{"id":"https://openalex.org/W3015588748","doi":"https://doi.org/10.1109/icassp40776.2020.9053111","title":"Vocal Tract Articulatory Contour Detection in Real-Time Magnetic Resonance Images Using Spatio-Temporal Context","display_name":"Vocal Tract Articulatory Contour Detection in Real-Time Magnetic Resonance Images Using Spatio-Temporal Context","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015588748","doi":"https://doi.org/10.1109/icassp40776.2020.9053111","mag":"3015588748"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053111","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":"conference-paper","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/A5021455824","display_name":"S. Ashwin Hebbar","orcid":"https://orcid.org/0000-0002-9339-850X"},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S Ashwin Hebbar","raw_affiliation_strings":["National Institute of Technology Karnataka, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Karnataka, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103065972","display_name":"Rahul Sharma","orcid":"https://orcid.org/0000-0003-1697-3897"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Sharma","raw_affiliation_strings":["University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna Somandepalli","raw_affiliation_strings":["University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030228191","display_name":"Asterios Toutios","orcid":"https://orcid.org/0000-0003-3193-2241"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asterios Toutios","raw_affiliation_strings":["University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7354","last_page":"7358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.993399977684021,"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":0.8003132343292236},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.7903326749801636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5925634503364563},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5837225317955017},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5184656977653503},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4976043999195099},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4437849819660187},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4016316533088684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003132343292236},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.7903326749801636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5925634503364563},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5837225317955017},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5184656977653503},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4976043999195099},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4437849819660187},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4016316533088684},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053111","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W855255571","https://openalex.org/W1485009520","https://openalex.org/W2032069772","https://openalex.org/W2101816108","https://openalex.org/W2158203944","https://openalex.org/W2166344791","https://openalex.org/W2270035140","https://openalex.org/W2328273089","https://openalex.org/W2614575902","https://openalex.org/W2746515373","https://openalex.org/W2886943560","https://openalex.org/W2888804310","https://openalex.org/W2916562508","https://openalex.org/W2936504074","https://openalex.org/W2938626520","https://openalex.org/W2962807789","https://openalex.org/W2963881378","https://openalex.org/W6623445213","https://openalex.org/W7063629575"],"related_works":["https://openalex.org/W2082000062","https://openalex.org/W2067459736","https://openalex.org/W2058733683","https://openalex.org/W2105635394","https://openalex.org/W953964455","https://openalex.org/W2150243332","https://openalex.org/W2010642486","https://openalex.org/W4234201046","https://openalex.org/W2804836678","https://openalex.org/W2621968591"],"abstract_inverted_index":{"Due":[0],"to":[1,4,33,73,82,93,107],"its":[2],"ability":[3,32],"visualize":[5],"and":[6,43,54,109],"measure":[7],"the":[8,27,39,44,62,90,95,111,116,134,143],"dynamics":[9,87],"of":[10,26,64],"vocal":[11],"tract":[12],"shaping":[13],"during":[14,151],"speech":[15],"production,":[16],"real-time":[17],"magnetic":[18],"resonance":[19],"imaging":[20],"(rtMRI)":[21],"has":[22],"emerged":[23],"as":[24,38],"one":[25],"prominent":[28],"research":[29],"tools.":[30],"The":[31],"track":[34],"different":[35],"articulators":[36,145],"such":[37],"tongue,":[40],"lips,":[41],"velum,":[42],"pharynx":[45],"is":[46],"a":[47,103,126],"crucial":[48],"step":[49],"toward":[50],"automating":[51],"further":[52],"scientific":[53],"clinical":[55],"analysis.":[56],"Recently,":[57],"various":[58],"researchers":[59],"have":[60],"addressed":[61],"problem":[63],"detecting":[65],"articulatory":[66,96,112],"boundaries,":[67],"but":[68],"those":[69],"are":[70],"primarily":[71],"limited":[72],"static-image":[74],"based":[75],"methods.":[76],"In":[77],"this":[78],"work,":[79],"we":[80],"propose":[81],"use":[83],"information":[84],"from":[85],"temporal":[86],"together":[88],"with":[89],"spatial":[91],"structure":[92],"detect":[94,108],"boundaries":[97],"in":[98,147],"rtMRI":[99],"videos.":[100],"We":[101,114,131],"train":[102],"convolutional":[104],"LSTM":[105],"network":[106],"label":[110],"contours.":[113],"compare":[115],"produced":[117],"contours":[118],"against":[119],"reference":[120],"labels":[121],"generated":[122],"by":[123],"iteratively":[124],"fitting":[125],"manually":[127],"created":[128],"subject-specific":[129],"template.":[130],"observe":[132],"that":[133],"proposed":[135],"method":[136],"outperforms":[137],"solely":[138],"image-based":[139],"methods,":[140],"especially":[141],"for":[142],"difficult-to-track":[144],"involved":[146],"airway":[148],"constriction":[149],"formation":[150],"speech.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
