{"id":"https://openalex.org/W4307485552","doi":"https://doi.org/10.1145/3526114.3558737","title":"LipLearner: Customizing Silent Speech Commands from Voice Input using One-shot Lipreading","display_name":"LipLearner: Customizing Silent Speech Commands from Voice Input using One-shot Lipreading","publication_year":2022,"publication_date":"2022-10-28","ids":{"openalex":"https://openalex.org/W4307485552","doi":"https://doi.org/10.1145/3526114.3558737"},"language":"en","primary_location":{"id":"doi:10.1145/3526114.3558737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3526114.3558737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"},"type":"article","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/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":true,"raw_author_name":"Zixiong Su","raw_affiliation_strings":["Rekimoto Lab, GSII, The University of Tokyo, Japan"],"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"],"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"],"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":3,"corresponding_author_ids":["https://openalex.org/A5009434654"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.4458,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59000506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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":0.996999979019165,"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":0.8156315088272095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7589613199234009},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5765345096588135},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47853145003318787},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4509425461292267},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3947809636592865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3749578595161438},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37447255849838257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156315088272095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7589613199234009},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5765345096588135},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47853145003318787},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4509425461292267},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3947809636592865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3749578595161438},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37447255849838257},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3526114.3558737","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3526114.3558737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adjunct Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2136155248","https://openalex.org/W2793257307","https://openalex.org/W2806172474","https://openalex.org/W2897318954","https://openalex.org/W2921295135","https://openalex.org/W2941048526","https://openalex.org/W3091762102","https://openalex.org/W3157582158","https://openalex.org/W3160833628"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351","https://openalex.org/W596245619"],"abstract_inverted_index":{"We":[0,90],"present":[1],"LipLearner,":[2,101],"a":[3,92],"lipreading-based":[4],"silent":[5,83],"speech":[6,49,84],"interface":[7],"that":[8,106],"enables":[9],"in-situ":[10],"command":[11,45],"customization":[12],"on":[13],"mobile":[14],"devices.":[15],"By":[16],"leveraging":[17],"contrastive":[18],"learning":[19],"to":[20,51,67,95],"learn":[21,53],"efficient":[22],"representations":[23],"from":[24,56],"existing":[25],"datasets,":[26],"it":[27],"performs":[28],"instant":[29],"fine-tuning":[30],"for":[31,118],"unseen":[32],"users":[33],"and":[34,71,102],"words":[35],"using":[36],"one-shot":[37],"learning.":[38],"To":[39],"further":[40],"minimize":[41],"the":[42,68,97,103],"labor":[43],"of":[44,74,100,110],"registration,":[46],"we":[47],"incorporate":[48],"recognition":[50],"automatically":[52],"new":[54],"commands":[55,65],"voice":[57],"input.":[58],"Conventional":[59],"lipreading":[60],"systems":[61],"provide":[62],"limited":[63],"pre-defined":[64],"due":[66],"time":[69],"cost":[70],"user":[72],"burden":[73],"data":[75,88],"collection.":[76],"In":[77],"contrast,":[78],"our":[79],"technique":[80],"provides":[81],"expressive":[82],"interaction":[85],"with":[86,113],"minimal":[87],"requirements.":[89],"conducted":[91],"pilot":[93],"experiment":[94],"investigate":[96],"real-time":[98],"performance":[99],"result":[104],"demonstrates":[105],"an":[107],"average":[108],"accuracy":[109],"is":[111],"achievable":[112],"only":[114],"one":[115],"training":[116],"sample":[117],"each":[119],"command.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}