{"id":"https://openalex.org/W4223681286","doi":"https://doi.org/10.1109/icassp43922.2022.9746976","title":"Multistream Neural Architectures for Cued Speech Recognition Using a Pre-Trained Visual Feature Extractor and Constrained CTC Decoding","display_name":"Multistream Neural Architectures for Cued Speech Recognition Using a Pre-Trained Visual Feature Extractor and Constrained CTC Decoding","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4223681286","doi":"https://doi.org/10.1109/icassp43922.2022.9746976"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746976","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.archives-ouvertes.fr/hal-03578503","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062020396","display_name":"Sanjana Sankar","orcid":null},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210124956","display_name":"Grenoble Images Parole Signal Automatique","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sanjana Sankar","raw_affiliation_strings":["Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab,Grenoble,France,38000","GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing"],"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab,Grenoble,France,38000","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085944842","display_name":"Denis Beautemps","orcid":"https://orcid.org/0000-0001-9625-3018"},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210124956","display_name":"Grenoble Images Parole Signal Automatique","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Denis Beautemps","raw_affiliation_strings":["Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab,Grenoble,France,38000","GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing"],"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab,Grenoble,France,38000","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060372031","display_name":"Thomas Hueber","orcid":"https://orcid.org/0000-0002-8296-5177"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210124956","display_name":"Grenoble Images Parole Signal Automatique","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Hueber","raw_affiliation_strings":["Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab,Grenoble,France,38000","GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing"],"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab,Grenoble,France,38000","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062020396"],"corresponding_institution_ids":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20467836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8477","last_page":"8481"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13497","display_name":"Hermeneutics and Narrative Identity","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13497","display_name":"Hermeneutics and Narrative Identity","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13695","display_name":"Aging, Elder Care, and Social Issues","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13099","display_name":"Health, Medicine and Society","score":0.95660001039505,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7453656196594238},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7358993291854858},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6859697699546814},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.6016397476196289},{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.594512403011322},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.518983781337738},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.468996524810791},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4487883746623993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4377089738845825},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42382270097732544},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08470523357391357},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08074849843978882},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08028542995452881}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7453656196594238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7358993291854858},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6859697699546814},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6016397476196289},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.594512403011322},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.518983781337738},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.468996524810791},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4487883746623993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4377089738845825},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42382270097732544},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08470523357391357},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08074849843978882},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08028542995452881},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","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/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746976","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03578503v1","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-03578503","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-03578503v2","is_oa":true,"landing_page_url":"https://hal.science/hal-03578503","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://2022.ieeeicassp.org/","raw_type":"Conference papers"},{"id":"doi:10.17023/yf5y-sm39","is_oa":true,"landing_page_url":"https://doi.org/10.17023/yf5y-sm39","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03578503v1","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-03578503","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W192471408","https://openalex.org/W1970027736","https://openalex.org/W1972680065","https://openalex.org/W2115410550","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2157331557","https://openalex.org/W2294798173","https://openalex.org/W2799813293","https://openalex.org/W2888888638","https://openalex.org/W3008402854","https://openalex.org/W3113399631","https://openalex.org/W3196404295","https://openalex.org/W6601066586","https://openalex.org/W6630165351","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W11553578","https://openalex.org/W7894605","https://openalex.org/W12811873","https://openalex.org/W4318159","https://openalex.org/W7296353","https://openalex.org/W16722605","https://openalex.org/W14456953","https://openalex.org/W8626355","https://openalex.org/W5132191","https://openalex.org/W6108535"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,15,52,64,69,83,113],"simple":[4],"and":[5,55,63,80,110,130],"effective":[6],"approach":[7,48],"for":[8,59,101],"automatic":[9],"recognition":[10],"of":[11,32,95,120],"Cued":[12],"Speech":[13],"(CS),":[14],"visual":[16,60],"communication":[17],"tool":[18],"that":[19,35],"helps":[20],"people":[21],"with":[22,29,75,82,132],"hearing":[23],"impairment":[24],"to":[25,44],"understand":[26],"spoken":[27],"language":[28],"the":[30,39,96,103,117,122],"help":[31],"hand":[33,54],"gestures":[34],"can":[36],"uniquely":[37],"identify":[38],"uttered":[40],"phonemes":[41],"in":[42],"complement":[43],"lip-reading.":[45],"The":[46,86],"proposed":[47,87,123],"is":[49,89],"based":[50,67],"on":[51,68,91],"pre-trained":[53],"lips":[56],"tracker":[57],"used":[58],"feature":[61],"extraction":[62],"phonetic":[65,104,118],"decoder":[66,129],"multistream":[70],"recurrent":[71],"neural":[72],"network":[73],"trained":[74],"connectionist":[76],"temporal":[77],"classification":[78],"loss":[79],"combined":[81],"pronunciation":[84],"lexicon.":[85],"system":[88,124],"evaluated":[90],"an":[92],"updated":[93],"version":[94],"French":[97],"CS":[98],"dataset":[99],"CSF18":[100],"which":[102],"transcription":[105],"has":[106],"been":[107],"manually":[108],"checked":[109],"corrected.":[111],"With":[112],"decoding":[114],"accuracy":[115],"at":[116],"level":[119],"70.88%,":[121],"outperforms":[125],"our":[126],"previous":[127],"CNN-HMM":[128],"competes":[131],"more":[133],"complex":[134],"baselines.":[135]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}