{"id":"https://openalex.org/W2267805933","doi":"https://doi.org/10.1109/icassp.2016.7472852","title":"Lipreading with long short-term memory","display_name":"Lipreading with long short-term memory","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2267805933","doi":"https://doi.org/10.1109/icassp.2016.7472852","mag":"2267805933"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5020719193","display_name":"Michael Wand","orcid":"https://orcid.org/0000-0003-0966-7824"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]},{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Michael Wand","raw_affiliation_strings":["USI & SUPSI, The Swiss AI Lab IDSIA"],"affiliations":[{"raw_affiliation_string":"USI & SUPSI, The Swiss AI Lab IDSIA","institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I15196421"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068199087","display_name":"Jan Koutn\u00edk","orcid":null},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jan Koutnik","raw_affiliation_strings":["USI & SUPSI, The Swiss AI Lab IDSIA"],"affiliations":[{"raw_affiliation_string":"USI & SUPSI, The Swiss AI Lab IDSIA","institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I15196421"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071172037","display_name":"J\u00fcrgen Schmidhuber","orcid":null},"institutions":[{"id":"https://openalex.org/I15196421","display_name":"University of Applied Sciences and Arts of Southern Switzerland","ror":"https://ror.org/05ep8g269","country_code":"CH","type":"education","lineage":["https://openalex.org/I15196421"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jurgen Schmidhuber","raw_affiliation_strings":["USI & SUPSI, The Swiss AI Lab IDSIA"],"affiliations":[{"raw_affiliation_string":"USI & SUPSI, The Swiss AI Lab IDSIA","institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I15196421"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020719193"],"corresponding_institution_ids":["https://openalex.org/I15196421","https://openalex.org/I2614128279"],"apc_list":null,"apc_paid":null,"fwci":17.3701,"has_fulltext":false,"cited_by_count":210,"citation_normalized_percentile":{"value":0.99466526,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6115","last_page":"6119"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8355239033699036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6725637912750244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6325209140777588},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6083277463912964},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.5993887186050415},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5696541666984558},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.5630311965942383},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5357540845870972},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.45596712827682495},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.44226643443107605},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4297771155834198},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.41638755798339844},{"id":"https://openalex.org/keywords/feedforward-neural-network","display_name":"Feedforward neural network","score":0.4144720137119293},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4140804708003998},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.3598359227180481},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.076131671667099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8355239033699036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6725637912750244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6325209140777588},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6083277463912964},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.5993887186050415},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5696541666984558},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.5630311965942383},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5357540845870972},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.45596712827682495},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.44226643443107605},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4297771155834198},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.41638755798339844},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.4144720137119293},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4140804708003998},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3598359227180481},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.076131671667099},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W91932436","https://openalex.org/W811578723","https://openalex.org/W1689711448","https://openalex.org/W1908325895","https://openalex.org/W1922655562","https://openalex.org/W1992790156","https://openalex.org/W1995735739","https://openalex.org/W2005708641","https://openalex.org/W2008120082","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2017280922","https://openalex.org/W2039640471","https://openalex.org/W2059169992","https://openalex.org/W2060756806","https://openalex.org/W2064675550","https://openalex.org/W2066941820","https://openalex.org/W2102113734","https://openalex.org/W2106137268","https://openalex.org/W2126584718","https://openalex.org/W2127141656","https://openalex.org/W2129160496","https://openalex.org/W2136155248","https://openalex.org/W2136848157","https://openalex.org/W2142490914","https://openalex.org/W2143612262","https://openalex.org/W2145442746","https://openalex.org/W2147800946","https://openalex.org/W2152417180","https://openalex.org/W2152826865","https://openalex.org/W2157190406","https://openalex.org/W2160815625","https://openalex.org/W2161969291","https://openalex.org/W2168861131","https://openalex.org/W2184045248","https://openalex.org/W2397098974","https://openalex.org/W2556171197","https://openalex.org/W6600971220","https://openalex.org/W6603833124","https://openalex.org/W6637409405","https://openalex.org/W6639968709","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6679032535","https://openalex.org/W6681494444","https://openalex.org/W6712664211","https://openalex.org/W6729699919","https://openalex.org/W6997266731"],"related_works":["https://openalex.org/W2912153778","https://openalex.org/W4288108708","https://openalex.org/W4387163678","https://openalex.org/W2973430807","https://openalex.org/W4385280324","https://openalex.org/W2890685186","https://openalex.org/W2984436043","https://openalex.org/W4390245176","https://openalex.org/W2524120878","https://openalex.org/W3173606726"],"abstract_inverted_index":{"Lipreading,":[0],"i.e.":[1],"speech":[2],"recognition":[3],"from":[4,95],"visual-only":[5],"recordings":[6],"of":[7,61,86,98,120],"a":[8,15,45,63,72,112],"speaker's":[9],"face,":[10],"can":[11],"be":[12],"achieved":[13],"with":[14],"processing":[16],"pipeline":[17],"based":[18],"solely":[19],"on":[20,93,116],"neural":[21,33,125],"networks,":[22],"yielding":[23],"significantly":[24],"better":[25],"accuracy":[26,115],"than":[27],"conventional":[28,79],"methods.":[29],"Feedforward":[30],"and":[31,69,84],"recurrent":[32],"network":[34,65],"layers":[35],"(namely":[36],"Long":[37],"Short-Term":[38],"Memory;":[39],"LSTM)":[40],"are":[41],"stacked":[42,64],"to":[43,71,108],"form":[44],"single":[46],"structure":[47],"which":[48],"is":[49],"trained":[50],"by":[51],"back-propagating":[52],"error":[53],"gradients":[54],"through":[55],"all":[56],"the":[57,99,123,131],"layers.":[58],"The":[59,89],"performance":[60],"such":[62],"was":[66,91],"experimentally":[67],"evaluated":[68],"compared":[70],"standard":[73],"Support":[74],"Vector":[75],"Machine":[76],"classifier":[77],"using":[78,122],"computer":[80],"vision":[81],"features":[82],"(Eigenlips":[83],"Histograms":[85],"Oriented":[87],"Gradients).":[88],"evaluation":[90,118],"performed":[92],"data":[94],"19":[96],"speakers":[97,119],"publicly":[100],"available":[101],"GRID":[102],"corpus.":[103],"With":[104],"51":[105],"different":[106],"words":[107],"classify,":[109],"we":[110],"report":[111],"best":[113,132],"word":[114],"held-out":[117],"79.6%":[121],"end-to-end":[124],"network-based":[126],"solution":[127,134],"(11.6%":[128],"improvement":[129],"over":[130],"feature-based":[133],"evaluated).":[135]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":36},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":7}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}