{"id":"https://openalex.org/W3113399631","doi":"https://doi.org/10.23919/eusipco47968.2020.9287365","title":"A Fully Convolutional Sequence Learning Approach for Cued Speech Recognition from Videos","display_name":"A Fully Convolutional Sequence Learning Approach for Cued Speech Recognition from Videos","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3113399631","doi":"https://doi.org/10.23919/eusipco47968.2020.9287365","mag":"3113399631"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287365","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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/A5054654614","display_name":"Katerina Papadimitriou","orcid":null},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Katerina Papadimitriou","raw_affiliation_strings":["University of Thessaly, Volos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["University of Thessaly, Volos, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145722265"],"apc_list":null,"apc_paid":null,"fwci":1.1889,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.77092415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/computer-science","display_name":"Computer science","score":0.8200647830963135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7713676691055298},{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.7265127897262573},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.70272296667099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5807660818099976},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5015249252319336},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4864937663078308},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47742876410484314},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4645639955997467},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43422651290893555},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42895182967185974},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4264858067035675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8200647830963135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7713676691055298},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.7265127897262573},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.70272296667099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5807660818099976},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5015249252319336},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4864937663078308},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47742876410484314},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4645639955997467},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43422651290893555},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42895182967185974},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4264858067035675},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287365","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/77585","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/77585","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":"European Signal Processing Conference","raw_type":"conferenceItem"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327859","display_name":"Hellenic Foundation for Research and Innovation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1502200391","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1731114447","https://openalex.org/W1902237438","https://openalex.org/W1972680065","https://openalex.org/W2064675550","https://openalex.org/W2082728674","https://openalex.org/W2108598243","https://openalex.org/W2115410550","https://openalex.org/W2133564696","https://openalex.org/W2140537255","https://openalex.org/W2146502635","https://openalex.org/W2164598857","https://openalex.org/W2194775991","https://openalex.org/W2567070169","https://openalex.org/W2587741066","https://openalex.org/W2613904329","https://openalex.org/W2766028520","https://openalex.org/W2785047343","https://openalex.org/W2792183839","https://openalex.org/W2799813293","https://openalex.org/W2888888638","https://openalex.org/W2899771611","https://openalex.org/W2908875155","https://openalex.org/W2963524571","https://openalex.org/W2963616706","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W2972557472","https://openalex.org/W2972620384","https://openalex.org/W2972630480","https://openalex.org/W2998214081","https://openalex.org/W3102516861","https://openalex.org/W4293318337","https://openalex.org/W6630165351","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6679434410","https://openalex.org/W6681435938","https://openalex.org/W6731370813","https://openalex.org/W6737778391","https://openalex.org/W6745214111","https://openalex.org/W6756040250","https://openalex.org/W6772523552"],"related_works":["https://openalex.org/W2791807133","https://openalex.org/W4220960781","https://openalex.org/W2010535944","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Cued":[0],"Speech":[1],"constitutes":[2],"a":[3,38,60,72,84,91,99,123,137,140],"sign-based":[4],"communication":[5],"variant":[6],"for":[7,104],"the":[8,112],"speech":[9,119,144],"and":[10,24,59,66,88,139,152],"hearing":[11],"impaired,":[12],"which":[13],"involves":[14],"visual":[15,68],"information":[16],"from":[17,71],"lip":[18,67],"movements":[19],"combined":[20],"with":[21],"hand":[22,79],"positional":[23],"gestural":[25],"cues.":[26],"In":[27],"this":[28,110],"paper,":[29],"we":[30],"consider":[31],"its":[32],"automatic":[33],"recognition":[34,116],"in":[35,146],"videos,":[36],"introducing":[37],"deep":[39],"sequence":[40],"learning":[41],"approach":[42,126],"that":[43],"consists":[44],"of":[45,117,148],"two":[46],"separately":[47],"trained":[48],"components:":[49],"an":[50],"image":[51],"learner":[52],"based":[53,127],"on":[54,129,136],"convolutional":[55,62,102],"neural":[56],"networks":[57],"(CNNs)":[58],"fully":[61],"encoder-decoder.":[63],"Specifically,":[64],"handshape":[65],"features":[69],"extracted":[70],"3D-CNN":[73],"feature":[74],"learner,":[75],"as":[76,78],"well":[77],"position":[80],"embeddings":[81],"obtained":[82],"by":[83,98],"2D-CNN,":[85],"are":[86],"concatenated":[87],"fed":[89],"to":[90,156],"time-depth":[92],"separable":[93],"(TDS)":[94],"block":[95],"structure,":[96],"followed":[97],"multi-step":[100],"attention-based":[101],"decoder":[103],"phoneme":[105,149],"prediction.":[106],"To":[107],"our":[108],"knowledge,":[109],"is":[111,120,134,154],"first":[113],"work":[114],"where":[115],"cued":[118,143],"addressed":[121],"using":[122],"common":[124],"modeling":[125,160],"entirely":[128],"CNNs.":[130],"The":[131],"introduced":[132],"model":[133],"evaluated":[135],"French":[138],"British":[141],"English":[142],"dataset":[145],"terms":[147],"error":[150],"rate,":[151],"it":[153],"shown":[155],"significantly":[157],"outperform":[158],"alternative":[159],"approaches.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2021-01-05T00:00:00"}