{"id":"https://openalex.org/W2725379595","doi":"https://doi.org/10.21437/avsp.2017-10","title":"Combining Multiple Views for Visual Speech Recognition","display_name":"Combining Multiple Views for Visual Speech Recognition","publication_year":2017,"publication_date":"2017-08-25","ids":{"openalex":"https://openalex.org/W2725379595","doi":"https://doi.org/10.21437/avsp.2017-10","mag":"2725379595"},"language":"en","primary_location":{"id":"doi:10.21437/avsp.2017-10","is_oa":false,"landing_page_url":"https://doi.org/10.21437/avsp.2017-10","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 14th International Conference on Auditory-Visual Speech Processing","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/1710.07168","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014631134","display_name":"Marina Zimmermann","orcid":"https://orcid.org/0000-0002-2666-5997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marina Zimmermann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076278565","display_name":"Mostafa Mehdipour Ghazi","orcid":"https://orcid.org/0000-0002-8473-281X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mostafa Mehdipour Ghazi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009982931","display_name":"Haz\u0131m Kemal Ekenel","orcid":"https://orcid.org/0000-0003-3697-8548"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hazim Kemal Ekenel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067782007","display_name":"Jean\u2010Philippe Thiran","orcid":"https://orcid.org/0000-0003-2938-9657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Philippe Thiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.07185751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9779999852180481,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.7972110509872437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7529911994934082},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6720412969589233},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5957828760147095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5306921005249023},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5083438754081726},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.500795841217041},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.49512138962745667},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4550631046295166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4539373815059662}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972110509872437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7529911994934082},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6720412969589233},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5957828760147095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5306921005249023},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5083438754081726},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.500795841217041},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49512138962745667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4550631046295166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4539373815059662},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/avsp.2017-10","is_oa":false,"landing_page_url":"https://doi.org/10.21437/avsp.2017-10","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 14th International Conference on Auditory-Visual Speech Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1710.07168","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.07168","pdf_url":"https://arxiv.org/pdf/1710.07168","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":null},{"id":"mag:2725379595","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1710.07168","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:infoscience.tind.io:229442","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/229442","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},{"id":"pmh:oai:polen.itu.edu.tr:11527/47855","is_oa":false,"landing_page_url":"https://hdl.handle.net/11527/47855","pdf_url":null,"source":{"id":"https://openalex.org/S4306400460","display_name":"Istanbul Technical University Academic Open Archive (Istanbul Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I48912391","host_organization_name":"Istanbul Technical University","host_organization_lineage":["https://openalex.org/I48912391"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.1710.07168","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1710.07168","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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1710.07168","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1710.07168","pdf_url":"https://arxiv.org/pdf/1710.07168","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":null},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2725379595.pdf","grobid_xml":"https://content.openalex.org/works/W2725379595.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W142758689","https://openalex.org/W2602044573","https://openalex.org/W2105523781","https://openalex.org/W1192783930","https://openalex.org/W69118165","https://openalex.org/W1490506669","https://openalex.org/W3114308011","https://openalex.org/W2905699315","https://openalex.org/W2790326622","https://openalex.org/W2113270438","https://openalex.org/W2889624961","https://openalex.org/W3162596541","https://openalex.org/W1603553412","https://openalex.org/W2402110615","https://openalex.org/W2752238778","https://openalex.org/W2964182350","https://openalex.org/W2968682061","https://openalex.org/W2963785710","https://openalex.org/W2134723767","https://openalex.org/W2963701934"],"abstract_inverted_index":{"Visual":[0],"speech":[1,16,30,58,81],"recognition":[2,17,31,82],"is":[3,155],"a":[4,9,49,90,106,112],"challenging":[5],"research":[6],"problem":[7],"with":[8,174],"particular":[10],"practical":[11],"application":[12],"of":[13,35,65],"aiding":[14],"audio":[15],"in":[18,33,84,105,136],"noisy":[19],"scenarios.":[20],"Multiple":[21],"camera":[22],"setups":[23],"can":[24],"be":[25],"beneficial":[26],"for":[27,56,159],"the":[28,124,132,143,148,152,160,175],"visual":[29,57,80],"systems":[32],"terms":[34],"improved":[36],"performance":[37],"and":[38,47,75,177],"robustness.":[39],"In":[40],"this":[41,45,85,120,172],"paper,":[42],"we":[43],"explore":[44],"aspect":[46],"provide":[48],"comprehensive":[50],"study":[51,86],"on":[52,151],"combining":[53,123,171],"multiple":[54],"views":[55],"recognition.":[59],"The":[60,78,115,128],"thorough":[61],"analysis":[62],"covers":[63],"fusion":[64,117],"all":[66],"possible":[67],"view":[68,140,164,173,179],"angle":[69],"combinations":[70],"both":[71],"at":[72],"feature":[73],"level":[74],"decision":[76,116],"level.":[77],"employed":[79],"system":[83],"extracts":[87],"features":[88,102],"through":[89],"PCA-based":[91],"convolutional":[92],"neural":[93],"network,":[94],"followed":[95],"by":[96,122],"an":[97],"LSTM":[98],"network.":[99],"Finally,":[100],"these":[101],"are":[103],"processed":[104],"tandem":[107],"system,":[108],"being":[109],"fed":[110],"into":[111],"GMM-HMM":[113],"scheme.":[114],"acts":[118],"after":[119],"point":[121],"Viterbi":[125],"path":[126],"log-likelihoods.":[127],"results":[129,144],"show":[130],"that":[131],"complementary":[133],"information":[134],"contained":[135],"recordings":[137],"from":[138,157],"different":[139],"angles":[141],"improves":[142],"significantly.":[145],"For":[146],"example,":[147],"sentence":[149],"correctness":[150],"test":[153],"set":[154],"increased":[156],"76%":[158],"highest":[161],"performing":[162],"single":[163],"($30^\\circ$)":[165],"to":[166,168],"up":[167],"83%":[169],"when":[170],"frontal":[176],"$60^\\circ$":[178],"angles.":[180]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}