{"id":"https://openalex.org/W3196404295","doi":"https://doi.org/10.21437/interspeech.2021-432","title":"Cross-Modal Knowledge Distillation Method for Automatic Cued Speech Recognition","display_name":"Cross-Modal Knowledge Distillation Method for Automatic Cued Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196404295","doi":"https://doi.org/10.21437/interspeech.2021-432","mag":"3196404295"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-432","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianrong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037548142","display_name":"Ziyue Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyue Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429597","display_name":"Xuewei Li","orcid":"https://orcid.org/0000-0002-5330-7298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuewei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027142928","display_name":"Mei Yu","orcid":"https://orcid.org/0000-0002-5169-4829"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779069","display_name":"Qiang Fang","orcid":"https://orcid.org/0000-0002-6548-980X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418896","display_name":"Li Liu","orcid":"https://orcid.org/0000-0003-1807-5492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2986","last_page":"2990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9976999759674072,"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cued-speech","display_name":"Cued speech","score":0.7747194170951843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7439346313476562},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6907616257667542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6480222940444946},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5905986428260803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46131017804145813},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3611290752887726},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32401081919670105},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07818511128425598}],"concepts":[{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.7747194170951843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7439346313476562},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6907616257667542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6480222940444946},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5905986428260803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46131017804145813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3611290752887726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32401081919670105},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07818511128425598},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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":1,"locations":[{"id":"doi:10.21437/interspeech.2021-432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-432","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":0.8500000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2791807133","https://openalex.org/W2082933777","https://openalex.org/W4220960781","https://openalex.org/W2010535944","https://openalex.org/W4256310722","https://openalex.org/W2082371543","https://openalex.org/W3157864487","https://openalex.org/W3176549632","https://openalex.org/W62877638","https://openalex.org/W2007272447"],"abstract_inverted_index":{"Cued":[0],"Speech":[1],"(CS)":[2],"is":[3,43,174],"a":[4,24,39,71,95,102,161,193],"visual":[5],"communication":[6],"system":[7],"for":[8,57,98,117,143,167],"the":[9,44,88,114,127,133,155,168,189],"deaf":[10],"or":[11],"hearing":[12],"impaired":[13],"people.":[14],"It":[15],"combines":[16],"lip":[17],"movements":[18],"with":[19,76,101,136],"hand":[20],"cues":[21],"to":[22,84,86,132,149,153,188],"obtain":[23,154],"complete":[25],"phonetic":[26],"repertoire.":[27],"Current":[28],"deep":[29],"learning":[30,148],"based":[31],"methods":[32],"on":[33,176],"automatic":[34],"CS":[35,85,99,122,165,181,185],"recognition":[36,100,186],"suffer":[37],"from":[38,129],"common":[40],"problem,":[41],"which":[42,79],"data":[45,90],"scarcity.":[46],"Until":[47],"now,":[48],"there":[49],"are":[50],"only":[51],"two":[52],"public":[53],"single":[54],"speaker":[55],"datasets":[56],"French":[58,177],"(238":[59],"sentences)":[60],"and":[61,111,119,138,178],"British":[62,163,179],"English":[63,164,180],"(97":[64],"sentences).":[65],"In":[66],"this":[67],"work,":[68],"we":[69,93,125,145,159],"propose":[70],"cross-modal":[72],"knowledge":[73,128],"distillation":[74,140],"method":[75,173],"teacher-student":[77],"structure,":[78],"transfers":[80],"audio":[81,108],"speech":[82,109],"information":[83],"overcome":[87],"limited":[89],"problem.":[91],"Firstly,":[92],"pretrain":[94,113],"teacher":[96,130],"model":[97,131,135],"large":[103,194],"amount":[104],"of":[105],"open":[106],"source":[107],"data,":[110],"simultaneously":[112],"feature":[115],"extractors":[116],"lips":[118],"hands":[120],"using":[121],"data.":[123],"Then,":[124],"distill":[126],"student":[134],"frame-level":[137],"sequence-level":[139],"strategies.":[141],"Importantly,":[142],"frame-level,":[144],"exploit":[146],"multi-task":[147],"weigh":[150],"losses":[151],"automatically,":[152],"balance":[156],"coefficient.":[157],"Besides,":[158],"establish":[160],"five-speaker":[162],"dataset":[166],"first":[169],"time.":[170],"The":[171],"proposed":[172],"evaluated":[175],"datasets,":[182],"showing":[183],"superior":[184],"performance":[187],"state-of-the-art":[190],"(SOTA)":[191],"by":[192],"margin.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}