{"id":"https://openalex.org/W2580471497","doi":"https://doi.org/10.1109/icassp.2017.7952625","title":"End-to-end visual speech recognition with LSTMS","display_name":"End-to-end visual speech recognition with LSTMS","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2580471497","doi":"https://doi.org/10.1109/icassp.2017.7952625","mag":"2580471497"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/1701.05847","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Imperial College London, Dept. of Computing, London, UK","Imperial College London, Department of Computing, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, Dept. of Computing, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, Department of Computing, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023881063","display_name":"Zuwei Li","orcid":"https://orcid.org/0000-0001-7396-1337"},"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":"Zuwei Li","raw_affiliation_strings":["Imperial College London, Dept. of Computing, London, UK","Imperial College London, Department of Computing, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, Dept. of Computing, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, Department of Computing, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"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/I124357947","display_name":"University of London","ror":"https://ror.org/04cw6st05","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"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, Univ. of Twente, UK","Imperial College London, Department of Computing, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London, Univ. of Twente, UK","institution_ids":["https://openalex.org/I47508984","https://openalex.org/I45129253","https://openalex.org/I124357947"]},{"raw_affiliation_string":"Imperial College London, Department of Computing, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009475700"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":2.2429,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88852437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2592","last_page":"2596"},"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":0.9990000128746033,"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":0.9976999759674072,"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":0.8727374076843262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6085538268089294},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5767242908477783},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5691598653793335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5246617794036865},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5190413594245911},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.48959165811538696},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4799104630947113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8727374076843262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6085538268089294},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5767242908477783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5691598653793335},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5246617794036865},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5190413594245911},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.48959165811538696},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4799104630947113},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp.2017.7952625","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952625","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1701.05847","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.05847","pdf_url":"https://arxiv.org/pdf/1701.05847","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:2580471497","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1701.05847.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":"pmh:oai:ris.utwente.nl:publications/f2ec7e83-b303-42a3-983c-ea304b4b8732","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85023746549&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Petridis, S, Li, Z & Pantic, M 2017, End-to-end visual speech recognition with LSTMS. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952625, IEEE, pp. 2592-2596, 42nd IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, Louisiana, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7952625","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/55125","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/55125","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"Conference Paper"},{"id":"pmh:ut:oai:ris.utwente.nl:publications/f2ec7e83-b303-42a3-983c-ea304b4b8732","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/f2ec7e83-b303-42a3-983c-ea304b4b8732","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings, 2592 - 2596","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"doi:10.48550/arxiv.1701.05847","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1701.05847","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:1701.05847","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.05847","pdf_url":"https://arxiv.org/pdf/1701.05847","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2580471497.pdf","grobid_xml":"https://content.openalex.org/works/W2580471497.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W44815768","https://openalex.org/W88081813","https://openalex.org/W154472438","https://openalex.org/W1503933356","https://openalex.org/W1526392145","https://openalex.org/W1588214556","https://openalex.org/W2015143272","https://openalex.org/W2022799064","https://openalex.org/W2051676197","https://openalex.org/W2076462394","https://openalex.org/W2087681821","https://openalex.org/W2096391593","https://openalex.org/W2100495367","https://openalex.org/W2121486117","https://openalex.org/W2142075667","https://openalex.org/W2148659689","https://openalex.org/W2171209807","https://openalex.org/W2184188583","https://openalex.org/W2208724044","https://openalex.org/W2267805933","https://openalex.org/W2404704342","https://openalex.org/W2406846463","https://openalex.org/W2511073133","https://openalex.org/W2612434330","https://openalex.org/W2949547965","https://openalex.org/W6606244218","https://openalex.org/W6639996154","https://openalex.org/W6656689313","https://openalex.org/W6686207219","https://openalex.org/W6713551954"],"related_works":["https://openalex.org/W2951015274","https://openalex.org/W2935504762","https://openalex.org/W2952746495","https://openalex.org/W2404704342","https://openalex.org/W2184188583","https://openalex.org/W2096391593","https://openalex.org/W2594690981","https://openalex.org/W2578229578","https://openalex.org/W2015143272","https://openalex.org/W2604769302","https://openalex.org/W2406846463","https://openalex.org/W2121486117","https://openalex.org/W2113814270","https://openalex.org/W2100495367","https://openalex.org/W2098923380","https://openalex.org/W2951700231","https://openalex.org/W3000834666","https://openalex.org/W2075925017","https://openalex.org/W2998778917","https://openalex.org/W1522301498"],"abstract_inverted_index":{"Traditional":[0],"visual":[1,56,96,171],"speech":[2,57,97],"recognition":[3,58],"systems":[4],"consist":[5],"of":[6,42,69,102,130,144],"two":[7,103,132],"stages,":[8],"feature":[9,34],"extraction":[10,35],"and":[11,29,44,87,90,112,127,156],"classification.":[12,98],"Recently,":[13],"several":[14],"deep":[15],"learning":[16,41],"approaches":[17],"have":[18],"been":[19],"presented":[20],"which":[21,77,105,167],"automatically":[22],"extract":[23,81,106],"features":[24,43,82,107],"from":[25,84,109],"the":[26,33,67,74,85,110,128,131,147,153,159],"mouth":[27,111],"images":[28],"aim":[30],"to":[31,80],"replace":[32],"stage.":[36],"However,":[37],"research":[38],"on":[39,61,152,158],"joint":[40],"classification":[45,89],"is":[46,73,150],"very":[47],"limited.":[48],"In":[49],"this":[50,72],"work,":[51],"we":[52],"present":[53],"an":[54,125],"end-to-end":[55],"system":[59],"based":[60],"Long-Short":[62],"Memory":[63],"(LSTM)":[64],"networks.":[65],"To":[66],"best":[68],"our":[70],"knowledge,":[71],"first":[75],"model":[76,100],"simultaneously":[78],"learns":[79],"directly":[83,108],"pixels":[86],"perform":[88],"also":[91],"achieves":[92],"state-of-the-art":[93],"performance":[94],"in":[95,119],"The":[99,116],"consists":[101],"streams":[104,133],"difference":[113],"images,":[114],"respectively.":[115],"temporal":[117],"dynamics":[118],"each":[120],"stream":[121],"are":[122],"modelled":[123],"by":[124],"LSTM":[126,139],"fusion":[129],"takes":[134],"place":[135],"via":[136],"a":[137,169],"Bidirectional":[138],"(BLSTM).":[140],"An":[141],"absolute":[142],"improvement":[143],"9.7%":[145],"over":[146],"base":[148],"line":[149],"reported":[151],"OuluVS2":[154],"database,":[155],"1.5%":[157],"CUAVE":[160],"database":[161],"when":[162],"compared":[163],"with":[164],"other":[165],"methods":[166],"use":[168],"similar":[170],"front-end.":[172]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}