{"id":"https://openalex.org/W4380862910","doi":"https://doi.org/10.21437/interspeech.2023-1669","title":"Investigating the dynamics of hand and lips in French Cued Speech using attention mechanisms and CTC-based decoding","display_name":"Investigating the dynamics of hand and lips in French Cued Speech using attention mechanisms and CTC-based decoding","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4380862910","doi":"https://doi.org/10.21437/interspeech.2023-1669"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1669","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.08290","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/I4210124956","display_name":"GIPSA-Lab","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":"Sanjana Sankar","raw_affiliation_strings":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"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/I4210124956","display_name":"GIPSA-Lab","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":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068848480","display_name":"Fr\u00e9d\u00e9ric Elisei","orcid":"https://orcid.org/0000-0002-1295-3445"},"institutions":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","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":"Fr\u00e9d\u00e9ric Elisei","raw_affiliation_strings":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","GIPSA-Services - GIPSA-Services (GIPSA-lab, \r\n11 rue des Math\u00e9matiques, \r\nGrenoble Campus BP46, \r\nF-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]},{"raw_affiliation_string":"GIPSA-Services - GIPSA-Services (GIPSA-lab, \r\n11 rue des Math\u00e9matiques, \r\nGrenoble Campus BP46, \r\nF-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013177566","display_name":"Olivier Perrotin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","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":"Olivier Perrotin","raw_affiliation_strings":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"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/I4210124956","display_name":"GIPSA-Lab","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":"Thomas Hueber","raw_affiliation_strings":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210124956"],"apc_list":null,"apc_paid":null,"fwci":0.4336,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5613644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4978","last_page":"4982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9386000037193298,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9386000037193298,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9075999855995178,"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/cued-speech","display_name":"Cued speech","score":0.8378312587738037},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7146344780921936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6830345392227173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6174687147140503},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.23075264692306519},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21254265308380127},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07807117700576782}],"concepts":[{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.8378312587738037},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7146344780921936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830345392227173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6174687147140503},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.23075264692306519},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21254265308380127},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07807117700576782}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-1669","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.08290","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.08290","pdf_url":"https://arxiv.org/pdf/2306.08290","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-04126530v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04126530","pdf_url":"https://hal.science/hal-04126530v1/file/sankar_interspeech23.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://interspeech2023.org/","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.08290","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.08290","pdf_url":"https://arxiv.org/pdf/2306.08290","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5656077686","display_name":"Communication for Children with Hearing Impairment to optimise Language Development","funder_award_id":"860755","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4380862910.pdf","grobid_xml":"https://content.openalex.org/works/W4380862910.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2791807133","https://openalex.org/W4220960781","https://openalex.org/W2010535944","https://openalex.org/W2082933777","https://openalex.org/W2082371543","https://openalex.org/W3157864487","https://openalex.org/W3095039513","https://openalex.org/W3176549632"],"abstract_inverted_index":{"Hard":[0],"of":[1,9,57,89,110,126,143],"hearing":[2],"or":[3],"profoundly":[4],"deaf":[5],"people":[6],"make":[7],"use":[8],"cued":[10],"speech":[11],"(CS)":[12],"as":[13],"a":[14,33,63,68,75,80,113,129,137],"communication":[15],"tool":[16],"to":[17,27,35,65,95],"understand":[18],"spoken":[19],"language.":[20],"By":[21],"delivering":[22],"cues":[23],"that":[24],"are":[25],"relevant":[26],"the":[28,46,49,52,55,90,97,100,108,124,140],"phonetic":[29],"information,":[30],"CS":[31],"offers":[32],"way":[34,64],"enhance":[36],"lipreading.":[37],"In":[38],"literature,":[39],"there":[40],"have":[41],"been":[42,117],"several":[43],"studies":[44],"on":[45],"dynamics":[47,92],"between":[48,99],"hand":[50],"and":[51,103],"lips":[53],"in":[54,139],"context":[56],"human":[58],"production.":[59],"This":[60],"article":[61],"proposes":[62],"investigate":[66],"how":[67],"neural":[69],"network":[70],"learns":[71],"this":[72,111,127],"relation":[73],"for":[74,119,134],"single":[76],"speaker":[77],"while":[78],"performing":[79],"recognition":[81,142],"task":[82],"using":[83],"attention":[84],"mechanisms.":[85],"Further,":[86],"an":[87],"analysis":[88],"learnt":[91],"is":[93],"utilized":[94],"establish":[96],"relationship":[98],"two":[101],"modalities":[102],"extract":[104],"automatic":[105,141],"segments.":[106],"For":[107],"purpose":[109],"study,":[112],"new":[114],"dataset":[115],"has":[116],"recorded":[118],"French":[120,144],"CS.":[121,145],"Along":[122],"with":[123],"release":[125],"dataset,":[128],"benchmark":[130],"will":[131],"be":[132],"reported":[133],"word-level":[135],"recognition,":[136],"novelty":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}