{"id":"https://openalex.org/W4372346132","doi":"https://doi.org/10.1109/icassp49357.2023.10096920","title":"Speech Reconstruction from Silent Tongue and Lip Articulation by Pseudo Target Generation and Domain Adversarial Training","display_name":"Speech Reconstruction from Silent Tongue and Lip Articulation by Pseudo Target Generation and Domain Adversarial Training","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346132","doi":"https://doi.org/10.1109/icassp49357.2023.10096920"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/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,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. 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,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. 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,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. 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":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9991000294685364,"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":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7940682172775269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7721818685531616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7157729268074036},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6773185133934021},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.4780876338481903},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4725886285305023},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4482173025608063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.395407497882843},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.07579618692398071}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7940682172775269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7721818685531616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157729268074036},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6773185133934021},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.4780876338481903},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4725886285305023},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4482173025608063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.395407497882843},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.07579618692398071},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","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/icassp49357.2023.10096920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1995735739","https://openalex.org/W2008120082","https://openalex.org/W2079402412","https://openalex.org/W2508425411","https://openalex.org/W2746109435","https://openalex.org/W2765811365","https://openalex.org/W2768153200","https://openalex.org/W2769767375","https://openalex.org/W2793399581","https://openalex.org/W2963936489","https://openalex.org/W2964243274","https://openalex.org/W2964352155","https://openalex.org/W3015338123","https://openalex.org/W3083438180","https://openalex.org/W3096927110","https://openalex.org/W3143787022","https://openalex.org/W3174954176","https://openalex.org/W3196749493","https://openalex.org/W4240592325","https://openalex.org/W6639480849"],"related_works":["https://openalex.org/W2081919107","https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W4403759994","https://openalex.org/W4400309480","https://openalex.org/W2549308614"],"abstract_inverted_index":{"This":[0,34],"paper":[1],"studies":[2],"the":[3,38,76,81,98,103,112,127,142,151,154,157,165],"task":[4,35],"of":[5,40,80,102,132,156],"speech":[6,52,82,105,120,158],"reconstruction":[7],"from":[8,84],"ultrasound":[9],"tongue":[10,86],"images":[11],"and":[12,28,43,65,78,87,100],"optical":[13],"lip":[14,88],"videos":[15],"recorded":[16],"in":[17,106,160],"a":[18,50,58],"silent":[19,51,85,107],"speaking":[20,108],"mode,":[21,163],"where":[22],"people":[23],"only":[24],"activate":[25],"their":[26],"intra-oral":[27],"extra-oral":[29],"articulators":[30],"without":[31],"producing":[32],"sound.":[33],"falls":[36],"under":[37],"umbrella":[39],"articulatory-to-acoustic":[41],"conversion,":[42],"may":[44],"also":[45,149],"be":[46],"refered":[47],"to":[48,56,74,111,124,141],"as":[49],"interface.":[53],"We":[54],"propose":[55],"employ":[57],"method":[59,95,135,148],"built":[60],"on":[61,153],"pseudo":[62],"target":[63],"generation":[64],"domain":[66],"adversarial":[67],"training":[68,72],"with":[69],"an":[70,118],"iterative":[71],"strategy":[73],"improve":[75],"intelligibility":[77,99,155],"naturalness":[79,101],"recovered":[83],"articulation.":[89],"Experiments":[90],"show":[91],"that":[92],"our":[93,133,146],"proposed":[94,134,147],"significantly":[96],"improves":[97],"reconstructed":[104,159],"mode":[109],"compared":[110,140],"baseline":[113,152],"TaLNet":[114],"model.":[115],"When":[116],"using":[117],"automatic":[119],"recognition":[121],"(ASR)":[122],"model":[123],"measure":[125],"intelligibility,":[126],"word":[128],"error":[129],"rate":[130],"(WER)":[131],"decreases":[136],"by":[137,167],"over":[138],"15%":[139],"baseline.":[143],"In":[144],"addition,":[145],"outperforms":[150],"vocalized":[161],"articulating":[162],"reducing":[164],"WER":[166],"approximately":[168],"10%.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
