{"id":"https://openalex.org/W2148872411","doi":"https://doi.org/10.1109/icsmc.2009.5346011","title":"Automatic visual feature extraction for Mandarin audio-visual speech recognition","display_name":"Automatic visual feature extraction for Mandarin audio-visual speech recognition","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2148872411","doi":"https://doi.org/10.1109/icsmc.2009.5346011","mag":"2148872411"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2009.5346011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5346011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","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/A5040187372","display_name":"Tsang-Long Pao","orcid":null},"institutions":[{"id":"https://openalex.org/I65196183","display_name":"Tatung University","ror":"https://ror.org/030m18266","country_code":"TW","type":"education","lineage":["https://openalex.org/I65196183"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsang-Long Pao","raw_affiliation_strings":["Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027271308","display_name":"Wenyuan Liao","orcid":"https://orcid.org/0000-0002-6566-9341"},"institutions":[{"id":"https://openalex.org/I65196183","display_name":"Tatung University","ror":"https://ror.org/030m18266","country_code":"TW","type":"education","lineage":["https://openalex.org/I65196183"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Yuan Liao","raw_affiliation_strings":["Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008528615","display_name":"Tsan-Nung Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I65196183","display_name":"Tatung University","ror":"https://ror.org/030m18266","country_code":"TW","type":"education","lineage":["https://openalex.org/I65196183"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsan-Nung Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101445293","display_name":"Ching\u2010Yi Lin","orcid":"https://orcid.org/0009-0009-5016-7857"},"institutions":[{"id":"https://openalex.org/I65196183","display_name":"Tatung University","ror":"https://ror.org/030m18266","country_code":"TW","type":"education","lineage":["https://openalex.org/I65196183"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ching-Yi Lin","raw_affiliation_strings":["Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Tatung University, Taipei, Taiwan","institution_ids":["https://openalex.org/I65196183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3572,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60700801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"4","issue":null,"first_page":"2936","last_page":"2940"},"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/T11448","display_name":"Face recognition and analysis","score":0.9749000072479248,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9726999998092651,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8479467630386353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7127654552459717},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6438219547271729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6417872905731201},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5696029663085938},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5496715307235718},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49915218353271484},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4731265902519226},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4401251971721649},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4156104624271393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8479467630386353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7127654552459717},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6438219547271729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6417872905731201},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5696029663085938},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5496715307235718},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49915218353271484},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4731265902519226},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4401251971721649},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4156104624271393},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2009.5346011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5346011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.75,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1563622701","https://openalex.org/W2070660347","https://openalex.org/W2083792893","https://openalex.org/W2096391593","https://openalex.org/W2101965618","https://openalex.org/W2108009821","https://openalex.org/W2111459438","https://openalex.org/W2113814270","https://openalex.org/W2116570754","https://openalex.org/W2121486117","https://openalex.org/W2130462770","https://openalex.org/W2132999255","https://openalex.org/W2133115605","https://openalex.org/W2134636830","https://openalex.org/W2157410017","https://openalex.org/W2166835904","https://openalex.org/W3149066084","https://openalex.org/W6671432306"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,34,62,96],"recognition":[2,63,71,111,118,130,161],"(ASR)":[3],"by":[4],"machine":[5],"has":[6],"been":[7],"an":[8,41],"attractive":[9],"research":[10],"area":[11],"in":[12,59,74,113],"past":[13],"several":[14],"decades.":[15],"In":[16,36],"recent":[17],"years,":[18],"there":[19],"are":[20,67],"many":[21],"automatic":[22,42],"speech-reading":[23],"systems":[24],"proposed":[25,40],"that":[26,55,151],"utilizing":[27],"the":[28,49,53,60,70,80,102,110,129,135,138,141,152,160],"combination":[29],"of":[30,52,79,94,140],"audio":[31],"and":[32,86,98,137],"visual":[33,43,50,95,122,153],"features.":[35],"this":[37,114],"paper,":[38],"we":[39],"feature":[44],"extraction":[45],"approach":[46],"to":[47,69,124],"extract":[48],"features":[51,66,123,133],"lips":[54],"can":[56],"be":[57],"used":[58,108],"audio-visual":[61],"system.":[64],"These":[65,132],"important":[68],"system,":[72],"especially":[73],"noisy":[75],"condition.":[76],"The":[77,104,143],"segmentation":[78],"lip":[81],"region":[82],"uses":[83],"both":[84],"color":[85],"edge":[87],"information.":[88],"We":[89,116],"then":[90],"establish":[91],"a":[92],"set":[93],"parameters":[97],"incorporate":[99],"them":[100],"into":[101],"recognizer.":[103],"WD-KNN":[105],"classifier":[106],"is":[107,155],"as":[109],"engine":[112],"paper.":[115],"present":[117],"performance":[119],"using":[120],"various":[121],"explore":[125],"their":[126],"impact":[127],"on":[128,147],"accuracy.":[131],"include":[134],"geometric":[136],"motion":[139],"lip.":[142],"experimental":[144],"results":[145],"based":[146],"Mandarin":[148],"databases":[149],"demonstrate":[150],"information":[154],"highly":[156],"effective":[157],"for":[158],"improving":[159],"performance.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}