{"id":"https://openalex.org/W4385822581","doi":"https://doi.org/10.21437/interspeech.2023-370","title":"Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech Based on Metric Learning","display_name":"Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech Based on Metric Learning","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822581","doi":"https://doi.org/10.21437/interspeech.2023-370"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-370","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-370","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":["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/A5092031914","display_name":"Sara Kashiwagi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sara Kashiwagi","raw_affiliation_strings":["Waseda University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085731517","display_name":"Keitaro Tanaka","orcid":"https://orcid.org/0009-0005-4338-5224"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keitaro Tanaka","raw_affiliation_strings":["Waseda University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695390","display_name":"Feng Qi","orcid":"https://orcid.org/0000-0001-6239-2968"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Qi Feng","raw_affiliation_strings":["Waseda University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083427215","display_name":"Shigeo Morishima","orcid":"https://orcid.org/0000-0001-8859-6539"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeo Morishima","raw_affiliation_strings":["Waseda Research Institute for Science and Engineering, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda Research Institute for Science and Engineering, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3397","last_page":"3401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11448","display_name":"Face recognition and analysis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11309","display_name":"Music and Audio Processing","score":0.996999979019165,"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/viseme","display_name":"Viseme","score":0.9274498224258423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7211289405822754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6902806162834167},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6779158115386963},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5991997718811035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49883556365966797},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4342370629310608},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.431551456451416},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.430736780166626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34710949659347534},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2792056202888489},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08242872357368469}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.9274498224258423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211289405822754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6902806162834167},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6779158115386963},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5991997718811035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49883556365966797},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4342370629310608},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.431551456451416},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.430736780166626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34710949659347534},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2792056202888489},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08242872357368469},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-370","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-370","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W65758255","https://openalex.org/W107924225","https://openalex.org/W1522301498","https://openalex.org/W1526392145","https://openalex.org/W1578725541","https://openalex.org/W2015143272","https://openalex.org/W2087681821","https://openalex.org/W2142490914","https://openalex.org/W2230777371","https://openalex.org/W2341033924","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2936149813","https://openalex.org/W2952746495","https://openalex.org/W2962915147","https://openalex.org/W2963356069","https://openalex.org/W2972756321","https://openalex.org/W3098841379","https://openalex.org/W3109715615","https://openalex.org/W3155765542","https://openalex.org/W3160833628","https://openalex.org/W3217229075","https://openalex.org/W4307286264","https://openalex.org/W4312638101"],"related_works":["https://openalex.org/W2133194887","https://openalex.org/W1974357398","https://openalex.org/W2053099149","https://openalex.org/W1559261064","https://openalex.org/W2299511660","https://openalex.org/W2124254345","https://openalex.org/W2105537028","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,31,74,96],"novel":[4],"metric":[5,75],"learning":[6,76],"approach":[7,77],"to":[8,43,61,83,92],"address":[9],"the":[10,28,51,63,85,106,110,118,136],"performance":[11],"gap":[12],"between":[13,27,67,115],"normal":[14,68],"and":[15,49,69,72,116,126],"silent":[16,44,57,70,139],"speech":[17,20,71,89,120],"in":[18,24,95],"visual":[19],"recognition":[21],"(VSR).The":[22],"difference":[23],"lip":[25],"movements":[26],"two":[29,88,119],"poses":[30],"challenge":[32],"for":[33,56],"existing":[34],"VSR":[35],"models,":[36],"which":[37],"exhibit":[38],"degraded":[39],"accuracy":[40,137],"when":[41,142],"applied":[42],"speech.To":[45],"solve":[46],"this":[47],"issue":[48],"tackle":[50],"scarcity":[52],"of":[53,87,109,138],"training":[54,144],"data":[55,145],"speech,":[58],"we":[59,81],"propose":[60],"leverage":[62],"shared":[64],"literal":[65],"content":[66],"present":[73],"based":[78],"on":[79],"visemes.Specifically,":[80],"aim":[82],"map":[84],"input":[86],"types":[90],"close":[91],"each":[93],"other":[94],"latent":[97],"space":[98],"if":[99],"they":[100],"have":[101],"similar":[102],"viseme":[103,112,128],"representations.By":[104],"minimizing":[105],"Kullback-Leibler":[107],"divergence":[108],"predicted":[111],"probability":[113],"distributions":[114],"within":[117],"types,":[121],"our":[122,133],"model":[123],"effectively":[124],"learns":[125],"predicts":[127],"identities.Our":[129],"evaluation":[130],"demonstrates":[131],"that":[132],"method":[134],"improves":[135],"VSR,":[140],"even":[141],"limited":[143],"is":[146],"available.":[147]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}