{"id":"https://openalex.org/W3158189221","doi":"https://doi.org/10.21437/interspeech.2021-1375","title":"Estimating Articulatory Movements in Speech Production with Transformer Networks","display_name":"Estimating Articulatory Movements in Speech Production with Transformer Networks","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3158189221","doi":"https://doi.org/10.21437/interspeech.2021-1375","mag":"3158189221"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1375","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.05017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023703313","display_name":"Sathvik Udupa","orcid":"https://orcid.org/0000-0002-2225-5464"},"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":"Sathvik Udupa","raw_affiliation_strings":["Indian Institute of Science Bangalore, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059878707","display_name":"Anwesha Roy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anwesha Roy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","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":false,"raw_author_name":"Abhayjeet Singh","raw_affiliation_strings":["Indian Institute of Science Bangalore, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Bangalore, Bengaluru, India","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 Bangalore, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Bangalore, Bengaluru, India","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 Bangalore, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04335633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9984999895095825,"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/transformer","display_name":"Transformer","score":0.725382924079895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6438549757003784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5909036993980408},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4826565384864807},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4662095010280609},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.43536248803138733},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23360031843185425},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.142338365316391},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12353888154029846},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1195107102394104}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.725382924079895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6438549757003784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5909036993980408},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4826565384864807},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4662095010280609},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.43536248803138733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23360031843185425},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.142338365316391},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12353888154029846},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1195107102394104},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1375","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:70646","is_oa":false,"landing_page_url":"http://eprints.iisc.ac.in/70646/1/INTERSPEECH_2021.pdf","pdf_url":"http://eprints.iisc.ac.in/70646/1/INTERSPEECH_2021.pdf","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 Paper"},{"id":"pmh:oai:arXiv.org:2104.05017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05017","pdf_url":"https://arxiv.org/pdf/2104.05017","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3158189221","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.05017.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2104.05017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.05017","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.05017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05017","pdf_url":"https://arxiv.org/pdf/2104.05017","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310071","display_name":"Indian Institute of Science","ror":"https://ror.org/04dese585"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158189221.pdf","grobid_xml":"https://content.openalex.org/works/W3158189221.grobid-xml"},"referenced_works_count":30,"referenced_works":["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/W2101802380","https://openalex.org/W2105478683","https://openalex.org/W2132733106","https://openalex.org/W2135707066","https://openalex.org/W2141697795","https://openalex.org/W2402610474","https://openalex.org/W2795138957","https://openalex.org/W2888815947","https://openalex.org/W2888898948","https://openalex.org/W2888915262","https://openalex.org/W2889550607","https://openalex.org/W2890563690","https://openalex.org/W2903739847","https://openalex.org/W2963403868","https://openalex.org/W2963925437","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2970971581","https://openalex.org/W2973058592","https://openalex.org/W2978661203","https://openalex.org/W2985287635","https://openalex.org/W3015908572","https://openalex.org/W3034949308","https://openalex.org/W3194601998"],"related_works":["https://openalex.org/W3197192693","https://openalex.org/W2084681258","https://openalex.org/W2952114636","https://openalex.org/W1516198943","https://openalex.org/W3160719719","https://openalex.org/W1004616342","https://openalex.org/W3015908572","https://openalex.org/W2352540147","https://openalex.org/W2891836073","https://openalex.org/W1622032071","https://openalex.org/W2043482182","https://openalex.org/W2294941847","https://openalex.org/W3096024701","https://openalex.org/W159384616","https://openalex.org/W1496997718","https://openalex.org/W1967225196","https://openalex.org/W1506223230","https://openalex.org/W2019977809","https://openalex.org/W2403459132","https://openalex.org/W2099750345"],"abstract_inverted_index":{"We":[0,73,81,105,149],"estimate":[1],"articulatory":[2,15,28,43,71],"movements":[3],"in":[4,36,97,113,138],"speech":[5],"production":[6],"from":[7],"different":[8],"modalities":[9],"-":[10,57],"acoustics":[11],"and":[12,41,70,86,118,134],"phonemes.":[13],"Acoustic-to":[14],"inversion":[16],"(AAI)":[17],"is":[18],"a":[19,33,54,76],"sequence-to-sequence":[20],"task.":[21],"On":[22],"the":[23,39,42,51,68,94,127,141,146,152],"other":[24],"hand,":[25],"phoneme":[26],"to":[27,63,92,99,145],"(PTA)":[29],"motion":[30],"estimation":[31,95],"faces":[32],"key":[34],"challenge":[35],"reliably":[37],"aligning":[38],"text":[40],"movements.":[44,72],"To":[45],"address":[46],"this":[47],"challenge,":[48],"we":[49,130],"explore":[50],"use":[52,82],"of":[53,155],"transformer":[55,77,157],"architecture":[56,158],"FastSpeech,":[58],"with":[59,115],"explicit":[60],"duration":[61],"modelling":[62],"learn":[64],"hard":[65],"alignments":[66],"between":[67],"phonemes":[69],"also":[74],"train":[75],"model":[78],"on":[79,102,126,140],"AAI.":[80],"correlation":[83],"coefficient":[84],"(CC)":[85],"root":[87],"mean":[88],"squared":[89],"error":[90],"(rMSE)":[91],"assess":[93],"performance":[96],"comparison":[98],"existing":[100],"methods":[101],"both":[103],"tasks.":[104],"observe":[106],"154%,":[107],"11.8%":[108],"&":[109],"4.8%":[110],"relative":[111,136],"improvement":[112],"CC":[114,139],"subject-dependent,":[116],"pooled":[117],"fine-tuning":[119],"strategies,":[120],"respectively,":[121],"for":[122],"PTA":[123],"estimation.":[124],"Additionally,":[125],"AAI":[128],"task,":[129],"obtain":[131],"1.5%,":[132],"3%":[133],"3.1%":[135],"gain":[137],"same":[142],"setups":[143],"compared":[144],"state-of-the-art":[147],"baseline.":[148],"further":[150],"present":[151],"computational":[153],"benefits":[154],"having":[156],"as":[159],"representation":[160],"blocks.":[161]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}