{"id":"https://openalex.org/W2596627958","doi":"https://doi.org/10.21437/interspeech.2017-85","title":"Combining Residual Networks with LSTMs for Lipreading","display_name":"Combining Residual Networks with LSTMs for Lipreading","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2596627958","doi":"https://doi.org/10.21437/interspeech.2017-85","mag":"2596627958"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-85","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-85","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/1703.04105","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["University of Nottingham, Nottingham, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Nottingham, Nottingham, United Kingdom","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024224610","display_name":"Georgios Tzimiropoulos","orcid":"https://orcid.org/0000-0002-1803-5338"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgios Tzimiropoulos","raw_affiliation_strings":["University of Nottingham, Nottingham, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Nottingham, Nottingham, United Kingdom","institution_ids":["https://openalex.org/I142263535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061939508"],"corresponding_institution_ids":["https://openalex.org/I142263535"],"apc_list":null,"apc_paid":null,"fwci":6.1561,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.9714636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3652","last_page":"3656"},"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":0.9979000091552734,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.8241729736328125},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.811939001083374},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8090328574180603},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6545171737670898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6308905482292175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6167593002319336},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5347081422805786},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.504346489906311},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4317713677883148},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36967676877975464},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07565608620643616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241729736328125},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.811939001083374},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8090328574180603},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6545171737670898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6308905482292175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6167593002319336},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5347081422805786},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.504346489906311},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4317713677883148},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36967676877975464},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07565608620643616},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2017-85","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-85","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1703.04105","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.04105","pdf_url":"https://arxiv.org/pdf/1703.04105","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:2596627958","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1703.04105","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":"pmh:oai:eprints.nottingham.ac.uk:44756","is_oa":false,"landing_page_url":"http://www.isca-speech.org/archive/Interspeech_2017/abstracts/0085.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402013","display_name":"Nottingham ePrints (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:nottingham-repository.worktribe.com:861527","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/861527","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},{"id":"doi:10.48550/arxiv.1703.04105","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.04105","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1703.04105","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.04105","pdf_url":"https://arxiv.org/pdf/1703.04105","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":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5015807494","display_name":"TalkingHeads: Audiovisual Speech Recognition in-the-wild","funder_award_id":"706668","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1514535095","https://openalex.org/W2015143272","https://openalex.org/W2022799064","https://openalex.org/W2071096833","https://openalex.org/W2076462394","https://openalex.org/W2096391593","https://openalex.org/W2098923380","https://openalex.org/W2106137268","https://openalex.org/W2127141656","https://openalex.org/W2142075667","https://openalex.org/W2160815625","https://openalex.org/W2194775991","https://openalex.org/W2296681920","https://openalex.org/W2302255633","https://openalex.org/W2365880764","https://openalex.org/W2398406965","https://openalex.org/W2404704342","https://openalex.org/W2557290168","https://openalex.org/W2578229578","https://openalex.org/W2579335913","https://openalex.org/W2594690981","https://openalex.org/W2949117887","https://openalex.org/W2951015274","https://openalex.org/W2951327905","https://openalex.org/W2952746495","https://openalex.org/W2953291251","https://openalex.org/W3105538092"],"related_works":["https://openalex.org/W2594690981","https://openalex.org/W2952746495","https://openalex.org/W2578229578","https://openalex.org/W2015143272","https://openalex.org/W2194775991","https://openalex.org/W2890952074","https://openalex.org/W2113814270","https://openalex.org/W2136155248","https://openalex.org/W2963528589","https://openalex.org/W2891205112","https://openalex.org/W2604379605","https://openalex.org/W2127141656","https://openalex.org/W2951015274","https://openalex.org/W2793493229","https://openalex.org/W2963654155","https://openalex.org/W2550980560","https://openalex.org/W2184188583","https://openalex.org/W1522734439","https://openalex.org/W2897492880","https://openalex.org/W2015394094"],"abstract_inverted_index":{"We":[0,27],"propose":[1],"an":[2],"end-to-end":[3],"deep":[4],"learning":[5],"architecture":[6],"for":[7],"word-level":[8],"visual":[9],"speech":[10],"recognition.":[11],"The":[12,52],"system":[13],"is":[14],"a":[15,37],"combination":[16],"of":[17,40,44],"spatiotemporal":[18],"convolutional,":[19],"residual":[20],"and":[21,29],"bidirectional":[22],"Long":[23],"Short-Term":[24],"Memory":[25],"networks.":[26],"train":[28],"evaluate":[30],"it":[31],"on":[32],"the":[33,66],"Lipreading":[34],"In-The-Wild":[35],"benchmark,":[36],"challenging":[38],"database":[39],"500-size":[41],"target-words":[42],"consisting":[43],"1.28sec":[45],"video":[46],"excerpts":[47],"from":[48],"BBC":[49],"TV":[50],"broadcasts.":[51],"proposed":[53],"network":[54],"attains":[55],"word":[56,73],"accuracy":[57],"equal":[58],"to":[59],"83.0,":[60],"yielding":[61],"6.8":[62],"absolute":[63],"improvement":[64],"over":[65],"current":[67],"state-of-the-art,":[68],"without":[69],"using":[70],"information":[71],"about":[72],"boundaries":[74],"during":[75],"training":[76],"or":[77],"testing.":[78]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}