{"id":"https://openalex.org/W4392903528","doi":"https://doi.org/10.1109/icassp48485.2024.10447224","title":"An Audio-Textual Diffusion Model for Converting Speech Signals into Ultrasound Tongue Imaging Data","display_name":"An Audio-Textual Diffusion Model for Converting Speech Signals into Ultrasound Tongue Imaging Data","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903528","doi":"https://doi.org/10.1109/icassp48485.2024.10447224"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100933548","display_name":"Yu-Dong Yang","orcid":"https://orcid.org/0009-0005-3048-176X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Yang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036142381","display_name":"Rongfeng Su","orcid":"https://orcid.org/0000-0002-7228-5768"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongfeng Su","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628113","display_name":"Xiaokang Liu","orcid":"https://orcid.org/0000-0001-8732-0338"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Liu","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","University of Chinese Academy of Sciences, Beijing, China","Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062053942","display_name":"Nan Yan","orcid":"https://orcid.org/0000-0002-1613-9301"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Yan","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China","Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China","institution_ids":[]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363630","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0001-6843-3003"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China","Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Shenzhen Institute of Advanced Technology, Shenzhen, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2170","last_page":"2174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9830999970436096,"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":0.9830999970436096,"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/T11309","display_name":"Music and Audio Processing","score":0.9822999835014343,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7361869215965271},{"id":"https://openalex.org/keywords/articulator","display_name":"Articulator","score":0.6913559436798096},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.6564909219741821},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6087291836738586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4060877561569214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361869215965271},{"id":"https://openalex.org/C2778415344","wikidata":"https://www.wikidata.org/wiki/Q443216","display_name":"Articulator","level":2,"score":0.6913559436798096},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.6564909219741821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6087291836738586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4060877561569214},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C29694066","wikidata":"https://www.wikidata.org/wiki/Q118301","display_name":"Orthodontics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G325171179","display_name":null,"funder_award_id":"NSFC 62271477","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3278014984","display_name":null,"funder_award_id":"U23B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4766593243","display_name":null,"funder_award_id":"62271477","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2398505291","https://openalex.org/W2565110584","https://openalex.org/W2768153200","https://openalex.org/W2896457183","https://openalex.org/W2962785568","https://openalex.org/W2979074722","https://openalex.org/W3128311146","https://openalex.org/W3143787022","https://openalex.org/W3183538106","https://openalex.org/W4206087508","https://openalex.org/W4310695675","https://openalex.org/W4312423208","https://openalex.org/W4312933868","https://openalex.org/W4372346132","https://openalex.org/W4375868790","https://openalex.org/W4375868947","https://openalex.org/W4385822346","https://openalex.org/W4385823094","https://openalex.org/W4387211386","https://openalex.org/W4387806972","https://openalex.org/W6637373629","https://openalex.org/W6755207826","https://openalex.org/W6765779288","https://openalex.org/W6780218876","https://openalex.org/W6786375611","https://openalex.org/W6810793953","https://openalex.org/W6838452192","https://openalex.org/W6838639034"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2034310431","https://openalex.org/W2724655958","https://openalex.org/W2033140727","https://openalex.org/W4250529536","https://openalex.org/W1963633157","https://openalex.org/W4290036070","https://openalex.org/W2412408187"],"abstract_inverted_index":{"Acoustic-to-articulatory":[0],"inversion":[1],"(AAI)":[2],"is":[3,23,46,130],"to":[4,30,75,91],"convert":[5],"audio":[6],"into":[7],"articulator":[8],"movements,":[9],"such":[10],"as":[11],"ultrasound":[12],"tongue":[13,36,77,95,127],"imaging":[14],"(UTI)":[15],"data.":[16],"An":[17],"issue":[18],"of":[19,35,42,72,94],"existing":[20],"AAI":[21],"methods":[22],"only":[24],"using":[25,83,100,108],"the":[26,32,40,60,68,76,87,92,116,133,147],"personalized":[27],"acoustic":[28,70],"information":[29],"derive":[31],"general":[33],"patterns":[34],"motions,":[37],"and":[38,136,141],"thus":[39],"quality":[41],"generated":[43,106],"UTI":[44,61,102,123],"data":[45,62,103,124],"limited.":[47],"To":[48],"address":[49],"this":[50,52,66],"issue,":[51],"paper":[53],"proposes":[54],"an":[55],"audio-textual":[56],"diffusion":[57,110,118],"model":[58,119],"for":[59,132],"generation":[63],"task.":[64],"In":[65],"model,":[67],"inherent":[69],"characteristics":[71],"individuals":[73],"related":[74,90],"motion":[78],"details":[79],"are":[80,97,104],"encoded":[81,98],"by":[82,99,107],"wav2vec":[84],"2.0,":[85],"while":[86],"ASR":[88],"transcriptions":[89],"universality":[93],"motions":[96],"BERT.":[101],"then":[105],"a":[109],"module.":[111],"Experimental":[112],"results":[113],"showed":[114],"that":[115,129],"proposed":[117],"could":[120],"generate":[121],"high-quality":[122],"with":[125],"clear":[126],"contour":[128],"crucial":[131],"linguistic":[134],"analysis":[135],"clinical":[137],"assessment.":[138],"The":[139],"codes":[140],"examples":[142],"can":[143],"be":[144],"found":[145],"on":[146],"website":[148],"<sup":[149],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[151],".":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}