{"id":"https://openalex.org/W2551426144","doi":"https://doi.org/10.1109/spcom.2016.7746670","title":"A comparative study of articulatory features from facial video and acoustic-to-articulatory inversion for phonetic discrimination","display_name":"A comparative study of articulatory features from facial video and acoustic-to-articulatory inversion for phonetic discrimination","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2551426144","doi":"https://doi.org/10.1109/spcom.2016.7746670","mag":"2551426144"},"language":"en","primary_location":{"id":"doi:10.1109/spcom.2016.7746670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2016.7746670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Signal Processing and Communications (SPCOM)","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/A5021843053","display_name":"Abhishek Narwekar","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Abhishek Narwekar","raw_affiliation_strings":["Dept. of Electrical Engg, Indian Institute of Technology, Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engg, Indian Institute of Technology, Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046000500","display_name":"Prasanta Ghosh","orcid":"https://orcid.org/0000-0002-2925-1802"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prasanta Kumar Ghosh","raw_affiliation_strings":["Dept. of Electrical Engg, Indian Institute of Technology, Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engg, Indian Institute of Technology, Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021843053"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":0.2547,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55619327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"5"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.996999979019165,"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":0.761310338973999},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7406395673751831},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.4463141858577728},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4357132315635681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42001938819885254},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3639102280139923},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.36014923453330994}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761310338973999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7406395673751831},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.4463141858577728},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4357132315635681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42001938819885254},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3639102280139923},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.36014923453330994},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/spcom.2016.7746670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom.2016.7746670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:56153","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","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 Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16"},{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W40694471","https://openalex.org/W77538914","https://openalex.org/W182561118","https://openalex.org/W222076935","https://openalex.org/W1505439126","https://openalex.org/W1561506132","https://openalex.org/W1589867908","https://openalex.org/W1595584206","https://openalex.org/W1635512741","https://openalex.org/W1875231349","https://openalex.org/W1984483979","https://openalex.org/W2002620567","https://openalex.org/W2002621203","https://openalex.org/W2014621385","https://openalex.org/W2015394094","https://openalex.org/W2077804127","https://openalex.org/W2099111195","https://openalex.org/W2121486117","https://openalex.org/W2139055331","https://openalex.org/W2152826865","https://openalex.org/W2157190406","https://openalex.org/W2210387432","https://openalex.org/W2400371635","https://openalex.org/W2800394774","https://openalex.org/W3099202502","https://openalex.org/W6601705228","https://openalex.org/W6603140536","https://openalex.org/W6630097687","https://openalex.org/W6635242571","https://openalex.org/W6639350448","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W4383605217","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W2533508831","https://openalex.org/W1599055764","https://openalex.org/W48790062","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Several":[0],"studies":[1],"in":[2,47,102,214],"the":[3,8,12,18,25,33,43,51,54,63,78,81,96,118,122,125,153,185,195,202,208,223],"past":[4],"have":[5,161],"shown":[6],"that":[7,32,41,50,60,184,207],"features":[9,149,187,197,213],"based":[10],"on":[11],"kinematics":[13],"of":[14,42,171,210],"speech":[15,35,82,109],"articulators":[16,56,68,83,127],"improve":[17],"phonetic":[19,130],"recognition":[20,36,215],"accuracy":[21],"when":[22,132],"combined":[23,148],"with":[24,134],"acoustic":[26,64,137,146,203,224],"features.":[27,65,138,204],"It":[28],"is":[29,38,57,98,150],"also":[30],"known":[31],"audio-visual":[34,167],"performance":[37],"better":[39],"than":[40,194,201],"audio-only":[44],"recognition,":[45],"which,":[46],"turn,":[48],"indicates":[49],"information":[52,119,140,155],"from":[53,73,108,222],"visible":[55,67,123,196,211],"complementary":[58],"to":[59],"provided":[61,120,141],"by":[62,121,142,152,176,189,219],"Typically,":[66],"can":[69],"be":[70,217],"extracted":[71],"directly":[72,100],"a":[74,163],"facial":[75],"video.":[76],"On":[77],"other":[79],"hand,":[80],"are":[84,191],"recorded":[85],"using":[86,110,180],"electromagnetic":[87],"articulography":[88],"(EMA),":[89],"which":[90],"requires":[91],"highly":[92],"specialized":[93],"equipment.":[94],"Thus,":[95],"latter":[97],"not":[99],"available":[101],"practice":[103],"and":[104,124,135,147],"hence":[105],"usually":[106],"estimated":[107,126,188],"acoustic-to-articulatory":[111],"inversion.":[112],"In":[113],"this":[114,158],"work,":[115],"we":[116,160],"compare":[117],"about":[128],"different":[129,143],"classes":[131],"used":[133],"without":[136],"The":[139],"visible,":[144],"articulatory,":[145],"quantified":[151],"mutual":[154],"(MI).":[156],"For":[157],"study,":[159],"created":[162],"large":[164],"phonetically":[165],"rich":[166],"(PRAV)":[168],"dataset":[169],"comprising":[170],"9000":[172],"TIMIT":[173],"sentences":[174],"spoken":[175],"four":[177],"subjects.":[178],"Experiments":[179],"PRAV":[181],"corpus":[182],"reveal":[183],"articulatory":[186,212],"inversion":[190],"more":[192],"informative":[193,200],"but":[198],"less":[199],"This":[205],"suggests":[206],"advantage":[209],"could":[216],"achieved":[218],"recovering":[220],"them":[221],"signal":[225],"itself.":[226]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}