{"id":"https://openalex.org/W4401990606","doi":"https://doi.org/10.1109/icmew63481.2024.10645425","title":"The Whu Wake Word Lipreading System for the 2024 Chat-Scenario Chinese Lipreading Challenge","display_name":"The Whu Wake Word Lipreading System for the 2024 Chat-Scenario Chinese Lipreading Challenge","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401990606","doi":"https://doi.org/10.1109/icmew63481.2024.10645425"},"language":"en","primary_location":{"id":"doi:10.1109/icmew63481.2024.10645425","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5016797242","display_name":"Haoxu Wang","orcid":"https://orcid.org/0000-0002-5430-0899"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoxu Wang","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113355139","display_name":"Cancan Li","orcid":"https://orcid.org/0009-0002-2537-6293"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cancan Li","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052100570","display_name":"Fei Su","orcid":"https://orcid.org/0000-0002-3529-9845"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Su","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446290","display_name":"Juan Liu","orcid":"https://orcid.org/0000-0001-9344-7415"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Liu","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109630497","display_name":"Hongbin Suo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongbin Suo","raw_affiliation_strings":["AI Center, OPPO,Beijing,China"],"affiliations":[{"raw_affiliation_string":"AI Center, OPPO,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100780143","display_name":"Ming Li","orcid":"https://orcid.org/0009-0009-3842-7337"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["School of Computer Science, Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016797242"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11937326,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6481262445449829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5784533023834229},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4459574222564697},{"id":"https://openalex.org/keywords/wake","display_name":"Wake","score":0.4217499792575836},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27426236867904663},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16129982471466064}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6481262445449829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5784533023834229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4459574222564697},{"id":"https://openalex.org/C48939323","wikidata":"https://www.wikidata.org/wiki/Q294879","display_name":"Wake","level":2,"score":0.4217499792575836},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27426236867904663},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16129982471466064},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew63481.2024.10645425","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2060510034","https://openalex.org/W2407023693","https://openalex.org/W2551572271","https://openalex.org/W2748659049","https://openalex.org/W2752782242","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2897492880","https://openalex.org/W2963528589","https://openalex.org/W2972756321","https://openalex.org/W2973226577","https://openalex.org/W3034552680","https://openalex.org/W3097777922","https://openalex.org/W3152754274","https://openalex.org/W3162293946","https://openalex.org/W3163237592","https://openalex.org/W3167917117","https://openalex.org/W3209059054","https://openalex.org/W4221154745","https://openalex.org/W4224213421","https://openalex.org/W4224933780","https://openalex.org/W4224940398","https://openalex.org/W4283014400","https://openalex.org/W4289665794","https://openalex.org/W4289752563","https://openalex.org/W4297841644","https://openalex.org/W4307286264","https://openalex.org/W4312638101","https://openalex.org/W4319300051","https://openalex.org/W4319862255","https://openalex.org/W4372270419","https://openalex.org/W4372346152","https://openalex.org/W4375869136","https://openalex.org/W4385245566","https://openalex.org/W4392909790","https://openalex.org/W4392910573","https://openalex.org/W6755207826","https://openalex.org/W6780218876","https://openalex.org/W6782374147","https://openalex.org/W6784333009","https://openalex.org/W6788484017","https://openalex.org/W6796538260","https://openalex.org/W6810168380","https://openalex.org/W6839026989"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2757285599","https://openalex.org/W2376025146","https://openalex.org/W161151693","https://openalex.org/W2955635855","https://openalex.org/W3195741387","https://openalex.org/W4381570180","https://openalex.org/W4324257240","https://openalex.org/W2314669870"],"abstract_inverted_index":{"The":[0],"paper":[1],"describes":[2],"the":[3,10,14,59,70,127,132,136,140],"Wake":[4,21,33],"Word":[5,22,34],"Lipreading":[6,19,35],"system":[7,40],"developed":[8],"by":[9],"WHU":[11],"team":[12],"for":[13,32],"ChatCLR":[15,141],"Challenge":[16],"2024.":[17],"Although":[18],"and":[20,47,54,66,68,74,112,130],"Spotting":[23],"have":[24],"seen":[25],"significant":[26],"development,":[27],"exploration":[28],"of":[29,61,72,110,117,124,139],"pretrained":[30,45],"frontends":[31],"(WWL)":[36],"remains":[37],"insufficient.":[38],"Our":[39],"is":[41],"built":[42],"upon":[43],"a":[44,55,106,113,121],"frontend":[46],"Transformer-liked":[48],"backend":[49],"architecture,":[50],"incorporating":[51],"Attentive":[52],"Pooling":[53],"Classifier.":[56],"We":[57],"investigate":[58],"effectiveness":[60],"different":[62],"frontends,":[63],"including":[64],"Auto-AVSR":[65],"AV-Hubert,":[67],"evaluate":[69],"performance":[71],"Conformer":[73],"E-Branchformer":[75],"backends.":[76],"Additionally,":[77],"we":[78,95],"introduce":[79],"Multi-layer":[80],"Feature":[81],"Aggregation":[82],"to":[83,101],"leverage":[84],"features":[85],"from":[86],"multiple":[87],"encoder":[88],"block":[89],"layers,":[90],"demonstrating":[91],"its":[92],"effectiveness.":[93],"Finally,":[94],"apply":[96],"various":[97],"fusion":[98,103],"strategies,":[99],"leading":[100],"score":[102,123],"that":[104],"achieved":[105],"false":[107,114],"reject":[108],"rate":[109,116],"8.21%":[111],"alarm":[115],"8.50%":[118],"along":[119],"with":[120],"WWS":[122],"16.71%":[125],"on":[126],"evaluation":[128],"set,":[129],"obtain":[131],"first":[133],"place":[134],"in":[135],"task":[137],"1":[138],"Challenge.":[142]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}