{"id":"https://openalex.org/W4285124867","doi":"https://doi.org/10.1109/taslp.2022.3182274","title":"End-to-End Lip-Reading Without Large-Scale Data","display_name":"End-to-End Lip-Reading Without Large-Scale Data","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285124867","doi":"https://doi.org/10.1109/taslp.2022.3182274"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3182274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3182274","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5079540599","display_name":"Adriana Fernandez-Lopez","orcid":"https://orcid.org/0000-0001-8839-6537"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Adriana Fernandez-Lopez","raw_affiliation_strings":["Department of Information and Comunication Technologies, Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Information and Comunication Technologies, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019420087","display_name":"Federico M. Sukno","orcid":"https://orcid.org/0000-0002-2029-1576"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Federico M. Sukno","raw_affiliation_strings":["Department of Information and Comunication Technologies, Universitat Pompeu Fabra, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Department of Information and Comunication Technologies, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079540599"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":2.3774,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88732513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"2076","last_page":"2090"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958000183105469,"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":0.719497799873352},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5961558222770691},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5724935531616211},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.571325421333313},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5692784190177917},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5510809421539307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4858419597148895},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4767918586730957},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.46887898445129395},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41424891352653503},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4117531180381775},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4018971025943756},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15069648623466492},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.11883950233459473},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09021109342575073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08095288276672363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719497799873352},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5961558222770691},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5724935531616211},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.571325421333313},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5692784190177917},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5510809421539307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4858419597148895},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4767918586730957},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.46887898445129395},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41424891352653503},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4117531180381775},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4018971025943756},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15069648623466492},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.11883950233459473},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09021109342575073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08095288276672363},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3182274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3182274","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8799999952316284}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W242871668","https://openalex.org/W1902237438","https://openalex.org/W1982656606","https://openalex.org/W2029199293","https://openalex.org/W2071096833","https://openalex.org/W2094829487","https://openalex.org/W2149197198","https://openalex.org/W2157285372","https://openalex.org/W2398406965","https://openalex.org/W2403559635","https://openalex.org/W2551572271","https://openalex.org/W2604379605","https://openalex.org/W2604769302","https://openalex.org/W2605246626","https://openalex.org/W2802223794","https://openalex.org/W2806872492","https://openalex.org/W2883725317","https://openalex.org/W2886945201","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2963173190","https://openalex.org/W2963192365","https://openalex.org/W2963240019","https://openalex.org/W2963744813","https://openalex.org/W2963775347","https://openalex.org/W2964251418","https://openalex.org/W2964283370","https://openalex.org/W2972756321","https://openalex.org/W2980100386","https://openalex.org/W2987952236","https://openalex.org/W3003241499","https://openalex.org/W3006974783","https://openalex.org/W3007589762","https://openalex.org/W3011234510","https://openalex.org/W3015301228","https://openalex.org/W3015383493","https://openalex.org/W3023351797","https://openalex.org/W3036224891","https://openalex.org/W3102469722","https://openalex.org/W3106423890","https://openalex.org/W3162293946","https://openalex.org/W3209059054","https://openalex.org/W4292779060","https://openalex.org/W6621543089","https://openalex.org/W6750475725","https://openalex.org/W6770196601","https://openalex.org/W6778883912","https://openalex.org/W6779997284","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2504004674","https://openalex.org/W1987679298","https://openalex.org/W2963177394","https://openalex.org/W4396816926","https://openalex.org/W2593532750","https://openalex.org/W2110442089","https://openalex.org/W2642467014","https://openalex.org/W2889523925"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,68,105,145,155,206,230],"Automatic":[3],"Lip-Reading":[4],"(ALR)":[5],"systems":[6,48],"for":[7,171,227],"continuous":[8],"speech":[9],"recognition":[10],"has":[11],"so":[12],"far":[13],"limited":[14],"their":[15],"applicability":[16],"to":[17,29,43,64,91,117,129,158],"English":[18],"since":[19],"this":[20,35,74,228],"is":[21,41,204],"the":[22,59,65,69,79,136,153,173,191,197,207,223,234],"only":[23],"language":[24],"with":[25,52,222],"large-scale":[26],"datasets":[27],"sufficient":[28],"train":[30,44,159],"end-to-end":[31,46,161],"ALR":[32,47,162,193],"systems.":[33],"In":[34],"work,":[36],"we":[37,76,165,244],"show":[38,122],"that":[39,78,123,141,203],"it":[40,90],"possible":[42],"competitive":[45,221],"in":[49,85,209,241],"alternative":[50],"languages":[51],"challenging":[53],"small-scale":[54,201],"data":[55,156,168],"as":[56,58,102,149],"long":[57],"appropriate":[60],"restrictions":[61],"are":[62,220,252],"made":[63],"learning":[66,144],"process":[67],"visual":[70,80,137,146],"front-end":[71,81],"objective.":[72],"To":[73],"end,":[75],"hypothesize":[77],"should":[82],"be":[83,127],"trained":[84],"a":[86,103,150,167,200,237],"self-supervised":[87],"setting,":[88],"allowing":[89],"target":[92],"its":[93],"own":[94],"<i>visual":[95,100,124],"units</i>.":[96],"We":[97,121,176,189],"specifically":[98],"define":[99],"units</i>":[101,125],"collection":[104],"visually":[106],"similar":[107],"images":[108],"constrained":[109],"by":[110,181],"linguistics":[111],"and":[112,138,211,216,225,248],"provide":[113],"an":[114,131,160],"algorithmic":[115],"implementation":[116],"automatically":[118],"generate":[119],"them.":[120],"can":[126],"used":[128],"add":[130],"intermediate":[132],"classification":[133],"task":[134],"between":[135],"temporal":[139,174],"modules":[140],"facilitates":[142],"meaningful":[143],"features":[147],"and,":[148],"consequence,":[151],"reduces":[152],"amount":[154],"required":[157],"system.":[163],"Additionally,":[164],"present":[166],"augmentation":[169],"strategy":[170],"enriching":[172],"context.":[175],"synthesize":[177],"realistic":[178],"video":[179],"sequences":[180],"appropriately":[182],"combining":[183],"characters-like":[184],"sub-sequences":[185],"from":[186],"existing":[187],"videos.":[188],"test":[190],"proposed":[192],"system":[194],"on":[195,256],"i)":[196],"VLRF":[198],"dataset,":[199,236],"database":[202,240],"one":[205],"largest":[208],"Spanish,":[210],"achieve":[212,245],"44.77<inline-formula><tex-math":[213],"notation=\"LaTeX\">$\\%$</tex-math></inline-formula>":[214],"CER":[215,247],"72.90%":[217],"WER,":[218,250],"which":[219,251],"state-of-the-art":[224,254],"significant":[226],"volume":[229],"training":[231],"material;":[232],"ii)":[233],"TCD-TIMIT":[235],"comparable":[238],"medium-scale":[239],"English,":[242],"where":[243],"36.58%":[246],"56.29%":[249],"also":[253],"results":[255],"speaker-dependent":[257],"experiments.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}