{"id":"https://openalex.org/W3197567540","doi":"https://doi.org/10.21437/interspeech.2021-1360","title":"LiRA: Learning Visual Speech Representations from Audio Through Self-Supervision","display_name":"LiRA: Learning Visual Speech Representations from Audio Through Self-Supervision","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197567540","doi":"https://doi.org/10.21437/interspeech.2021-1360","mag":"3197567540"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1360","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1360","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":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91586/91586.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["iBUG Group, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iBUG Group, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013092421","display_name":"Rodrigo Mira","orcid":"https://orcid.org/0000-0002-9493-3842"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rodrigo Mira","raw_affiliation_strings":["iBUG Group, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iBUG Group, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Facebook London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook London, UK","institution_ids":["https://openalex.org/I4210111288"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","iBUG Group, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"iBUG Group, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Facebook London, UK","iBUG Group, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook London, UK","institution_ids":["https://openalex.org/I4210111288"]},{"raw_affiliation_string":"iBUG Group, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9803,"has_fulltext":true,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97817981,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3011","last_page":"3015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9172999858856201,"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":0.9129999876022339,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.8013435006141663},{"id":"https://openalex.org/keywords/lira","display_name":"Lira","score":0.6961709856987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6650713682174683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6156876087188721},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3695716857910156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3459016978740692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3342909812927246}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.8013435006141663},{"id":"https://openalex.org/C2777163752","wikidata":"https://www.wikidata.org/wiki/Q6557574","display_name":"Lira","level":3,"score":0.6961709856987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6650713682174683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6156876087188721},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3695716857910156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3459016978740692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3342909812927246},{"id":"https://openalex.org/C2776988154","wikidata":"https://www.wikidata.org/wiki/Q66100","display_name":"Exchange rate","level":2,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-1360","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1360","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"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:91586","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/91586","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91586/91586.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:91586","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/91586","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/91586/91586.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197567540.pdf","grobid_xml":"https://content.openalex.org/works/W3197567540.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2115252128","https://openalex.org/W2138862063","https://openalex.org/W2261706002","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2890052321","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2898926657","https://openalex.org/W2908510526","https://openalex.org/W2913939497","https://openalex.org/W2947883281","https://openalex.org/W2962931510","https://openalex.org/W2962960500","https://openalex.org/W2962969419","https://openalex.org/W2963528589","https://openalex.org/W2963785710","https://openalex.org/W2964110616","https://openalex.org/W2972894903","https://openalex.org/W2972977747","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2981501041","https://openalex.org/W2990408345","https://openalex.org/W3006974783","https://openalex.org/W3015213852","https://openalex.org/W3015383493","https://openalex.org/W3015830103","https://openalex.org/W3016011581","https://openalex.org/W3016663370","https://openalex.org/W3022984097","https://openalex.org/W3023351797","https://openalex.org/W3035118106","https://openalex.org/W3097777922","https://openalex.org/W3119418740","https://openalex.org/W3162293946","https://openalex.org/W3162707322","https://openalex.org/W3163060364","https://openalex.org/W4297808394","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2355862304","https://openalex.org/W2356108042","https://openalex.org/W2030250808","https://openalex.org/W2376796979","https://openalex.org/W2379418341","https://openalex.org/W2380054981","https://openalex.org/W2393110101","https://openalex.org/W2379285345","https://openalex.org/W2789919619","https://openalex.org/W2293457016"],"abstract_inverted_index":{"The":[0],"large":[1],"amount":[2],"of":[3,17,26,138],"audiovisual":[4,18],"content":[5],"being":[6],"shared":[7],"online":[8],"today":[9],"has":[10,45],"drawn":[11],"substantial":[12],"attention":[13,44],"to":[14,34,48,56,79],"the":[15,59,116,120,139],"prospect":[16],"self-supervised":[19,113],"learning.Recent":[20],"works":[21],"have":[22,32],"focused":[23],"on":[24,115,128],"each":[25],"these":[27],"modalities":[28],"separately,":[29],"while":[30],"others":[31],"attempted":[33],"model":[35,78,91],"both":[36],"simultaneously":[37],"in":[38,119],"a":[39,53,76,136],"cross-modal":[40],"fashion.However,":[41],"comparatively":[42],"little":[43],"been":[46],"given":[47],"leveraging":[49],"one":[50],"modality":[51],"as":[52],"training":[54],"objective":[55],"learn":[57],"from":[58,69,83],"other.In":[60],"this":[61,89],"work,":[62],"we":[63,74],"propose":[64],"Learning":[65],"visual":[66,85],"speech":[67],"Representations":[68],"Audio":[70],"via":[71],"self-supervision":[72],"(LiRA).Specifically,":[73],"train":[75],"ResNet+Conformer":[77],"predict":[80],"acoustic":[81],"features":[82],"unlabelled":[84],"speech.We":[86],"find":[87],"that":[88,107],"pre-trained":[90],"can":[92],"be":[93],"leveraged":[94],"towards":[95],"word-level":[96],"and":[97,103,124],"sentence-level":[98],"lip-reading":[99],"through":[100],"feature":[101],"extraction":[102],"fine-tuning":[104],"experiments.We":[105],"show":[106],"our":[108],"approach":[109],"significantly":[110],"outperforms":[111],"other":[112],"methods":[114],"Lip":[117,129],"Reading":[118,130],"Wild":[121],"(LRW)":[122],"dataset":[123],"achieves":[125],"state-of-the-art":[126],"performance":[127],"Sentences":[131],"2":[132],"(LRS2)":[133],"using":[134],"only":[135],"fraction":[137],"total":[140],"labelled":[141],"data.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":7}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}