{"id":"https://openalex.org/W2792390673","doi":"https://doi.org/10.1109/globalsip.2017.8308666","title":"Visual speech recognition for isolated digits using discrete cosine transform and local binary pattern features","display_name":"Visual speech recognition for isolated digits using discrete cosine transform and local binary pattern features","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2792390673","doi":"https://doi.org/10.1109/globalsip.2017.8308666","mag":"2792390673"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2017.8308666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2017.8308666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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/A5072470646","display_name":"Abhilash Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhilash Jain","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Science, Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042604366","display_name":"G. N. Rathna","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"G. N. Rathna","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Science, Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Science, Bangalore","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.5478,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.67849067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"368","last_page":"372"},"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":0.9947999715805054,"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/T11448","display_name":"Face recognition and analysis","score":0.9926000237464905,"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":0.7401061058044434},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.7367962002754211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7113322019577026},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6891293525695801},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6629215478897095},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6356304883956909},{"id":"https://openalex.org/keywords/local-binary-patterns","display_name":"Local binary patterns","score":0.6157897710800171},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.48263412714004517},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4590972065925598},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.44095349311828613},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4328269362449646},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.42766305804252625},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13724470138549805},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12702414393424988},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.09555813670158386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401061058044434},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.7367962002754211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7113322019577026},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6891293525695801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6629215478897095},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6356304883956909},{"id":"https://openalex.org/C87335442","wikidata":"https://www.wikidata.org/wiki/Q2494345","display_name":"Local binary patterns","level":4,"score":0.6157897710800171},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.48263412714004517},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4590972065925598},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.44095349311828613},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4328269362449646},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.42766305804252625},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13724470138549805},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12702414393424988},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.09555813670158386},{"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},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/globalsip.2017.8308666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2017.8308666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"},{"id":"pmh:oai::73206","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W1503762774","https://openalex.org/W1676820704","https://openalex.org/W2015143272","https://openalex.org/W2031614119","https://openalex.org/W2043698530","https://openalex.org/W2096391593","https://openalex.org/W2127015832","https://openalex.org/W2148956009","https://openalex.org/W2163352848","https://openalex.org/W2163808566","https://openalex.org/W2164598857","https://openalex.org/W2184188583","https://openalex.org/W2397098974","https://openalex.org/W3149793578","https://openalex.org/W4285719527","https://openalex.org/W6605737493","https://openalex.org/W6686207219"],"related_works":["https://openalex.org/W2055219403","https://openalex.org/W2791313072","https://openalex.org/W3166997759","https://openalex.org/W2794489335","https://openalex.org/W2080437822","https://openalex.org/W2020681746","https://openalex.org/W1916685473","https://openalex.org/W1589677080","https://openalex.org/W2770255720","https://openalex.org/W1560125148"],"abstract_inverted_index":{"Visual":[0],"Speech":[1],"Recognition":[2],"(VSR)":[3],"deals":[4],"with":[5],"the":[6],"task":[7,42],"of":[8,105],"extracting":[9],"speech":[10,61],"information":[11],"from":[12,15],"visual":[13,70],"cues":[14],"a":[16,40,54],"person's":[17],"face":[18],"while":[19],"speaking.":[20],"Accurate":[21],"lip":[22,37,67],"segmentation":[23],"and":[24,43,77,103],"modeling":[25,38],"are":[26],"essential":[27],"in":[28,48],"any":[29],"VSR":[30],"algorithm":[31],"for":[32,57,101],"good":[33],"feature":[34,71],"extraction.":[35],"However,":[36],"is":[39,44,99],"complicated":[41],"not":[45,65],"very":[46],"robust":[47],"natural":[49],"conditions.":[50],"This":[51],"paper":[52],"describes":[53],"novel":[55],"technique":[56],"limited":[58],"vocabulary":[59],"visual-only":[60],"recognition":[62,102],"that":[63],"does":[64],"use":[66],"modeling.":[68],"For":[69],"extraction,":[72],"Discrete":[73],"Cosine":[74],"Transform":[75],"(DCT)":[76],"Local":[78],"Binary":[79],"Pattern":[80],"(LBP)":[81],"have":[82],"been":[83],"tested.":[84],"An":[85],"Error-Correcting":[86],"Output":[87],"Codes":[88],"(ECOC)":[89],"multi-class":[90],"model":[91],"using":[92],"Support":[93],"Vector":[94],"Machine":[95],"(SVM)":[96],"binary":[97],"learners":[98],"used":[100],"classification":[104],"words.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}