{"id":"https://openalex.org/W4416250181","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229086","title":"Enhancing Mandarin Lip Reading with a Multimodal Conformer and Structured State-Space Decoder","display_name":"Enhancing Mandarin Lip Reading with a Multimodal Conformer and Structured State-Space Decoder","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416250181","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229086"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5019567696","display_name":"Miao Meng","orcid":"https://orcid.org/0000-0002-8453-0388"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng Miao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019567696"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41851985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919999837875366,"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":0.9919999837875366,"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":0.0020000000949949026,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7609999775886536},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5547999739646912},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5133000016212463},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5022000074386597},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5001000165939331},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.400299996137619},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36419999599456787},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3093999922275543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972000241279602},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7609999775886536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6592000126838684},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5547999739646912},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.400299996137619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3799999952316284},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.30149999260902405},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C2780544925","wikidata":"https://www.wikidata.org/wiki/Q569874","display_name":"Surround sound","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2996970093","https://openalex.org/W2999528291","https://openalex.org/W3080253586","https://openalex.org/W3097777922","https://openalex.org/W3114237205","https://openalex.org/W3197567540","https://openalex.org/W4213457947","https://openalex.org/W4214752847","https://openalex.org/W4221153521","https://openalex.org/W4307286264","https://openalex.org/W4308238102","https://openalex.org/W4372346152","https://openalex.org/W4375869161","https://openalex.org/W4394916639","https://openalex.org/W4404238212"],"related_works":[],"abstract_inverted_index":{"Lip":[0],"reading":[1,58],"is":[2,18,28,134],"a":[3,20,37,46,61,97],"visual":[4,71],"recognition":[5],"technology":[6],"that":[7,40,69],"interprets":[8],"spoken":[9],"content":[10,79],"by":[11],"decoding":[12],"lip":[13,32,57],"movements.":[14],"Since":[15],"speech":[16,78],"perception":[17],"inherently":[19],"multimodal":[21,52],"task,":[22],"incorporating":[23],"audio":[24,67,92],"information":[25,72],"during":[26],"training":[27],"crucial":[29],"to":[30,54,86,103],"assist":[31],"reading.":[33],"This":[34,116],"paper":[35],"proposes":[36],"novel":[38],"architecture":[39],"combines":[41],"the":[42,75,84,107,125],"Conformer":[43,85],"network":[44],"with":[45],"structured":[47,99],"state":[48,100],"space":[49,101],"decoder":[50,102],"under":[51],"input":[53],"enhance":[55],"Mandarin":[56,64],"capabilities.":[59],"As":[60],"tonal":[62],"language,":[63],"benefits":[65],"from":[66,90],"cues":[68],"guide":[70],"learning,":[73],"improving":[74],"accuracy":[76],"of":[77,113,120],"recognition.":[80],"Our":[81],"approach":[82],"leverages":[83],"extract":[87],"shared":[88],"semantics":[89],"both":[91],"and":[93,95,110,122,127],"video,":[94],"employs":[96],"bidirectional":[98],"decode,":[104],"effectively":[105],"capturing":[106],"temporal":[108],"dynamics":[109],"complex":[111],"dependencies":[112],"long":[114],"sequences.":[115],"method":[117],"achieved":[118],"CERs":[119],"54.97%":[121],"12.53%":[123],"in":[124],"CN-CVS":[126],"CMLR":[128],"datasets,":[129],"respectively.":[130],"The":[131],"research":[132],"code":[133],"open":[135],"source":[136],"at:":[137],"https://anonymous.4open.science/r/Lip-reading-model-D7B8.":[138]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}