{"id":"https://openalex.org/W4403792192","doi":"https://doi.org/10.1145/3664647.3680770","title":"Speech Reconstruction from Silent Lip and Tongue Articulation by Diffusion Models and Text-Guided Pseudo Target Generation","display_name":"Speech Reconstruction from Silent Lip and Tongue Articulation by Diffusion Models and Text-Guided Pseudo Target Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792192","doi":"https://doi.org/10.1145/3664647.3680770"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680770","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5066498315","display_name":"Rui-Chen Zheng","orcid":"https://orcid.org/0009-0000-8074-9553"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui-Chen Zheng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-8074-9553","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-022X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6559","last_page":"6568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9846000075340271,"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/articulation","display_name":"Articulation (sociology)","score":0.8540776968002319},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.6721738576889038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6454403400421143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6251840591430664},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3639976382255554},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2000262439250946},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06310760974884033}],"concepts":[{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.8540776968002319},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.6721738576889038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6454403400421143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251840591430664},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3639976382255554},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2000262439250946},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06310760974884033},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680770","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2008120082","https://openalex.org/W2068056889","https://openalex.org/W2079402412","https://openalex.org/W2508425411","https://openalex.org/W2604379605","https://openalex.org/W2746109435","https://openalex.org/W2747874407","https://openalex.org/W2768153200","https://openalex.org/W2769767375","https://openalex.org/W2889413431","https://openalex.org/W2889853672","https://openalex.org/W2941048526","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W3015338123","https://openalex.org/W3015734344","https://openalex.org/W3081492798","https://openalex.org/W3095801312","https://openalex.org/W3096927110","https://openalex.org/W3101631197","https://openalex.org/W3143787022","https://openalex.org/W3158762648","https://openalex.org/W3174954176","https://openalex.org/W3196749493","https://openalex.org/W3198213150","https://openalex.org/W3204420730","https://openalex.org/W3211862173","https://openalex.org/W4221144097","https://openalex.org/W4283809657","https://openalex.org/W4285019302","https://openalex.org/W4294435344","https://openalex.org/W4304099317","https://openalex.org/W4372346132","https://openalex.org/W4375868850","https://openalex.org/W4375869120","https://openalex.org/W4385822362","https://openalex.org/W4387969537"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3136794468","https://openalex.org/W2367950022","https://openalex.org/W2416809655","https://openalex.org/W2365707941","https://openalex.org/W2366141844","https://openalex.org/W2383946220","https://openalex.org/W2358428239"],"abstract_inverted_index":{"This":[0,35],"paper":[1],"studies":[2],"the":[3,39,58,77,87,113,117,123,131,144,149,153,163,168,187,202],"task":[4,36,120],"of":[5,41,89,148,167],"speech":[6,54,97,151,170,180],"reconstruction":[7,98],"from":[8,99],"ultrasound":[9],"tongue":[10],"images":[11],"and":[12,28,45,63,121,146,186],"optical":[13],"lip":[14],"videos":[15],"recorded":[16],"in":[17,152],"a":[18,52,69,107,126],"silent":[19,53,62,100,154],"speaking":[20,155],"mode,":[21],"where":[22],"people":[23],"only":[24],"activate":[25],"their":[26],"intra-oral":[27],"extra-oral":[29],"articulators":[30],"without":[31],"producing":[32],"real":[33],"speech.":[34],"falls":[37],"under":[38],"umbrella":[40],"articulatory-to-acoustic":[42],"(A2A)":[43],"conversion":[44,119],"may":[46],"also":[47],"be":[48],"referred":[49],"to":[50,80,105,158],"as":[51,112],"interface.":[55],"To":[56],"overcome":[57],"domain":[59],"discrepancy":[60],"between":[61],"standard":[64],"vocalized":[65],"articulation,":[66],"we":[67,103],"introduce":[68],"novel":[70],"pseudo":[71,90,133,204,210],"target":[72,205],"generation":[73,88,206],"strategy.":[74],"It":[75],"integrates":[76],"text":[78],"modality":[79],"align":[81],"with":[82,130,216],"articulatory":[83,217],"movements,":[84],"thereby":[85],"guiding":[86],"acoustic":[91,134,211],"features":[92,212],"for":[93,116,183,192],"supervised":[94],"training":[95,128],"on":[96],"articulation.":[101],"Furthermore,":[102],"propose":[104],"employ":[106],"denoising":[108],"diffusion":[109],"probabilistic":[110],"model":[111,124],"fundamental":[114],"architecture":[115],"A2A":[118],"train":[122],"using":[125,177],"combined":[127],"approach":[129],"generated":[132],"features.":[135],"Experiments":[136],"show":[137],"that":[138,201,213],"our":[139,226],"proposed":[140,203],"method":[141],"significantly":[142],"improves":[143,194],"intelligibility":[145,184],"naturalness":[147,193],"reconstructed":[150,169],"mode":[156],"compared":[157],"all":[159],"baseline":[160],"methods.":[161],"Specifically,":[162],"word":[164],"error":[165],"rate":[166],"decreases":[171],"by":[172,195],"approximately":[173],"5%":[174],"when":[175],"measured":[176],"an":[178],"automatic":[179],"recognition":[181],"engine":[182],"assessment,":[185],"subjective":[188],"mean":[189],"opinion":[190],"score":[191],"0.14.":[196],"Moreover,":[197],"analytical":[198],"experiments":[199],"reveal":[200],"strategy":[207],"can":[208],"generate":[209],"synchronize":[214],"better":[215],"movements":[218],"than":[219],"previous":[220],"strategies.":[221],"Samples":[222],"are":[223],"available":[224],"at":[225],"project":[227],"page.":[228]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}