373","https://openalex.org/W161160007","https://openalex.org/W1499889635","https://openalex.org/W1505362415","https://openalex.org/W1529401398","https://openalex.org/W1894724970","https://openalex.org/W2086936614","https://openalex.org/W2089674526","https://openalex.org/W2096391593","https://openalex.org/W2096651761","https://openalex.org/W2115755118","https://openalex.org/W2116305477","https://openalex.org/W2118376687","https://openalex.org/W2130997456","https://openalex.org/W2139212933","https://openalex.org/W2146880335","https://openalex.org/W2148603752","https://openalex.org/W2149187660","https://openalex.org/W2150251355","https://openalex.org/W2153635508","https://openalex.org/W2155765376","https://openalex.org/W2162435945","https://openalex.org/W2163361484","https://openalex.org/W2165715280","https://openalex.org/W2166835904","https://openalex.org/W2171246813","https://openalex.org/W3120421331","https://openalex.org/W6600539764","https://openalex.org/W6606619957","https://openalex.org/W6684699587"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2164637175","https://openalex.org/W2052688117","https://openalex.org/W642007152","https://openalex.org/W2008120082","https://openalex.org/W2184127972","https://openalex.org/W596245619","https://openalex.org/W2320148263"],"abstract_inverted_index":{"This":[0,39],"paper":[1],"presents":[2],"a":[3,34,42,90,98],"vision-based":[4],"approach":[5],"to":[6,25,46,63],"recognize":[7],"speech":[8,36,83],"without":[9],"evaluating":[10],"the":[11,48,80],"acoustic":[12],"signals.":[13],"The":[14,75],"proposed":[15,81],"technique":[16,85],"combines":[17],"motion":[18],"features":[19],"and":[20,50,65,114],"support":[21],"vector":[22],"machines":[23],"(SVMs)":[24],"classify":[26],"utterances.":[27],"Segmentation":[28],"of":[29,53,96,116],"utterances":[30,55],"is":[31],"important":[32],"in":[33,89,120],"visual":[35,82],"recognition":[37,84],"system.":[38],"research":[40],"proposes":[41],"video":[43],"segmentation":[44],"method":[45],"detect":[47],"start":[49],"end":[51],"frames":[52],"isolated":[54],"from":[56],"an":[57],"image":[58],"sequence.":[59],"Frames":[60],"that":[61,79],"correspond":[62],"`speaking'":[64],"`silence'":[66],"phases":[67],"are":[68],"identified":[69],"based":[70],"on":[71],"mouth":[72],"movement":[73],"information.":[74],"experimental":[76],"results":[77],"demonstrate":[78],"yields":[86],"high":[87],"accuracy":[88],"phoneme":[91],"classification":[92],"task.":[93],"Potential":[94],"applications":[95],"such":[97],"system":[99],"are,":[100],"e.g.,":[101],"human":[102],"computer":[103,118],"interface":[104],"(HCI)":[105],"for":[106],"mobility-impaired":[107],"users,":[108],"lip-reading":[109],"mobile":[110],"phones,":[111],"in-vehicle":[112],"systems,":[113],"improvement":[115],"speech-based":[117],"control":[119],"noisy":[121],"environments.":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
