{"id":"https://openalex.org/W3003133812","doi":"https://doi.org/10.1109/icassp40776.2020.9053841","title":"Lipreading Using Temporal Convolutional Networks","display_name":"Lipreading Using Temporal Convolutional Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3003133812","doi":"https://doi.org/10.1109/icassp40776.2020.9053841","mag":"3003133812"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.08702","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081233863","display_name":"Brais Mart\u00ednez","orcid":"https://orcid.org/0000-0001-7511-8941"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Brais Martinez","raw_affiliation_strings":["Samsung AI Research Center, Cambridge, UK","Samsung AI Research Center,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Samsung AI Research Center, Cambridge, UK","institution_ids":["https://openalex.org/I4210117523"]},{"raw_affiliation_string":"Samsung AI Research Center,Cambridge,UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","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":["Computing Department, Imperial College, London, UK","Imperial College,Computing Department,London,UK"],"affiliations":[{"raw_affiliation_string":"Computing Department, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College,Computing Department,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/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Samsung AI Research Center, Cambridge, UK","Samsung AI Research Center,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Samsung AI Research Center, Cambridge, UK","institution_ids":["https://openalex.org/I4210117523"]},{"raw_affiliation_string":"Samsung AI Research Center,Cambridge,UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"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/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Samsung AI Research Center, Cambridge, UK","Samsung AI Research Center,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Samsung AI Research Center, Cambridge, UK","institution_ids":["https://openalex.org/I4210117523"]},{"raw_affiliation_string":"Samsung AI Research Center,Cambridge,UK","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081233863"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":1.8273,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85303744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6319","last_page":"6323"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9934999942779541,"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":0.9821000099182129,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7919936180114746},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6617029905319214},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6013160347938538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5839313268661499},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5364978909492493},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4961331784725189},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47707974910736084},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4700671136379242},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46480026841163635},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.42405790090560913},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4192376136779785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38632047176361084},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23032870888710022},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08268672227859497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919936180114746},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6617029905319214},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6013160347938538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5839313268661499},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5364978909492493},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4961331784725189},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47707974910736084},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4700671136379242},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46480026841163635},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.42405790090560913},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4192376136779785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38632047176361084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23032870888710022},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08268672227859497},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.08702","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.08702","pdf_url":"https://arxiv.org/pdf/2001.08702","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:3003133812","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.08702.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2001.08702","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.08702","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/nnjh-kk63","is_oa":true,"landing_page_url":"https://doi.org/10.17023/nnjh-kk63","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.08702","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.08702","pdf_url":"https://arxiv.org/pdf/2001.08702","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8700000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3003133812.pdf","grobid_xml":"https://content.openalex.org/works/W3003133812.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2060510034","https://openalex.org/W2076462394","https://openalex.org/W2096391593","https://openalex.org/W2121486117","https://openalex.org/W2194775991","https://openalex.org/W2267805933","https://openalex.org/W2404704342","https://openalex.org/W2511073133","https://openalex.org/W2594690981","https://openalex.org/W2792764867","https://openalex.org/W2890952074","https://openalex.org/W2897492880","https://openalex.org/W2949382160","https://openalex.org/W2952746495","https://openalex.org/W2962912639","https://openalex.org/W2963192365","https://openalex.org/W2963263347","https://openalex.org/W2963524571","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963785710","https://openalex.org/W2972756321","https://openalex.org/W3021355978","https://openalex.org/W3023679742","https://openalex.org/W6726497184","https://openalex.org/W6754392867","https://openalex.org/W6755201655","https://openalex.org/W6763296340","https://openalex.org/W6765296696","https://openalex.org/W6767349417"],"related_works":["https://openalex.org/W2754613063","https://openalex.org/W2978440502","https://openalex.org/W2981501041","https://openalex.org/W2791521493","https://openalex.org/W3036733515","https://openalex.org/W2953111739","https://openalex.org/W2895358653","https://openalex.org/W2809047131","https://openalex.org/W3182470493","https://openalex.org/W2978390373","https://openalex.org/W1423376249","https://openalex.org/W3034207266","https://openalex.org/W2969866314","https://openalex.org/W2951819117","https://openalex.org/W2911640609","https://openalex.org/W2107620532","https://openalex.org/W2240668419","https://openalex.org/W2583684860","https://openalex.org/W3109271037","https://openalex.org/W2983284857"],"abstract_inverted_index":{"Lip-reading":[0],"has":[1],"attracted":[2],"a":[3,27,113],"lot":[4],"of":[5,21,26,44,147],"research":[6],"attention":[7],"lately":[8],"thanks":[9],"to":[10,77,100],"advances":[11],"in":[12,81,128,143,152],"deep":[13],"learning.":[14],"The":[15],"current":[16,90],"state-of-the-art":[17,91,159],"model":[18,46,80,138],"for":[19,124],"recognition":[20,127],"isolated":[22,125],"words":[23],"in-the-wild":[24],"consists":[25],"residual":[28],"network":[29],"and":[30,47,106,130,133,149],"Bidirectional":[31],"Gated":[32],"Recurrent":[33],"Unit":[34],"(BGRU)":[35],"layers.":[36],"In":[37],"this":[38,45,109],"work,":[39],"we":[40,48,68,86,107],"address":[41,108],"the":[42,57,71,79,89,103,120,157],"limitations":[43],"propose":[49],"changes":[50],"which":[51,74,155],"further":[52],"improve":[53],"its":[54],"performance.":[55,160],"Firstly,":[56],"BGRU":[58],"layers":[59],"are":[60],"replaced":[61],"with":[62],"Temporal":[63],"Convolutional":[64],"Networks":[65],"(TCN).":[66],"Secondly,":[67],"greatly":[69],"simplify":[70],"training":[72],"procedure,":[73],"allows":[75],"us":[76],"train":[78],"one":[82],"single":[83],"stage.":[84],"Thirdly,":[85],"show":[87],"that":[88,95],"methodology":[92],"produces":[93],"models":[94],"do":[96],"not":[97],"generalize":[98],"well":[99],"variations":[101],"on":[102,119],"sequence":[104],"length,":[105],"issue":[110],"by":[111],"proposing":[112],"variable-length":[114],"augmentation.":[115],"We":[116],"present":[117],"results":[118,142],"largest":[121],"publicly-available":[122],"datasets":[123,154],"word":[126],"English":[129],"Mandarin,":[131],"LRW":[132],"LRW1000,":[134],"respectively.":[135],"Our":[136],"proposed":[137],"<sup":[139],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[141],"an":[144],"absolute":[145],"improvement":[146],"1.2%":[148],"3.2%,":[150],"respectively,":[151],"these":[153],"is":[156],"new":[158]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}