{"id":"https://openalex.org/W4321009928","doi":"https://doi.org/10.1145/3544548.3581465","title":"LipLearner: Customizable Silent Speech Interactions on Mobile Devices","display_name":"LipLearner: Customizable Silent Speech Interactions on Mobile Devices","publication_year":2023,"publication_date":"2023-04-19","ids":{"openalex":"https://openalex.org/W4321009928","doi":"https://doi.org/10.1145/3544548.3581465"},"language":"en","primary_location":{"id":"doi:10.1145/3544548.3581465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3544548.3581465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems","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/2302.05907","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009434654","display_name":"Zixiong Su","orcid":"https://orcid.org/0000-0001-6048-3268"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zixiong Su","raw_affiliation_strings":["Rekimoto Lab, GSII, The University of Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6048-3268","affiliations":[{"raw_affiliation_string":"Rekimoto Lab, GSII, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007497017","display_name":"Shitao Fang","orcid":"https://orcid.org/0000-0003-1401-8482"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shitao Fang","raw_affiliation_strings":["Interactive Intelligent Systems Laboratory, The University of Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1401-8482","affiliations":[{"raw_affiliation_string":"Interactive Intelligent Systems Laboratory, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082649952","display_name":"Jun Rekimoto","orcid":"https://orcid.org/0000-0002-3629-2514"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Rekimoto","raw_affiliation_strings":["The University of Tokyo, Japan and Sony CSL Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3629-2514","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Japan and Sony CSL Kyoto, Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8179072141647339},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5958951711654663},{"id":"https://openalex.org/keywords/learnability","display_name":"Learnability","score":0.5938977599143982},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.5653214454650879},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5422661304473877},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5345249772071838},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5229895114898682},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5042101144790649},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49685290455818176},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4867077171802521},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.47980406880378723},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4338856637477875},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.41540664434432983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3846965432167053},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3321724534034729},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0953567624092102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179072141647339},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5958951711654663},{"id":"https://openalex.org/C2777723229","wikidata":"https://www.wikidata.org/wiki/Q4367921","display_name":"Learnability","level":2,"score":0.5938977599143982},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.5653214454650879},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5422661304473877},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5345249772071838},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5229895114898682},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5042101144790649},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49685290455818176},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4867077171802521},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.47980406880378723},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4338856637477875},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.41540664434432983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3846965432167053},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3321724534034729},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0953567624092102},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3544548.3581465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3544548.3581465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2302.05907","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.05907","pdf_url":"https://arxiv.org/pdf/2302.05907","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2302.05907","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.05907","pdf_url":"https://arxiv.org/pdf/2302.05907","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W19399978","https://openalex.org/W1488659701","https://openalex.org/W1540787848","https://openalex.org/W1578725541","https://openalex.org/W1995735739","https://openalex.org/W2013317861","https://openalex.org/W2032191478","https://openalex.org/W2039640471","https://openalex.org/W2056852181","https://openalex.org/W2087681821","https://openalex.org/W2099257899","https://openalex.org/W2108033344","https://openalex.org/W2110015077","https://openalex.org/W2115252128","https://openalex.org/W2149034627","https://openalex.org/W2156060621","https://openalex.org/W2322064186","https://openalex.org/W2394613688","https://openalex.org/W2793257307","https://openalex.org/W2806172474","https://openalex.org/W2808135558","https://openalex.org/W2896622783","https://openalex.org/W2897318954","https://openalex.org/W2909141918","https://openalex.org/W2921295135","https://openalex.org/W2941048526","https://openalex.org/W2952609044","https://openalex.org/W2963115079","https://openalex.org/W2963272864","https://openalex.org/W2963654155","https://openalex.org/W2963680395","https://openalex.org/W2963741406","https://openalex.org/W2981852735","https://openalex.org/W3007912670","https://openalex.org/W3016011581","https://openalex.org/W3031554797","https://openalex.org/W3035626590","https://openalex.org/W3091762102","https://openalex.org/W3093564344","https://openalex.org/W3095897738","https://openalex.org/W3103322708","https://openalex.org/W3135367836","https://openalex.org/W3145450063","https://openalex.org/W3157582158","https://openalex.org/W3160833628","https://openalex.org/W3164825066","https://openalex.org/W3166396011","https://openalex.org/W3177183117","https://openalex.org/W3182657421","https://openalex.org/W3206248339","https://openalex.org/W3207628370","https://openalex.org/W4200482297","https://openalex.org/W4220783478","https://openalex.org/W4220871331","https://openalex.org/W4224926225","https://openalex.org/W4225124540","https://openalex.org/W4287392530","https://openalex.org/W4288089799","https://openalex.org/W4288327876","https://openalex.org/W4292779060","https://openalex.org/W4297808394"],"related_works":["https://openalex.org/W4302791369","https://openalex.org/W2951285859","https://openalex.org/W2766040214","https://openalex.org/W72092541","https://openalex.org/W2118717649","https://openalex.org/W37360785","https://openalex.org/W1973394166","https://openalex.org/W2413243053","https://openalex.org/W180475243","https://openalex.org/W410723623"],"abstract_inverted_index":{"Silent":[0],"speech":[1,97,142],"interface":[2,98],"is":[3,69],"a":[4,19,94],"promising":[5],"technology":[6],"that":[7,111,133],"enables":[8],"private":[9],"communications":[10],"in":[11],"natural":[12],"language.":[13],"However,":[14],"previous":[15],"approaches":[16],"only":[17,71],"support":[18],"small":[20],"and":[21,55,75,103,147],"inflexible":[22],"vocabulary,":[23],"which":[24],"leads":[25],"to":[26,33,51,92],"limited":[27],"expressiveness.":[28],"We":[29],"leverage":[30],"contrastive":[31],"learning":[32,84,128],"learn":[34],"efficient":[35],"lipreading":[36],"representations,":[37],"enabling":[38],"few-shot":[39],"command":[40],"customization":[41],"with":[42,100,112,120,144],"minimal":[43],"user":[44,108],"effort.":[45],"Our":[46],"model":[47],"exhibits":[48],"high":[49,121,145],"robustness":[50],"different":[52],"lighting,":[53],"posture,":[54],"gesture":[56],"conditions":[57],"on":[58],"an":[59,65,125],"in-the-wild":[60],"dataset.":[61],"For":[62],"25-command":[63],"classification,":[64],"F1-score":[66],"of":[67],"0.8947":[68],"achievable":[70],"using":[72],"one":[73],"shot,":[74],"its":[76],"performance":[77],"can":[78],"be":[79],"further":[80],"boosted":[81],"by":[82,124],"adaptively":[83],"from":[85],"more":[86],"data.":[87],"This":[88],"generalizability":[89],"allowed":[90],"us":[91],"develop":[93],"mobile":[95],"silent":[96,141],"empowered":[99],"on-device":[101],"fine-tuning":[102],"visual":[104],"keyword":[105],"spotting.":[106],"A":[107],"study":[109],"demonstrated":[110],"LipLearner,":[113],"users":[114],"could":[115],"define":[116],"their":[117],"own":[118],"commands":[119],"reliability":[122],"guaranteed":[123],"online":[126],"incremental":[127],"scheme.":[129],"Subjective":[130],"feedback":[131],"indicated":[132],"our":[134],"system":[135],"provides":[136],"essential":[137],"functionalities":[138],"for":[139],"customizable":[140],"interactions":[143],"usability":[146],"learnability.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}