{"id":"https://openalex.org/W4408352804","doi":"https://doi.org/10.1109/icassp49660.2025.10890859","title":"Speech2rtMRI: Speech-Guided Diffusion Model for Real-time MRI Video of the Vocal Tract during Speech","display_name":"Speech2rtMRI: Speech-Guided Diffusion Model for Real-time MRI Video of the Vocal Tract during Speech","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352804","doi":"https://doi.org/10.1109/icassp49660.2025.10890859"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5102012426","display_name":"Hong Nguyen","orcid":"https://orcid.org/0000-0002-2452-4859"},"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":"Hong Nguyen","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046583470","display_name":"Sean Foley","orcid":null},"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":"Sean Foley","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062032121","display_name":"Kevin Huang","orcid":"https://orcid.org/0000-0002-0300-9911"},"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":"Kevin Huang","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101907238","display_name":"Xuan Shi","orcid":"https://orcid.org/0000-0002-1387-5418"},"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":"Xuan Shi","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100567944","display_name":"Tiantian Feng","orcid":null},"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":"Tiantian Feng","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089","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,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Lab,Los Angeles,CA,90089","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79045628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6061000227928162,"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":0.6061000227928162,"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/vocal-tract","display_name":"Vocal tract","score":0.7998517751693726},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6860309839248657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6791888475418091},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.557970404624939},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.481986939907074},{"id":"https://openalex.org/keywords/real-time-mri","display_name":"Real-time MRI","score":0.46540552377700806},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4239104986190796},{"id":"https://openalex.org/keywords/diffusion-mri","display_name":"Diffusion MRI","score":0.4122657775878906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26965096592903137},{"id":"https://openalex.org/keywords/magnetic-resonance-imaging","display_name":"Magnetic resonance imaging","score":0.15936604142189026},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.11983263492584229},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08261570334434509},{"id":"https://openalex.org/keywords/radiology","display_name":"Radiology","score":0.06761443614959717},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.05802318453788757}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.7998517751693726},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6860309839248657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791888475418091},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.557970404624939},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.481986939907074},{"id":"https://openalex.org/C157787499","wikidata":"https://www.wikidata.org/wiki/Q13479657","display_name":"Real-time MRI","level":3,"score":0.46540552377700806},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4239104986190796},{"id":"https://openalex.org/C149550507","wikidata":"https://www.wikidata.org/wiki/Q899360","display_name":"Diffusion MRI","level":3,"score":0.4122657775878906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26965096592903137},{"id":"https://openalex.org/C143409427","wikidata":"https://www.wikidata.org/wiki/Q161238","display_name":"Magnetic resonance imaging","level":2,"score":0.15936604142189026},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.11983263492584229},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08261570334434509},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.06761443614959717},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.05802318453788757},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W223004871","https://openalex.org/W1962568395","https://openalex.org/W2032069772","https://openalex.org/W2054007705","https://openalex.org/W2061283402","https://openalex.org/W2067243719","https://openalex.org/W2133665775","https://openalex.org/W2164483251","https://openalex.org/W2501279594","https://openalex.org/W2916562508","https://openalex.org/W2928787164","https://openalex.org/W2940009604","https://openalex.org/W2944592655","https://openalex.org/W2973058592","https://openalex.org/W2990180062","https://openalex.org/W3003771583","https://openalex.org/W3047225699","https://openalex.org/W3130860000","https://openalex.org/W3173844979","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4375868790","https://openalex.org/W4386100600","https://openalex.org/W6766759079","https://openalex.org/W6780218876","https://openalex.org/W6848353379","https://openalex.org/W6856805842","https://openalex.org/W6857659407","https://openalex.org/W6948038273"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2400533375","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2097143083","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W4385543169","https://openalex.org/W111365173"],"abstract_inverted_index":{"Understanding":[0],"speech":[1,52,58,64,97],"production":[2],"both":[3],"visually":[4,36],"and":[5,25,133],"kinematically":[6],"can":[7],"inform":[8],"second":[9],"language":[10],"learning":[11],"system":[12],"designs,":[13],"as":[14,16],"well":[15],"the":[17,47,74,89,95,116,123,127,137,140,148],"creation":[18],"of":[19,46,118,122,129],"speaking":[20],"characters":[21],"in":[22,40,105],"video":[23,134],"games":[24],"animations.":[26],"In":[27],"this":[28],"work,":[29],"we":[30],"introduce":[31],"a":[32],"data-driven":[33],"method":[34],"to":[35,72,77],"represent":[37],"articulator":[38],"motion":[39,132],"Magnetic":[41],"Resonance":[42],"Imaging":[43],"(MRI)":[44],"videos":[45],"human":[48],"vocal":[49],"tract":[50],"during":[51],"based":[53],"on":[54],"arbitrary":[55],"audio":[56],"or":[57],"input.":[59],"We":[60,99],"leverage":[61],"large":[62],"pre-trained":[63,96],"models,":[65],"which":[66],"are":[67],"embedded":[68],"with":[69],"prior":[70],"knowledge,":[71],"generalize":[73],"visual":[75,90],"domain":[76],"unseen":[78],"data":[79],"using":[80],"an":[81],"speech-to-video":[82],"diffusion":[83],"model.":[84],"Our":[85],"findings":[86],"demonstrate":[87],"that":[88,102],"generation":[91],"significantly":[92],"benefits":[93],"from":[94],"representations.":[98],"also":[100],"observed":[101],"evaluating":[103],"phonemes":[104],"isolation":[106],"is":[107,145],"challenging":[108],"but":[109],"becomes":[110],"more":[111],"straightforward":[112],"when":[113,136],"assessed":[114],"within":[115],"context":[117],"spoken":[119],"words.":[120],"Limitations":[121],"current":[124],"results":[125],"include":[126],"presence":[128],"unsmooth":[130],"tongue":[131,138],"distortion":[135],"contacts":[139],"palate.":[141],"The":[142],"source":[143],"code":[144],"available":[146],"for":[147],"public":[149],"at:":[150],"https://github.com/Hong7Cong/SPAN-rtmri.git":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}