{"id":"https://openalex.org/W4362604502","doi":"https://doi.org/10.1117/12.2653345","title":"Synthesizing audio from tongue motion during speech using tagged MRI via transformer","display_name":"Synthesizing audio from tongue motion during speech using tagged MRI via transformer","publication_year":2023,"publication_date":"2023-04-03","ids":{"openalex":"https://openalex.org/W4362604502","doi":"https://doi.org/10.1117/12.2653345","pmid":"https://pubmed.ncbi.nlm.nih.gov/38009135"},"language":"en","primary_location":{"id":"doi:10.1117/12.2653345","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.2653345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Medical Imaging 2023: Image Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10669779/pdf/nihms-1870805.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100359288","display_name":"Xiaofeng Liu","orcid":"https://orcid.org/0000-0002-4514-2016"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaofeng Liu","raw_affiliation_strings":["Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114 USA"],"affiliations":[{"raw_affiliation_string":"Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114 USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007259734","display_name":"Fangxu Xing","orcid":"https://orcid.org/0000-0002-0517-0952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangxu Xing","raw_affiliation_strings":["Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114 USA"],"affiliations":[{"raw_affiliation_string":"Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114 USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066682675","display_name":"Jerry L. Prince","orcid":"https://orcid.org/0000-0002-6553-0876"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerry L. Prince","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218 USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218 USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109307699","display_name":"Maureen Stone","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maureen Stone","raw_affiliation_strings":["Department of Neural and Pain Sciences, University of Maryland School of Dentistry, Baltimore, MD 21201 USA"],"affiliations":[{"raw_affiliation_string":"Department of Neural and Pain Sciences, University of Maryland School of Dentistry, Baltimore, MD 21201 USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053436378","display_name":"Georges El Fakhri","orcid":"https://orcid.org/0000-0002-9005-6993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georges El Fakhri","raw_affiliation_strings":["Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114 USA"],"affiliations":[{"raw_affiliation_string":"Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114 USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101491780","display_name":"Jonghye Woo","orcid":"https://orcid.org/0000-0002-5621-9218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonghye Woo","raw_affiliation_strings":["Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114 USA"],"affiliations":[{"raw_affiliation_string":"Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02114 USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100359288"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3457,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63382479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"29","issue":null,"first_page":"31","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8561009168624878},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7846165299415588},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5862249135971069},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5746367573738098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5193506479263306},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3634006381034851}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8561009168624878},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7846165299415588},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5862249135971069},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5746367573738098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5193506479263306},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3634006381034851},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1117/12.2653345","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.2653345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Medical Imaging 2023: Image Processing","raw_type":"proceedings-article"},{"id":"pmid:38009135","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38009135","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of SPIE--the International Society for Optical Engineering","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10669779","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10669779","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10669779/pdf/nihms-1870805.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc SPIE Int Soc Opt Eng","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10669779","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10669779","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10669779/pdf/nihms-1870805.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc SPIE Int Soc Opt Eng","raw_type":"Text"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2859102646","display_name":null,"funder_award_id":"R01CA133015","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5391730219","display_name":null,"funder_award_id":"R01DC018511","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8646276009","display_name":null,"funder_award_id":"R01DC014717","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4362604502.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W143677236","https://openalex.org/W2065862912","https://openalex.org/W2120847449","https://openalex.org/W2724710072","https://openalex.org/W2963373786","https://openalex.org/W3015468748","https://openalex.org/W3118182541","https://openalex.org/W3118835302","https://openalex.org/W3126752887","https://openalex.org/W3165358499","https://openalex.org/W4225316786","https://openalex.org/W4229379189","https://openalex.org/W6605848209","https://openalex.org/W6667126320","https://openalex.org/W6718379498","https://openalex.org/W6732945439","https://openalex.org/W6740190199","https://openalex.org/W6746173266","https://openalex.org/W6776048684","https://openalex.org/W6779245525","https://openalex.org/W6779468923","https://openalex.org/W6787848580","https://openalex.org/W6790441406","https://openalex.org/W6810493939"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W1891287906","https://openalex.org/W2036807459","https://openalex.org/W2897924318","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W2138997758","https://openalex.org/W3116076068"],"abstract_inverted_index":{"Investigating":[0],"the":[1,9,40,54,83,98,171,187,194,202],"relationship":[2,41,195],"between":[3,42,59,196],"internal":[4],"tissue":[5],"point":[6],"motion":[7,61,65,89,133,160,181],"of":[8,46,97,173,180,193,204],"tongue":[10],"and":[11,19,30,67,111,163,200],"oropharyngeal":[12],"muscle":[13],"deformation":[14],"measured":[15],"from":[16,177],"tagged":[17],"MRI":[18],"intelligible":[20],"speech":[21,26,36,164,207],"can":[22],"aid":[23],"in":[24,51,56,87],"advancing":[25],"motor":[27],"control":[28],"theories":[29],"developing":[31],"novel":[32],"treatment":[33],"methods":[34],"for":[35,81,206],"related-disorders.":[37],"However,":[38],"elucidating":[39],"these":[43,197],"two":[44,198],"sources":[45],"information":[47,85],"is":[48,104],"challenging,":[49],"due":[50],"part":[52],"to":[53,126,131,146,189],"disparity":[55],"data":[57],"structure":[58],"spatiotemporal":[60],"fields":[62,90],"(i.e.,":[63],"4D":[64,88,132],"fields)":[66],"one-dimensional":[68],"audio":[69,99,175],"waveforms.":[70],"In":[71],"this":[72],"work,":[73],"we":[74,136],"present":[75],"an":[76,121],"efficient":[77],"encoder-decoder":[78],"translation":[79],"network":[80],"exploring":[82],"predictive":[84],"inherent":[86],"via":[91],"2D":[92,123],"spectrograms":[93,128],"as":[94],"a":[95,138,178],"surrogate":[96],"data.":[100],"Specifically,":[101],"our":[102,144,152,168,184,191],"encoder":[103],"based":[105],"on":[106,151,157],"3D":[107],"convolutional":[108],"spatial":[109],"modeling":[110],"transformer-based":[112],"temporal":[113],"modeling.":[114],"The":[115],"extracted":[116],"features":[117],"are":[118],"processed":[119],"by":[120],"asymmetric":[122],"convolution":[124],"decoder":[125],"generate":[127],"that":[129,167],"correspond":[130],"fields.":[134,182],"Furthermore,":[135],"incorporate":[137],"generative":[139],"adversarial":[140],"training":[141],"approach":[142],"into":[143],"framework":[145,169,185],"further":[147],"improve":[148,190],"synthesis":[149],"quality":[150],"generated":[153],"spectrograms.":[154],"We":[155],"experiment":[156],"63":[158],"paired":[159],"field":[161],"sequences":[162],"waveforms,":[165],"demonstrating":[166],"enables":[170],"generation":[172],"clear":[174],"waveforms":[176],"sequence":[179],"Thus,":[183],"has":[186],"potential":[188],"understanding":[192],"modalities":[199],"inform":[201],"development":[203],"treatments":[205],"disorders.":[208]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}