{"id":"https://openalex.org/W3167366044","doi":"https://doi.org/10.1145/3450618.3469176","title":"Silent Speech and Emotion Recognition from Vocal Tract Shape Dynamics in Real-Time MRI","display_name":"Silent Speech and Emotion Recognition from Vocal Tract Shape Dynamics in Real-Time MRI","publication_year":2021,"publication_date":"2021-08-05","ids":{"openalex":"https://openalex.org/W3167366044","doi":"https://doi.org/10.1145/3450618.3469176","mag":"3167366044"},"language":"en","primary_location":{"id":"doi:10.1145/3450618.3469176","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3450618.3469176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Posters","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/2106.08706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103065161","display_name":"Laxmi Pandey","orcid":"https://orcid.org/0000-0001-8523-7741"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Laxmi Pandey","raw_affiliation_strings":["University of California Merced, United States of America","University of California Merced"],"affiliations":[{"raw_affiliation_string":"University of California Merced, United States of America","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"University of California Merced","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034325005","display_name":"Ahmed Sabbir Arif","orcid":"https://orcid.org/0000-0002-8384-4764"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Sabbir Arif","raw_affiliation_strings":["University of California Merced, United States of America","University of California Merced"],"affiliations":[{"raw_affiliation_string":"University of California Merced, United States of America","institution_ids":["https://openalex.org/I156087764"]},{"raw_affiliation_string":"University of California Merced","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103065161"],"corresponding_institution_ids":["https://openalex.org/I156087764"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06778217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9980000257492065,"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":0.9976000189781189,"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/vocal-tract","display_name":"Vocal tract","score":0.8817684650421143},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7096377611160278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6465665698051453},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.6260706186294556},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5611537098884583},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.48607829213142395},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.4643478989601135},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.45880451798439026},{"id":"https://openalex.org/keywords/manner-of-articulation","display_name":"Manner of articulation","score":0.4273050129413605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41806384921073914},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3970777988433838},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.36615318059921265}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8817684650421143},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7096377611160278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6465665698051453},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.6260706186294556},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5611537098884583},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.48607829213142395},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4643478989601135},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.45880451798439026},{"id":"https://openalex.org/C66029223","wikidata":"https://www.wikidata.org/wiki/Q210847","display_name":"Manner of articulation","level":2,"score":0.4273050129413605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41806384921073914},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3970777988433838},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.36615318059921265},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3450618.3469176","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3450618.3469176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Posters","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.08706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08706","pdf_url":"https://arxiv.org/pdf/2106.08706","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":"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:3167366044","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2106.08706","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.2106.08706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.08706","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.08706","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08706","pdf_url":"https://arxiv.org/pdf/2106.08706","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":"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":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3167366044.pdf","grobid_xml":"https://content.openalex.org/works/W3167366044.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1489098793","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W1983364832","https://openalex.org/W2095705004","https://openalex.org/W2119610351","https://openalex.org/W2127141656","https://openalex.org/W2182927573","https://openalex.org/W2187654922","https://openalex.org/W2193413348","https://openalex.org/W2314163059","https://openalex.org/W2578229578","https://openalex.org/W2696259631","https://openalex.org/W2884768626","https://openalex.org/W2912526802","https://openalex.org/W2949120115","https://openalex.org/W2953384591","https://openalex.org/W2962851944","https://openalex.org/W2964121744","https://openalex.org/W2972691962","https://openalex.org/W3163934237"],"related_works":["https://openalex.org/W3190519930","https://openalex.org/W2981410855","https://openalex.org/W2767887339","https://openalex.org/W2171209503","https://openalex.org/W3021879315","https://openalex.org/W2141114508","https://openalex.org/W3046440749","https://openalex.org/W1826208965","https://openalex.org/W2606460785","https://openalex.org/W3127944602","https://openalex.org/W1512724978","https://openalex.org/W2163180231","https://openalex.org/W2980917218","https://openalex.org/W2122886924","https://openalex.org/W3046248521","https://openalex.org/W1489404612","https://openalex.org/W2998790278","https://openalex.org/W2065910677","https://openalex.org/W189529222","https://openalex.org/W2395719637"],"abstract_inverted_index":{"Speech":[0],"sounds":[1],"of":[2,10,31,52,75,112,124,143,148,153],"spoken":[3,126],"language":[4],"are":[5],"obtained":[6],"by":[7,60,135,182],"varying":[8],"configuration":[9],"the":[11,14,28,49,82,91,94,106,110,117,122,146,154],"articulators":[12],"surrounding":[13],"vocal":[15,53,155],"tract.":[16],"They":[17],"contain":[18],"abundant":[19],"information":[20,47],"that":[21,44,120,176],"can":[22],"be":[23],"utilized":[24],"to":[25,105,169],"better":[26,103],"understand":[27],"underlying":[29],"mechanism":[30],"human":[32],"speech":[33,57],"production.":[34],"We":[35,138],"propose":[36],"a":[37,78,97],"novel":[38],"deep":[39],"neural":[40],"network-based":[41],"learning":[42],"framework":[43,73],"understands":[45],"acoustic":[46],"in":[48,145,150],"variable-length":[50],"sequence":[51],"tract":[54,156],"shaping":[55],"during":[56],"production,":[58],"captured":[59,134],"real-time":[61],"magnetic":[62],"resonance":[63],"imaging":[64],"(rtMRI),":[65],"and":[66,81,160,172,185],"translate":[67],"it":[68],"into":[69],"text.":[70],"The":[71],"proposed":[72],"comprises":[74],"spatiotemporal":[76],"convolutions,":[77],"recurrent":[79],"network,":[80],"connectionist":[83],"temporal":[84],"classification":[85],"loss,":[86],"trained":[87],"entirely":[88],"end-to-end.":[89],"On":[90],"USC-TIMIT":[92],"corpus,":[93],"model":[95],"achieved":[96],"40.6%":[98],"PER":[99],"at":[100],"sentence-level,":[101],"much":[102],"compared":[104],"existing":[107],"models.":[108],"To":[109],"best":[111],"our":[113],"knowledge,":[114],"this":[115],"is":[116,180],"first":[118],"study":[119],"demonstrates":[121],"recognition":[123],"entire":[125],"sentence":[127],"based":[128],"on":[129],"an":[130,141],"individual's":[131],"articulatory":[132],"motions":[133],"rtMRI":[136],"video.":[137],"also":[139],"performed":[140],"analysis":[142],"variations":[144],"geometry":[147],"articulation":[149],"each":[151,177],"sub-regions":[152,178],"(i.e.,":[157],"pharyngeal,":[158],"velar":[159],"dorsal,":[161],"hard":[162],"palate,":[163],"labial":[164],"constriction":[165],"region)":[166],"with":[167],"respect":[168],"different":[170],"emotions":[171],"genders.":[173],"Results":[174],"suggest":[175],"distortion":[179],"affected":[181],"both":[183],"emotion":[184],"gender.":[186]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}