{"id":"https://openalex.org/W2064826957","doi":"https://doi.org/10.1109/isccsp.2014.6877957","title":"A lip geometry approach for feature-fusion based audio-visual speech recognition","display_name":"A lip geometry approach for feature-fusion based audio-visual speech recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2064826957","doi":"https://doi.org/10.1109/isccsp.2014.6877957","mag":"2064826957"},"language":"en","primary_location":{"id":"doi:10.1109/isccsp.2014.6877957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isccsp.2014.6877957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 6th International Symposium on Communications, Control and Signal Processing (ISCCSP)","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/A5037731226","display_name":"Mohd Zamri Ibrahim","orcid":"https://orcid.org/0000-0003-0795-4096"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]},{"id":"https://openalex.org/I102913810","display_name":"Universiti Malaysia Pahang Al-Sultan Abdullah","ror":"https://ror.org/01704wp68","country_code":"MY","type":"education","lineage":["https://openalex.org/I102913810"]}],"countries":["GB","MY"],"is_corresponding":true,"raw_author_name":"M. Z. Ibrahim","raw_affiliation_strings":["Faculty of Electrical and Electronics Engineering, University Malaysia Pahang, Pahang, Malaysia","Sch. of Electron., Electr. & Syst. Eng. Loughborough Univ., Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Faculty of Electrical and Electronics Engineering, University Malaysia Pahang, Pahang, Malaysia","institution_ids":["https://openalex.org/I102913810"]},{"raw_affiliation_string":"Sch. of Electron., Electr. & Syst. Eng. Loughborough Univ., Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109941879","display_name":"David Mulvaney","orcid":null},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"D. J. Mulvaney","raw_affiliation_strings":["Electrical and Systems Engineering, Loughborough University, United Kingdom","Sch. of Electron., Electr. & Syst. Eng. Loughborough Univ., Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Electrical and Systems Engineering, Loughborough University, United Kingdom","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"Sch. of Electron., Electr. & Syst. Eng. Loughborough Univ., Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5037731226"],"corresponding_institution_ids":["https://openalex.org/I102913810","https://openalex.org/I143804889"],"apc_list":null,"apc_paid":null,"fwci":1.1645,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79149306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"644","last_page":"647"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9937999844551086,"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":0.9934999942779541,"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":0.7126526236534119},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7028113603591919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6306649446487427},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5892127752304077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5820962190628052},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4934064447879791},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46320641040802},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.4361013174057007},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41899752616882324},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2752786874771118},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11614403128623962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126526236534119},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7028113603591919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6306649446487427},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5892127752304077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5820962190628052},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4934064447879791},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46320641040802},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.4361013174057007},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41899752616882324},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2752786874771118},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11614403128623962},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isccsp.2014.6877957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isccsp.2014.6877957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 6th International Symposium on Communications, Control and Signal Processing (ISCCSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W51714401","https://openalex.org/W1974387177","https://openalex.org/W1981706894","https://openalex.org/W2078088780","https://openalex.org/W2092744455","https://openalex.org/W2124397839","https://openalex.org/W2134867751","https://openalex.org/W2145379201","https://openalex.org/W2148659689","https://openalex.org/W2164598857","https://openalex.org/W3157685993","https://openalex.org/W4237171445"],"related_works":["https://openalex.org/W1916685473","https://openalex.org/W2055682261","https://openalex.org/W2053269318","https://openalex.org/W1993363272","https://openalex.org/W2186390138","https://openalex.org/W2364370872","https://openalex.org/W2060035984","https://openalex.org/W2790129917","https://openalex.org/W2992856432","https://openalex.org/W2100638064"],"abstract_inverted_index":{"This":[0],"paper":[1,72],"describes":[2,73],"a":[3,19,33,39],"feature-fusion":[4],"audio-visual":[5],"speech":[6,122],"recognition":[7,50,123],"(AVSR)":[8],"system":[9],"that":[10,63,101],"extracts":[11],"lip":[12],"geometry":[13],"from":[14],"the":[15,49,52,55,59,76,84,89,103,112,117,130],"mouth":[16],"region":[17],"using":[18,32],"combination":[20],"of":[21,42,61,75,114],"skin":[22],"color":[23],"filter,":[24],"border":[25],"following":[26],"and":[27,30,88],"convex":[28],"hull,":[29],"classification":[31],"Hidden":[34],"Markov":[35],"Model.":[36],"By":[37],"defining":[38],"small":[40],"number":[41],"highly":[43],"descriptive":[44],"geometrical":[45,118],"features":[46],"relevant":[47],"to":[48],"task,":[51],"approach":[53,78],"avoids":[54],"poor":[56],"scalability":[57],"(termed":[58],"`curse":[60],"dimensionality')":[62],"is":[64],"often":[65],"associated":[66],"with":[67,79,126],"featurefusion":[68],"AVSR":[69],"methods.":[70],"The":[71,106],"comparisons":[74],"new":[77,131],"conventional":[80],"appearance-based":[81,127],"methods,":[82],"namely":[83],"discrete":[85],"cosine":[86],"transform":[87],"principal":[90],"component":[91],"analysis":[92],"techniques,":[93],"when":[94],"operating":[95],"under":[96],"simulated":[97],"ambient":[98],"noise":[99],"conditions":[100],"affect":[102],"spoken":[104],"phrases.":[105],"experimental":[107],"results":[108],"demonstrate":[109],"that,":[110],"in":[111],"presence":[113],"audio":[115],"noise,":[116],"method":[119,132],"significantly":[120,134],"improves":[121],"accuracy":[124],"compared":[125],"approaches,":[128],"despite":[129],"requiring":[133],"fewer":[135],"features.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}