{"id":"https://openalex.org/W4225299282","doi":"https://doi.org/10.1109/icassp43922.2022.9746706","title":"Training Strategies for Improved Lip-Reading","display_name":"Training Strategies for Improved Lip-Reading","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225299282","doi":"https://doi.org/10.1109/icassp43922.2022.9746706"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746706","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.01383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Imperial College London,Department of Computing,UK","Department of Computing, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101471095","display_name":"Yujiang Wang","orcid":"https://orcid.org/0000-0002-6220-029X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yujiang Wang","raw_affiliation_strings":["Imperial College London,Department of Computing,UK","Department of Computing, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Imperial College London,Department of Computing,UK","Department of Computing, Imperial College London, UK","Meta AI, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Meta AI, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101405147","display_name":"Jie Shen","orcid":"https://orcid.org/0000-0002-6722-2754"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jie Shen","raw_affiliation_strings":["Imperial College London,Department of Computing,UK","Department of Computing, Imperial College London, UK","Meta AI, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Meta AI, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Imperial College London,Department of Computing,UK","Department of Computing, Imperial College London, UK","Meta AI, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Meta AI, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":38.1578,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.99919957,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8472","last_page":"8476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919000267982483,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9886999726295471,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6716527342796326},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.650970995426178},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5304198861122131},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35781270265579224},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10983836650848389}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6716527342796326},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.650970995426178},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5304198861122131},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35781270265579224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10983836650848389},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746706","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.01383","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.01383","pdf_url":"https://arxiv.org/pdf/2209.01383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.01383","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.01383","pdf_url":"https://arxiv.org/pdf/2209.01383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8899999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2752782242","https://openalex.org/W2803023299","https://openalex.org/W2891205112","https://openalex.org/W2898926657","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2947883281","https://openalex.org/W2949662773","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W3016011581","https://openalex.org/W3034552680","https://openalex.org/W3103322708","https://openalex.org/W3104792420","https://openalex.org/W3119418740","https://openalex.org/W3128564814","https://openalex.org/W3162707322","https://openalex.org/W3197567540","https://openalex.org/W4220782092","https://openalex.org/W6734491695","https://openalex.org/W6751751081","https://openalex.org/W6754420807","https://openalex.org/W6757817989","https://openalex.org/W6763296340","https://openalex.org/W6785851975"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Several":[0],"training":[1,57,158],"strategies":[2,27,159],"and":[3,28,55,61,80,98],"temporal":[4,53,89],"models":[5,54],"have":[6],"been":[7,38],"recently":[8],"proposed":[9],"for":[10,91],"isolated":[11,94],"word":[12,63,99],"lip-reading":[13,92],"in":[14,117],"a":[15,106,118],"series":[16],"of":[17,23,32,34,48,93,111,121,128,155,170],"independent":[18],"works.":[19],"However,":[20],"the":[21,25,30,46,73,87,113,131,136,156,162,167],"potential":[22],"combining":[24],"best":[26,88],"investigating":[29],"impact":[31],"each":[33],"them":[35],"has":[36],"not":[37],"explored.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"systematically":[44],"investigate":[45],"performance":[47,134,140,163],"state-of-the-art":[49,133],"data":[50],"augmentation":[51,76],"approaches,":[52],"other":[56],"strategies,":[58],"like":[59],"self-distillation":[60,97],"using":[62],"boundaries":[64,100],"indicators.":[65],"Our":[66],"results":[67,116],"show":[68],"that":[69,161],"time":[70],"masking":[71],"is":[72,101,124],"most":[74],"important":[75],"followed":[77],"by":[78,147,165],"mixup":[79],"Densely-Connected":[81],"Temporal":[82],"Convolutional":[83],"Networks":[84],"(DC-TCN)":[85],"are":[86],"model":[90],"words.":[95,172],"Using":[96],"also":[102],"beneficial":[103],"but":[104],"to":[105,145],"lesser":[107],"extent.":[108],"A":[109],"combination":[110],"all":[112],"above":[114],"methods":[115],"classification":[119,168],"accuracy":[120,169],"93.4%,":[122],"which":[123],"an":[125],"absolute":[126],"improvement":[127],"4.6%":[129],"over":[130],"current":[132],"on":[135,149],"LRW":[137],"dataset.":[138],"The":[139],"can":[141],"be":[142],"further":[143],"improved":[144],"94.1%":[146],"pre-training":[148],"additional":[150],"datasets.":[151],"An":[152],"error":[153],"analysis":[154],"various":[157],"reveals":[160],"improves":[164],"increasing":[166],"hard-to-recognise":[171]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}