{"id":"https://openalex.org/W4409353060","doi":"https://doi.org/10.1186/s13636-025-00403-8","title":"Silent speech recognition using visual cascading fusion of tongue-lip movements based on pre-trained and fine-tuned model","display_name":"Silent speech recognition using visual cascading fusion of tongue-lip movements based on pre-trained and fine-tuned model","publication_year":2025,"publication_date":"2025-04-12","ids":{"openalex":"https://openalex.org/W4409353060","doi":"https://doi.org/10.1186/s13636-025-00403-8"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00403-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00403-8","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00403-8","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00403-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075985115","display_name":"Chongchong Yu","orcid":"https://orcid.org/0000-0003-4234-1260"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongchong Yu","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing, 100048, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing, 100048, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101857376","display_name":"Xuening Wang","orcid":"https://orcid.org/0009-0009-5266-6115"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuening Wang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing, 100048, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing, 100048, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074188184","display_name":"Zhaopeng Qian","orcid":"https://orcid.org/0000-0003-0743-0700"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaopeng Qian","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing, 100048, China"],"raw_orcid":"https://orcid.org/0000-0003-0743-0700","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing, 100048, China","institution_ids":["https://openalex.org/I179026463"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5074188184"],"corresponding_institution_ids":["https://openalex.org/I179026463"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":2.5269,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.88695243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11448","display_name":"Face recognition and analysis","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-science","display_name":"Computer science","score":0.8768733739852905},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6505897641181946},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6065220832824707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46230024099349976},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.44847556948661804},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3553076982498169},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07704618573188782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8768733739852905},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6505897641181946},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6065220832824707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46230024099349976},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.44847556948661804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3553076982498169},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07704618573188782},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00403-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00403-8","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00403-8","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bd1206e093524238b2ae19ad823d3b0e","is_oa":true,"landing_page_url":"https://doaj.org/article/bd1206e093524238b2ae19ad823d3b0e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-14 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00403-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00403-8","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00403-8","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316084","display_name":"China Computer Federation","ror":"https://ror.org/015xj5w40"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409353060.pdf","grobid_xml":"https://content.openalex.org/works/W4409353060.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1488659701","https://openalex.org/W1964178275","https://openalex.org/W1982854652","https://openalex.org/W1995735739","https://openalex.org/W2007050140","https://openalex.org/W2008120082","https://openalex.org/W2008130220","https://openalex.org/W2059169992","https://openalex.org/W2059761048","https://openalex.org/W2060756806","https://openalex.org/W2067517374","https://openalex.org/W2076676508","https://openalex.org/W2077018202","https://openalex.org/W2087681821","https://openalex.org/W2113814270","https://openalex.org/W2128989405","https://openalex.org/W2138672527","https://openalex.org/W2140360678","https://openalex.org/W2160594205","https://openalex.org/W2183414650","https://openalex.org/W2250338440","https://openalex.org/W2296614680","https://openalex.org/W2394855416","https://openalex.org/W2397670449","https://openalex.org/W2419247625","https://openalex.org/W2584291667","https://openalex.org/W2623847621","https://openalex.org/W2769402512","https://openalex.org/W2889853672","https://openalex.org/W2963272864","https://openalex.org/W2963787388","https://openalex.org/W2996970093","https://openalex.org/W3096268352","https://openalex.org/W3096927110","https://openalex.org/W3107695054","https://openalex.org/W3128311146","https://openalex.org/W3143787022","https://openalex.org/W3195467321","https://openalex.org/W3198447999","https://openalex.org/W4210261408","https://openalex.org/W4302993121","https://openalex.org/W4322732853","https://openalex.org/W4328093594","https://openalex.org/W4377235517"],"related_works":["https://openalex.org/W3136794468","https://openalex.org/W2367950022","https://openalex.org/W2365707941","https://openalex.org/W2366141844","https://openalex.org/W2383946220","https://openalex.org/W2358428239","https://openalex.org/W3011636953","https://openalex.org/W2351206852","https://openalex.org/W3212410916","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Tongue-lip":[0],"movement":[1],"visual":[2,30,52],"information":[3,53],"exhibits":[4],"superior":[5],"performance":[6],"in":[7,23,187],"the":[8,24,39,50,64,72,87,106,117,136,141,157,179],"task":[9],"of":[10,26,63,90,96,123,144],"silent":[11],"speech":[12],"recognition":[13],"(SSR)":[14],"and":[15,34,66,74,108,156],"is":[16,102],"increasingly":[17],"focused":[18],"on":[19,78,105,148],"by":[20,54,69],"researchers.":[21],"Traditionally,":[22],"field":[25],"SSR":[27],"using":[28,80],"tongue-lip":[29,51],"information,":[31],"data":[32,111,151],"augmentation":[33],"feature":[35],"fusion":[36,57],"have":[37],"received":[38],"most":[40],"attention.":[41],"Different":[42],"from":[43],"traditional":[44],"approaches,":[45],"we":[46],"proposed":[47,100,124,145,172],"to":[48,59,85,93,128,135,164],"fuse":[49],"a":[55,94,131],"cascading":[56],"algorithm":[58],"achieve":[60,127,154,163],"\u201cvisual":[61],"co-occurrence\u201d":[62],"tongue":[65],"lip":[67],"frame":[68],"frame.":[70],"Besides,":[71],"pre-trained":[73],"fine-tuned":[75],"frameworks":[76],"based":[77,104,147],"Visual-HuBERT":[79],"masked":[81],"technology":[82],"are":[83],"used":[84],"address":[86],"overfitting":[88],"problems":[89],"model":[91,101,125,146,173],"due":[92],"lack":[95],"training":[97],"data.":[98],"The":[99,166],"evaluated":[103],"TaL":[107],"self-made":[109,149],"Chinese":[110,150],"corpus.":[112],"Experimental":[113],"results":[114,168],"show":[115],"that":[116,170],"average":[118,142,158],"word":[119],"error":[120,160],"rate":[121,161],"(WER)":[122],"can":[126,153,162],"23.34%,":[129],"representing":[130],"1.75%":[132],"reduction":[133],"compared":[134],"baseline":[137,180],"model.":[138],"In":[139],"addition,":[140],"WER":[143],"corpus":[152],"50.23%,":[155],"tone":[159],"47.04%.":[165],"above":[167],"illustrate":[169],"our":[171],"not":[174],"only":[175],"performs":[176],"better":[177],"than":[178],"model,":[181],"but":[182],"also":[183],"handles":[184],"tonal":[185],"language":[186],"SSR,":[188],"such":[189],"as":[190],"Mandarin.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}