{"id":"https://openalex.org/W3196826198","doi":"https://doi.org/10.21437/interspeech.2021-440","title":"An Attention Self-Supervised Contrastive Learning Based Three-Stage Model for Hand Shape Feature Representation in Cued Speech","display_name":"An Attention Self-Supervised Contrastive Learning Based Three-Stage Model for Hand Shape Feature Representation in Cued Speech","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196826198","doi":"https://doi.org/10.21437/interspeech.2021-440","mag":"3196826198"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-440","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5102003658","display_name":"Jianrong Wang","orcid":"https://orcid.org/0000-0002-8980-1634"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianrong Wang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025111505","display_name":"Nan Gu","orcid":"https://orcid.org/0000-0002-2214-9928"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Gu","raw_affiliation_strings":["Tianjin International Engineering Institute, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin International Engineering Institute, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027142928","display_name":"Mei Yu","orcid":"https://orcid.org/0000-0002-5169-4829"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Yu","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429597","display_name":"Xuewei Li","orcid":"https://orcid.org/0000-0002-5330-7298"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuewei Li","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779069","display_name":"Qiang Fang","orcid":"https://orcid.org/0000-0002-6548-980X"},"institutions":[{"id":"https://openalex.org/I114218197","display_name":"Chinese Academy of Social Sciences","ror":"https://ror.org/05bxbmy32","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197"]},{"id":"https://openalex.org/I4210121707","display_name":"Institute of Linguistics","ror":"https://ror.org/02mrea437","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fang","raw_affiliation_strings":["Institute of Linguistics, Chinese Academy of Social Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Linguistics, Chinese Academy of Social Science, Beijing, China","institution_ids":["https://openalex.org/I114218197","https://openalex.org/I4210121707"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418896","display_name":"Li Liu","orcid":"https://orcid.org/0000-0003-1807-5492"},"institutions":[{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Liu","raw_affiliation_strings":["Shenzhen Research Institute of Big Data, the Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, the Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100418896"],"corresponding_institution_ids":["https://openalex.org/I4210099586","https://openalex.org/I4210116924"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"626","last_page":"630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9993000030517578,"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":0.9993000030517578,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.852144718170166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7348864674568176},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6296712160110474},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.61588454246521},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6151217222213745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5912346839904785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5166342854499817},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5090963244438171},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.4445226192474365},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42417648434638977},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34305131435394287},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23164120316505432},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21717891097068787},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.17670947313308716}],"concepts":[{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.852144718170166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7348864674568176},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6296712160110474},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.61588454246521},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6151217222213745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5912346839904785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5166342854499817},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5090963244438171},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.4445226192474365},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42417648434638977},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34305131435394287},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23164120316505432},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21717891097068787},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.17670947313308716},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-440","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-440","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4716616089","display_name":null,"funder_award_id":"61977049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5370700012","display_name":null,"funder_award_id":"2020A1515110376","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W276105310","https://openalex.org/W1581734961","https://openalex.org/W2000761799","https://openalex.org/W2115252128","https://openalex.org/W2132328527","https://openalex.org/W2140537255","https://openalex.org/W2143612262","https://openalex.org/W2164416728","https://openalex.org/W2168392347","https://openalex.org/W2763858995","https://openalex.org/W2765793020","https://openalex.org/W2778635523","https://openalex.org/W2799813293","https://openalex.org/W2805691304","https://openalex.org/W2888888638","https://openalex.org/W2904106524","https://openalex.org/W2952200000","https://openalex.org/W2962858109","https://openalex.org/W2972620384","https://openalex.org/W2985525390","https://openalex.org/W3005680577","https://openalex.org/W3008402854","https://openalex.org/W3010227584","https://openalex.org/W3044285175","https://openalex.org/W3082828314","https://openalex.org/W3113399631","https://openalex.org/W3208826636","https://openalex.org/W4242582195","https://openalex.org/W4297803663","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2791807133","https://openalex.org/W2082933777","https://openalex.org/W2082371543","https://openalex.org/W4220960781","https://openalex.org/W2905271011","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579","https://openalex.org/W1872833176","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Cued":[0],"Speech":[1],"(CS)":[2],"is":[3,42],"a":[4,16,22,43,70,85,102,135],"communication":[5],"system":[6],"for":[7,61],"deaf":[8],"people":[9],"or":[10],"hearing":[11],"impaired":[12],"people,":[13],"in":[14,24,46,161,177],"which":[15,104],"speaker":[17],"uses":[18],"it":[19],"to":[20,75,95,110,120],"aid":[21],"lipreader":[23],"phonetic":[25],"level":[26],"by":[27],"clarifying":[28],"potentially":[29],"ambiguous":[30],"mouth":[31],"movements":[32],"with":[33,115,183],"hand":[34,62,162],"shape":[35,63,163],"and":[36,107,117,124,149,170],"positions.Feature":[37],"extraction":[38],"of":[39,80,88,127,166],"multi-modal":[40],"CS":[41,47,57,91,131,143,178],"key":[44],"step":[45],"recognition.Recent":[48],"supervised":[49],"deep":[50],"learning":[51,73],"based":[52],"methods":[53],"suffer":[54],"from":[55],"noisy":[56],"data":[58,92],"annotations":[59],"especially":[60],"modality.In":[64],"this":[65],"work,":[66],"we":[67,100,133],"first":[68,98],"propose":[69],"self-supervised":[71],"contrastive":[72],"method":[74],"learn":[76,112],"the":[77,97,122,125,128,184],"feature":[78],"representation":[79],"image":[81],"without":[82],"using":[83],"labels.Secondly,":[84],"small":[86],"amount":[87],"manually":[89],"annotated":[90],"are":[93,175],"used":[94],"fine-tune":[96],"module.Thirdly,":[99],"present":[101],"module,":[103],"combines":[105],"Bi-LSTM":[106],"self-attention":[108],"networks":[109],"further":[111],"sequential":[113],"features":[114],"temporal":[116],"contextual":[118],"information.Besides,":[119],"enlarge":[121],"volume":[123],"diversity":[126],"current":[129],"limited":[130],"datasets,":[132],"build":[134],"new":[136],"British":[137,150,173],"English":[138,151],"dataset":[139],"containing":[140],"5":[141],"native":[142],"speakers.Evaluation":[144],"results":[145],"on":[146],"both":[147],"French":[148],"datasets":[152],"show":[153],"that":[154],"our":[155],"model":[156],"achieves":[157],"over":[158],"90%":[159],"accuracy":[160],"recognition.Significant":[164],"improvements":[165],"8.75%":[167],"(for":[168,172],"French)":[169],"10.09%":[171],"English)":[174],"achieved":[176],"phoneme":[179],"recognition":[180],"correctness":[181],"compared":[182],"state-of-the-art.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
