{"id":"https://openalex.org/W2735762732","doi":"https://doi.org/10.21437/interspeech.2017-106","title":"Improving Computer Lipreading via DNN Sequence Discriminative Training Techniques","display_name":"Improving Computer Lipreading via DNN Sequence Discriminative Training Techniques","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2735762732","doi":"https://doi.org/10.21437/interspeech.2017-106","mag":"2735762732"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-106","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-106","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":"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/A5010066202","display_name":"Kwanchiva Thangthai","orcid":null},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kwanchiva Thangthai","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035826908","display_name":"Richard Harvey","orcid":"https://orcid.org/0000-0001-9925-8316"},"institutions":[{"id":"https://openalex.org/I1118541","display_name":"University of East Anglia","ror":"https://ror.org/026k5mg93","country_code":"GB","type":"education","lineage":["https://openalex.org/I1118541"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard Harvey","raw_affiliation_strings":["School of Computing Sciences, University of East Anglia, Norwich, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing Sciences, University of East Anglia, Norwich, UK","institution_ids":["https://openalex.org/I1118541"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010066202"],"corresponding_institution_ids":["https://openalex.org/I1118541"],"apc_list":null,"apc_paid":null,"fwci":1.6778,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.85372829,"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":"3657","last_page":"3661"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8304669857025146},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8270291090011597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.784084677696228},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7567400932312012},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6701210737228394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5303616523742676},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4751558005809784},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4442847967147827},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4319227635860443},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42940810322761536},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4243418574333191},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38891151547431946},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07300430536270142}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8304669857025146},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8270291090011597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784084677696228},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7567400932312012},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6701210737228394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5303616523742676},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4751558005809784},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4442847967147827},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4319227635860443},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42940810322761536},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4243418574333191},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38891151547431946},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07300430536270142},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-106","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-106","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:ueaeprints.uea.ac.uk:63708","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W142945732","https://openalex.org/W1273351261","https://openalex.org/W1498436455","https://openalex.org/W1524333225","https://openalex.org/W1542311097","https://openalex.org/W1877570817","https://openalex.org/W1908325895","https://openalex.org/W1929897159","https://openalex.org/W1987238397","https://openalex.org/W1993882792","https://openalex.org/W2002342963","https://openalex.org/W2029199293","https://openalex.org/W2062164080","https://openalex.org/W2076462394","https://openalex.org/W2096263221","https://openalex.org/W2114016253","https://openalex.org/W2115439799","https://openalex.org/W2131342762","https://openalex.org/W2132991150","https://openalex.org/W2140826107","https://openalex.org/W2147768505","https://openalex.org/W2155765376","https://openalex.org/W2160815625","https://openalex.org/W2289925289","https://openalex.org/W2293009711","https://openalex.org/W2316870419","https://openalex.org/W2395416438","https://openalex.org/W2398406965","https://openalex.org/W2579335913","https://openalex.org/W2594690981","https://openalex.org/W2952746495","https://openalex.org/W3099202502","https://openalex.org/W4235765578"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2146591867","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W1990589093","https://openalex.org/W2160650576","https://openalex.org/W2535098683","https://openalex.org/W2501000458"],"abstract_inverted_index":{"Although":[0],"there":[1,10],"have":[2],"been":[3,12],"some":[4],"promising":[5],"results":[6,164],"in":[7,51,158,182],"computer":[8],"lipreading,":[9],"has":[11],"a":[13,71,87,99,115,120,179],"paucity":[14],"of":[15,27,40,47,89,152,155,173],"data":[16],"on":[17,143],"which":[18,83,118],"to":[19,76,125,177],"train":[20,85],"automatic":[21],"systems.":[22],"However":[23],"the":[24,28,45,68,108,127,144,153,183],"recent":[25,49],"emergence":[26],"TCD-TIMIT":[29],"corpus,":[30],"with":[31,70,98,132],"around":[32],"6000":[33],"words,":[34],"59":[35],"speakers":[36],"and":[37,59],"seven":[38],"hours":[39],"recorded":[41],"audio-visual":[42],"speech,":[43],"allows":[44],"deployment":[46],"more":[48],"techniques":[50],"audio-speech":[52],"such":[53],"as":[54],"Deep":[55],"Neural":[56],"Networks":[57],"(DNNs)":[58],"sequence":[60,90],"discriminative":[61,91],"training.":[62],"In":[63],"this":[64],"paper":[65],"we":[66,84],"combine":[67],"DNN":[69,109],"Hidden":[72],"Markov":[73],"Model":[74,123],"(HMM)":[75],"the,":[77],"so":[78],"called,":[79],"hybrid":[80],"DNN-HMM":[81],"configuration":[82],"using":[86],"variety":[88,146],"training":[92,138],"methods.":[93],"This":[94],"is":[95,106,169],"then":[96],"followed":[97],"weighted":[100],"finite":[101],"state":[102],"transducer.":[103],"The":[104],"conclusion":[105],"that":[107,167],"offers":[110,139],"very":[111],"substantial":[112],"improvement":[113,157],"over":[114],"conventional":[116],"classifier":[117],"uses":[119],"Gaussian":[121],"Mixture":[122],"(GMM)":[124],"model":[126],"densities":[128],"even":[129],"when":[130],"optimised":[131],"Speaker":[133],"Adaptive":[134],"Training.":[135],"Sequence":[136],"adaptive":[137],"further":[140],"improvements":[141,150],"depending":[142],"precise":[145],"employed":[147],"but":[148],"those":[149],"are":[151],"order":[154],"~10\\%":[156],"word":[159],"accuracy.":[160],"Putting":[161],"these":[162],"two":[163],"together":[165],"implies":[166],"lipreading":[168],"moving":[170],"from":[171],"something":[172],"rather":[174],"esoteric":[175],"interest":[176],"becoming":[178],"practical":[180],"reality":[181],"foreseeable":[184],"future.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}