{"id":"https://openalex.org/W4415707788","doi":"https://doi.org/10.1109/icme59968.2025.11209943","title":"Chinese-LiPS: A Chinese Audio-Visual Speech Recognition Dataset with Lip-Reading and Presentation Slides","display_name":"Chinese-LiPS: A Chinese Audio-Visual Speech Recognition Dataset with Lip-Reading and Presentation Slides","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707788","doi":"https://doi.org/10.1109/icme59968.2025.11209943"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5033737287","display_name":"Jinghua Zhao","orcid":"https://orcid.org/0000-0002-9741-6998"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghua Zhao","raw_affiliation_strings":["Nankai University,College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061270485","display_name":"Yuhang Jia","orcid":"https://orcid.org/0000-0002-0412-3812"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Jia","raw_affiliation_strings":["Nankai University,College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114585213","display_name":"Shiyao Wang","orcid":"https://orcid.org/0000-0001-5291-4945"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyao Wang","raw_affiliation_strings":["Nankai University,College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114859604","display_name":"Jiaming Zhou","orcid":"https://orcid.org/0009-0001-4760-9708"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":["Nankai University,College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101473591","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-0023-3715"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Nankai University,College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010808374","display_name":"Yong Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["Nankai University,College of Computer Science,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38728929,"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":0.9948999881744385,"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":0.9948999881744385,"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":0.0013000000035390258,"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":0.0006000000284984708,"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/presentation","display_name":"Presentation (obstetrics)","score":0.738099992275238},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.597000002861023},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5799000263214111},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47360000014305115},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.33340001106262207}],"concepts":[{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.738099992275238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287999987602234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6894000172615051},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.597000002861023},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5799000263214111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4948999881744385},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27959999442100525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2890952074","https://openalex.org/W2897492880","https://openalex.org/W2963785710","https://openalex.org/W2999528291","https://openalex.org/W4296414218","https://openalex.org/W4372346152","https://openalex.org/W4375869161","https://openalex.org/W4385822890","https://openalex.org/W4385823274","https://openalex.org/W4392903409","https://openalex.org/W4392909790","https://openalex.org/W4392909863","https://openalex.org/W4392910434","https://openalex.org/W4402112360","https://openalex.org/W4402112425","https://openalex.org/W4402671247"],"related_works":[],"abstract_inverted_index":{"Incorporating":[0],"visual":[1,42,71,105],"modalities":[2,106],"to":[3,12],"assist":[4],"Automatic":[5],"Speech":[6,18],"Recognition":[7,19],"(ASR)":[8],"tasks":[9],"has":[10],"led":[11],"significant":[13],"improvements.":[14],"However,":[15],"existing":[16],"Audio-Visual":[17],"(AVSR)":[20],"datasets":[21],"and":[22,65,77,100,114,124],"methods":[23],"typically":[24],"rely":[25],"solely":[26],"on":[27,86],"lip-reading":[28,75,99,113],"information":[29,76,103,117],"or":[30],"speaking":[31,46],"contextual":[32],"video,":[33,64],"neglecting":[34],"the":[35,45,70,78,83],"potential":[36],"of":[37,62,132],"combining":[38],"these":[39],"different":[40],"valuable":[41],"cues":[43],"within":[44],"context.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51,88],"release":[52],"a":[53,90,128],"multimodal":[54],"Chinese":[55],"AVSR":[56,108],"dataset,":[57],"Chinese-LiPS,":[58,87],"comprising":[59],"100":[60],"hours":[61],"speech,":[63],"corresponding":[66],"manual":[67],"transcription,":[68],"with":[69,127],"modality":[72],"encompassing":[73],"both":[74,98],"presentation":[79,101,115],"slides":[80],"used":[81],"by":[82,121],"speaker.":[84],"Based":[85],"develop":[89],"simple":[91],"yet":[92],"effective":[93],"pipeline,":[94],"LiPS-AVSR,":[95],"which":[96],"leverages":[97],"slide":[102,116],"as":[104],"for":[107],"tasks.":[109],"Experiments":[110],"show":[111],"that":[112],"improve":[118],"ASR":[119],"performance":[120,130],"approximately":[122],"8%":[123],"25%,":[125],"respectively,":[126],"combined":[129],"improvement":[131],"about":[133],"35%.":[134],"The":[135],"dataset":[136],"is":[137],"available":[138],"at":[139],"https://kiri0824.github.io/Chinese-LiPS/":[140]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}