{"id":"https://openalex.org/W2914859359","doi":"https://doi.org/10.1109/slt.2018.8639698","title":"Deep View2View Mapping for View-Invariant Lipreading","display_name":"Deep View2View Mapping for View-Invariant Lipreading","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914859359","doi":"https://doi.org/10.1109/slt.2018.8639698","mag":"2914859359"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055069331","display_name":"Alexandros Koumparoulis","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Alexandros Koumparoulis","raw_affiliation_strings":["School of Electrical & Computer Eng., National Technical University of Athens, 15773 Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical & Computer Eng., National Technical University of Athens, 15773 Athens, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["thena Research and Innovation Center, 15125 Maroussi, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"thena Research and Innovation Center, 15125 Maroussi, Greece","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0824,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79569065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"588","last_page":"594"},"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":0.9976000189781189,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7312780618667603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7178753018379211},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4490705728530884},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4420109987258911},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.41077083349227905},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4102460443973541},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3981838524341583},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35764312744140625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312780618667603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7178753018379211},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4490705728530884},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4420109987258911},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.41077083349227905},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4102460443973541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3981838524341583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35764312744140625},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2018.8639698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/75302","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/75302","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings","raw_type":"conferenceItem"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W142945732","https://openalex.org/W652928785","https://openalex.org/W1503933356","https://openalex.org/W1518556865","https://openalex.org/W1524333225","https://openalex.org/W1526392145","https://openalex.org/W1535545184","https://openalex.org/W1608493013","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1982883756","https://openalex.org/W2004143321","https://openalex.org/W2029199293","https://openalex.org/W2060510034","https://openalex.org/W2074905202","https://openalex.org/W2076462394","https://openalex.org/W2078517841","https://openalex.org/W2078711706","https://openalex.org/W2098923380","https://openalex.org/W2152826865","https://openalex.org/W2184188583","https://openalex.org/W2267805933","https://openalex.org/W2412782625","https://openalex.org/W2551572271","https://openalex.org/W2578229578","https://openalex.org/W2602044573","https://openalex.org/W2604745051","https://openalex.org/W2604769302","https://openalex.org/W2605246626","https://openalex.org/W2612754342","https://openalex.org/W2613448434","https://openalex.org/W2889448058","https://openalex.org/W2890137412","https://openalex.org/W2893436174","https://openalex.org/W2897846591","https://openalex.org/W2898213923","https://openalex.org/W2952746495","https://openalex.org/W2962835968","https://openalex.org/W2962907415","https://openalex.org/W2962912639","https://openalex.org/W2963073614","https://openalex.org/W2963552679","https://openalex.org/W2963654155","https://openalex.org/W2972756321","https://openalex.org/W3143803406","https://openalex.org/W4298112588","https://openalex.org/W6605769872","https://openalex.org/W6631362777","https://openalex.org/W6631564540","https://openalex.org/W6632058173","https://openalex.org/W6636419984","https://openalex.org/W6637373629","https://openalex.org/W6675190910","https://openalex.org/W6686207219","https://openalex.org/W6732872814","https://openalex.org/W6743738265","https://openalex.org/W6753038255","https://openalex.org/W7011482893"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"Recently,":[0],"visual-only":[1],"and":[2,54],"audio-visual":[3,160],"speech":[4,162],"recognition":[5,163],"have":[6],"made":[7],"significant":[8],"progress":[9],"thanks":[10],"to":[11,33,44,61,82,88,124,126,133],"deep-learning":[12],"based,":[13],"trainable":[14],"visual":[15],"front-ends":[16],"(VFEs),":[17],"with":[18,197],"most":[19],"research":[20],"focusing":[21],"on":[22,40,50,58,64,104,155],"frontal":[23,41,127],"or":[24],"near-frontal":[25],"face":[26,42],"videos.":[27,67],"In":[28],"this":[29,69],"paper,":[30],"we":[31,71,97,130],"seek":[32],"expand":[34],"the":[35,51,73,105,139,151,171,175,178,193],"applicability":[36],"of":[37,112,186],"VFEs":[38],"targeted":[39],"views":[43,118],"non-frontal":[45,66,84,121],"ones,":[46,128],"without":[47],"making":[48],"assumptions":[49],"VFE":[52,152],"type,":[53],"allowing":[55,110],"systems":[56],"trained":[57],"frontal-view":[59,135],"data":[60],"be":[62],"applied":[63],"mismatched,":[65],"For":[68],"purpose,":[70],"adapt":[72],"\u201cpix2pix\u201d":[74],"model,":[75],"recently":[76],"proposed":[77],"for":[78],"image":[79],"translation":[80],"tasks,":[81],"transform":[83],"speaker":[85],"mouth":[86],"regions":[87],"frontal,":[89],"employing":[90],"a":[91,134,143],"convolutional":[92],"neural":[93],"network":[94,141],"architecture,":[95],"which":[96,129],"call":[98],"\u201cview2view\u201d.":[99],"We":[100,137],"develop":[101],"our":[102],"approach":[103,194],"OuluVS2":[106],"multiview":[107],"lipreading":[108],"dataset,":[109],"training":[111],"four":[113],"such":[114],"networks":[115],"that":[116,145,170],"map":[117],"at":[119,150],"predefined":[120],"angles":[122],"(up":[123],"profile)":[125],"subsequently":[131],"feed":[132],"VFE.":[136],"compare":[138],"\u201cview2view\u201d":[140,172],"against":[142],"baseline":[144],"performs":[146],"linear":[147],"cross-view":[148],"regression":[149],"space.":[153],"Results":[154],"visual-only,":[156],"as":[157,159],"well":[158],"automatic":[161,199],"over":[164],"multiple":[165],"acoustic":[166],"noise":[167],"conditions,":[168],"demonstrate":[169],"significantly":[173],"outperforms":[174],"baseline,":[176],"narrowing":[177],"performance":[179],"gap":[180],"from":[181],"an":[182,198],"ideal,":[183],"matched":[184],"scenario":[185],"view-specific":[187],"systems.":[188],"Improvements":[189],"are":[190],"retained":[191],"when":[192],"is":[195],"coupled":[196],"view":[200],"estimator.":[201]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}