{"id":"https://openalex.org/W3118036524","doi":"https://doi.org/10.1109/tencon50793.2020.9293784","title":"Improved Viseme Recognition using Generative Adversarial Networks","display_name":"Improved Viseme Recognition using Generative Adversarial Networks","publication_year":2020,"publication_date":"2020-11-16","ids":{"openalex":"https://openalex.org/W3118036524","doi":"https://doi.org/10.1109/tencon50793.2020.9293784","mag":"3118036524"},"language":"en","primary_location":{"id":"doi:10.1109/tencon50793.2020.9293784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon50793.2020.9293784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","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/A5003510504","display_name":"Jayanth Shreekumar","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Jayanth Shreekumar","raw_affiliation_strings":["Electronics and Communication, PES University, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Electronics and Communication, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037388462","display_name":"Ganesh K Shet","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ganesh K Shet","raw_affiliation_strings":["Electronics and Communication, PES University, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Electronics and Communication, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109484534","display_name":"Pranav Vijay","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vijay P N","raw_affiliation_strings":["Electronics and Communication, PES University, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Electronics and Communication, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039382012","display_name":"S. Preethi","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preethi S J","raw_affiliation_strings":["Electronics and Communication, PES University, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Electronics and Communication, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075281607","display_name":"Niranjana Krupa","orcid":"https://orcid.org/0000-0003-4785-0400"},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Niranjana Krupa","raw_affiliation_strings":["Electronics and Communication, PES University, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Electronics and Communication, PES University, Bengaluru, India","institution_ids":["https://openalex.org/I196608512"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003510504"],"corresponding_institution_ids":["https://openalex.org/I196608512"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.16688611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"10","issue":null,"first_page":"1118","last_page":"1123"},"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/T11309","display_name":"Music 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7581311464309692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6755056381225586},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6750292778015137},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6699709296226501},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6251626014709473},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.6045268177986145},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.542717695236206},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5370888113975525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5229437947273254},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5027220249176025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47389450669288635},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4602592885494232},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.44302898645401},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37142959237098694},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1566195785999298},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07107767462730408},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.05997055768966675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581311464309692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6755056381225586},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6750292778015137},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6699709296226501},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6251626014709473},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.6045268177986145},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.542717695236206},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5370888113975525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5229437947273254},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5027220249176025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47389450669288635},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4602592885494232},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.44302898645401},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37142959237098694},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1566195785999298},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07107767462730408},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.05997055768966675},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tencon50793.2020.9293784","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon50793.2020.9293784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE REGION 10 CONFERENCE (TENCON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2095705004","https://openalex.org/W2095729891","https://openalex.org/W2096391593","https://openalex.org/W2108598243","https://openalex.org/W2115252128","https://openalex.org/W2121486117","https://openalex.org/W2125389028","https://openalex.org/W2148143831","https://openalex.org/W2194775991","https://openalex.org/W2242464395","https://openalex.org/W2531409750","https://openalex.org/W2756182389","https://openalex.org/W2794022343","https://openalex.org/W2806872492","https://openalex.org/W2884547199","https://openalex.org/W2898213923","https://openalex.org/W2898336590","https://openalex.org/W2949117887","https://openalex.org/W2963684088","https://openalex.org/W2964121744","https://openalex.org/W2964261464","https://openalex.org/W2972756321","https://openalex.org/W3099202502","https://openalex.org/W4294643831","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6674543778","https://openalex.org/W6677618333","https://openalex.org/W6678815747","https://openalex.org/W6685352114","https://openalex.org/W6687483927","https://openalex.org/W6745560452","https://openalex.org/W6753038255","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W4385421777","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501"],"abstract_inverted_index":{"The":[0,86],"proliferation":[1],"of":[2,15,31,35,103,129,139],"convolutional":[3],"neural":[4],"networks":[5,64],"(CNN)":[6],"has":[7,28,37],"resulted":[8],"in":[9,12,126,136],"increased":[10],"interest":[11],"the":[13,45,101,107,113,145,151],"field":[14],"visual":[16],"speech":[17],"recognition":[18,34],"(VSR).":[19],"However,":[20],"while":[21],"VSR":[22,49,104],"for":[23,48,73,79,99],"word-level":[24],"and":[25,83],"sentence-level":[26],"classification":[27,80],"received":[29],"much":[30],"this":[32],"attention,":[33],"visemes":[36],"remained":[38],"relatively":[39],"unexplored.":[40],"This":[41],"paper":[42],"focuses":[43],"on":[44],"visemic":[46],"approach":[47],"as":[50],"it":[51],"can":[52],"be":[53],"used":[54,72,78],"to":[55,66,122],"build":[56],"language-independent":[57],"models.":[58,105],"Our":[59],"method":[60],"employs":[61],"generative":[62],"adversarial":[63],"(GANs)":[65],"create":[67],"synthetic":[68],"images":[69,110,148],"that":[70,90],"are":[71],"data":[74,91],"augmentation.":[75,85],"VGG16":[76],"is":[77,95],"both":[81],"before":[82],"after":[84],"results":[87],"obtained":[88],"prove":[89],"augmentation":[92],"using":[93,112,147],"GANs":[94],"a":[96],"viable":[97],"technique":[98],"improving":[100],"performance":[102],"Augmenting":[106],"dataset":[108,146],"with":[109],"generated":[111,149],"Progressive":[114],"Growing":[115],"Generative":[116,155],"Adversarial":[117,156],"Network":[118,157],"(PGGAN)":[119],"model":[120],"led":[121],"an":[123],"average":[124,134],"increase":[125,135],"test":[127,137],"accuracy":[128,138],"3.695%":[130],"across":[131],"speakers.":[132],"An":[133],"2.59%":[140],"was":[141],"achieved":[142],"by":[143,150],"augmenting":[144],"conditional":[152],"Deep":[153],"Convolutional":[154],"(DCGAN)":[158],"model.":[159]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}