{"id":"https://openalex.org/W2982385481","doi":"https://doi.org/10.1109/icassp40776.2020.9053852","title":"A Comparative Study of Estimating Articulatory Movements from Phoneme Sequences and Acoustic Features","display_name":"A Comparative Study of Estimating Articulatory Movements from Phoneme Sequences and Acoustic Features","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982385481","doi":"https://doi.org/10.1109/icassp40776.2020.9053852","mag":"2982385481"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.14375","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064971186","display_name":"Abhayjeet Singh","orcid":"https://orcid.org/0000-0002-8512-8083"},"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":true,"raw_author_name":"Abhayjeet Singh","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering,Bangalore,India,560012"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023231479","display_name":"Aravind Illa","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":"Aravind Illa","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering,Bangalore,India,560012"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]},{"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/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":"Prasanta Kumar Ghosh","raw_affiliation_strings":["Indian Institute of Science (IISc),Electrical Engineering,Bangalore,India,560012"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science (IISc),Electrical Engineering,Bangalore,India,560012","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064971186"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00719754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7334","last_page":"7338"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7235367298126221},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6715368032455444},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.6357855200767517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6135429739952087},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5713261365890503},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4495198428630829},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4204736351966858},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32650357484817505},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25594308972358704}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7235367298126221},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6715368032455444},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.6357855200767517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6135429739952087},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5713261365890503},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4495198428630829},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4204736351966858},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32650357484817505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25594308972358704},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:66377","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"},{"id":"pmh:oai:arXiv.org:1910.14375","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.14375","pdf_url":"https://arxiv.org/pdf/1910.14375","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2982385481","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1910.14375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.14375","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.14375","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/j4pw-4p22","is_oa":true,"landing_page_url":"https://doi.org/10.17023/j4pw-4p22","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.14375","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.14375","pdf_url":"https://arxiv.org/pdf/1910.14375","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982385481.pdf","grobid_xml":"https://content.openalex.org/works/W2982385481.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1490506669","https://openalex.org/W1524333225","https://openalex.org/W1525807100","https://openalex.org/W1531956331","https://openalex.org/W1973016470","https://openalex.org/W1982854652","https://openalex.org/W2090250131","https://openalex.org/W2101802380","https://openalex.org/W2105478683","https://openalex.org/W2132733106","https://openalex.org/W2135707066","https://openalex.org/W2141697795","https://openalex.org/W2402144811","https://openalex.org/W2402610474","https://openalex.org/W2740744211","https://openalex.org/W2888898948","https://openalex.org/W2888915262","https://openalex.org/W2889550607","https://openalex.org/W2890563690","https://openalex.org/W2940009604","https://openalex.org/W2964243274","https://openalex.org/W2973058592","https://openalex.org/W2978661203","https://openalex.org/W3194601998","https://openalex.org/W6623517193","https://openalex.org/W6629271487","https://openalex.org/W6631362777","https://openalex.org/W6631452893","https://openalex.org/W6675504311","https://openalex.org/W6713134421","https://openalex.org/W6713398208"],"related_works":["https://openalex.org/W3015908572","https://openalex.org/W1622032071","https://openalex.org/W2090255916","https://openalex.org/W2352540147","https://openalex.org/W2084681258","https://openalex.org/W2952114636","https://openalex.org/W1004616342","https://openalex.org/W1516198943","https://openalex.org/W62672326","https://openalex.org/W2040410767","https://openalex.org/W2099750345","https://openalex.org/W1496997718","https://openalex.org/W2043482182","https://openalex.org/W1857335443","https://openalex.org/W1589867908","https://openalex.org/W3197192693","https://openalex.org/W2891836073","https://openalex.org/W2030671974","https://openalex.org/W2521251085","https://openalex.org/W159384616"],"abstract_inverted_index":{"Unlike":[0],"phoneme":[1,57,75,78,144],"sequences,":[2],"movements":[3,48,65],"of":[4,96,122,130],"speech":[5],"articulators":[6],"(lips,":[7],"tongue,":[8],"jaw,":[9],"velum)":[10],"and":[11,104,125,133,185],"the":[12,22,94,114,128,172],"resultant":[13],"acoustic":[14,39,72,161],"signal":[15,162],"are":[16,187],"known":[17,43],"to":[18,44,157,181],"encode":[19],"not":[20],"only":[21,52,143],"linguistic":[23,54,173],"message":[24],"but":[25],"also":[26],"carry":[27],"para-linguistic":[28],"information.":[29,82],"While":[30,83],"several":[31],"works":[32],"exist":[33],"for":[34,89,102,190],"estimating":[35,90,191],"articulatory":[36,47,64,91,166,192],"movement":[37,92],"from":[38,53,66],"signals,":[40],"little":[41],"is":[42,87,100,168,178],"what":[45],"extent":[46],"can":[49],"be":[50],"predicted":[51],"information,":[55,150],"i.e.,":[56],"sequence.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"estimate":[63],"three":[67],"different":[68],"input":[69],"representations:":[70],"R1)":[71],"signal,":[73],"R2)":[74],"sequence,":[76],"R3)":[77],"sequence":[79,145],"with":[80,107],"timing":[81,149],"an":[84,118,153],"attention":[85,139],"network":[86,99],"used":[88,101,188],"in":[93,127,152],"case":[95,129],"R2,":[97,132],"BLSTM":[98],"R1":[103,184],"R3.":[105],"Experiments":[106],"ten":[108],"subjects\u2019":[109],"acoustic-articulatory":[110],"data":[111],"reveal":[112],"that":[113,138,158,165],"estimation":[115,154],"techniques":[116],"achieve":[117],"average":[119],"correlation":[120,176],"coefficient":[121,177],"0.85,":[123],"0.81,":[124],"0.81":[126],"R1,":[131],"R3":[134,186],"respectively.":[135],"This":[136],"indicates":[137],"network,":[140],"although":[141],"uses":[142],"(R2)":[146],"without":[147],"any":[148],"results":[151],"performance":[155],"similar":[156],"using":[159],"rich":[160],"(R1),":[163],"suggesting":[164],"motion":[167],"primarily":[169],"driven":[170],"by":[171],"message.":[174],"The":[175],"further":[179],"improved":[180],"0.88":[182],"when":[183],"together":[189],"movements.":[193]},"counts_by_year":[],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2022-07-28T00:00:00"}
