{"id":"https://openalex.org/W4308238102","doi":"https://doi.org/10.1109/icip46576.2022.9897760","title":"Chinese Mandarin Lipreading using Cascaded Transformers with Multiple Intermediate Representations","display_name":"Chinese Mandarin Lipreading using Cascaded Transformers with Multiple Intermediate Representations","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4308238102","doi":"https://doi.org/10.1109/icip46576.2022.9897760"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897760","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5057414684","display_name":"Xinghua Ma","orcid":"https://orcid.org/0000-0001-6020-6770"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinghua Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering","School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101717685","display_name":"Shilin Wang","orcid":"https://orcid.org/0000-0002-8214-6809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering","School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057414684"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.3677,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51943128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2561","last_page":"2565"},"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/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9941999912261963,"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/pinyin","display_name":"Pinyin","score":0.8989299535751343},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8082088828086853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7766026258468628},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6894144415855408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6229905486106873},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5447893142700195},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4492720663547516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40779924392700195},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.3255408704280853},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24863749742507935},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09162449836730957}],"concepts":[{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.8989299535751343},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8082088828086853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766026258468628},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6894144415855408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6229905486106873},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5447893142700195},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4492720663547516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40779924392700195},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.3255408704280853},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24863749742507935},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09162449836730957},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897760","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2087681821","https://openalex.org/W2127141656","https://openalex.org/W2547875792","https://openalex.org/W2551572271","https://openalex.org/W2905426022","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2981501041","https://openalex.org/W2996970093","https://openalex.org/W2999528291","https://openalex.org/W3016011581","https://openalex.org/W3035042697","https://openalex.org/W3080253586","https://openalex.org/W3106694838","https://openalex.org/W3109715615","https://openalex.org/W3127334095","https://openalex.org/W4298112588","https://openalex.org/W4385245566","https://openalex.org/W6631751486","https://openalex.org/W6729448088","https://openalex.org/W6732872814","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2152091600","https://openalex.org/W4214677368","https://openalex.org/W2787859844","https://openalex.org/W2599178495","https://openalex.org/W4385493412","https://openalex.org/W3159297355","https://openalex.org/W1575804004","https://openalex.org/W2386864954","https://openalex.org/W380382270","https://openalex.org/W1788792945"],"abstract_inverted_index":{"Automatic":[0],"lipreading":[1,153],"has":[2],"attracted":[3],"much":[4],"research":[5],"interest":[6],"over":[7,171],"the":[8,26,66,71,106,116,127,141,149,159,162],"past":[9],"few":[10],"decades.":[11],"Different":[12],"from":[13],"English,":[14],"Chinese":[15,29,52,124,152],"is":[16,34],"a":[17,21,48,56,95,100],"tone-based":[18],"language":[19],"with":[20,99],"large":[22],"alphabet":[23],"and":[24,31,46,62,114,126,135,138,168],"thus":[25],"correlation":[27],"between":[28,111],"characters":[30],"lip":[32],"motions":[33],"more":[35],"complex.":[36],"Most":[37],"existing":[38],"methods":[39],"employed":[40],"an":[41],"intermediate":[42,67,121],"representation":[43,68],"(usually":[44],"Pinyin),":[45],"adopted":[47,130],"cascaded":[49,57,96],"architecture":[50],"for":[51,83,144],"lipreading.":[53],"However,":[54],"such":[55],"structure":[58],"may":[59],"accumulate":[60],"errors,":[61],"employing":[63],"Pinyin":[64,125],"as":[65],"would":[69],"cause":[70],"loss":[72],"of":[73,108,118,161],"visual":[74,134],"information.":[75],"Moreover,":[76],"these":[77],"approaches":[78],"do":[79],"not":[80],"perform":[81],"well":[82],"unseen":[84,145],"speakers":[85],"due":[86],"to":[87,131,139],"inter-speaker":[88],"variability.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93],"propose":[94],"Transformer-based":[97],"model":[98],"new":[101],"cross-level":[102],"attention":[103],"mechanism,":[104],"enriching":[105],"ways":[107],"information":[109],"transmission":[110],"cascading":[112],"structures":[113],"reducing":[115],"accumulation":[117],"errors.":[119],"Multiple":[120],"representations":[122],"including":[123],"visemes":[128],"are":[129],"acquire":[132],"multi-perspective":[133],"linguistic":[136],"features":[137],"improve":[140],"generalization":[142],"ability":[143],"speakers.":[146],"Evaluations":[147],"on":[148],"public":[150],"sentence-level":[151],"database,":[154],"i.e.":[155],"CMLR,":[156],"have":[157],"demonstrated":[158],"advantages":[160],"proposed":[163],"method":[164],"in":[165],"both":[166],"speaker-independent":[167],"multi-speaker":[169],"scenarios":[170],"state-of-the-art":[172],"approaches.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}