{"id":"https://openalex.org/W2990159822","doi":"https://doi.org/10.1109/icassp40776.2020.9054253","title":"ASR is All You Need: Cross-Modal Distillation for Lip Reading","display_name":"ASR is All You Need: Cross-Modal Distillation for Lip Reading","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2990159822","doi":"https://doi.org/10.1109/icassp40776.2020.9054253","mag":"2990159822"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.12747","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018690028","display_name":"Triantafyllos Afouras","orcid":"https://orcid.org/0000-0002-3935-9681"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Triantafyllos Afouras","raw_affiliation_strings":["Visual Geometry Group, University of Oxford","University of Oxford,Visual Geometry Group"],"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Visual Geometry Group, University of Oxford","University of Oxford,Visual Geometry Group"],"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["Visual Geometry Group, University of Oxford","University of Oxford,Visual Geometry Group"],"affiliations":[{"raw_affiliation_string":"Visual Geometry Group, University of Oxford","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"University of Oxford,Visual Geometry Group","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018690028"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":1.5227,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82416863,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2143","last_page":"2147"},"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":0.9957000017166138,"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":0.9947999715805054,"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":0.7870126962661743},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.7410910725593567},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6867047548294067},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5924330949783325},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5671424269676208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5176625847816467},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4757244884967804},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45771992206573486},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.4541747272014618},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43960967659950256},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.43838387727737427},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33436232805252075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3231487274169922}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870126962661743},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.7410910725593567},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6867047548294067},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5924330949783325},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5671424269676208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5176625847816467},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4757244884967804},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45771992206573486},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4541747272014618},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43960967659950256},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.43838387727737427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33436232805252075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3231487274169922},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.12747","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.12747","pdf_url":"https://arxiv.org/pdf/1911.12747","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2990159822","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.12747v1","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.12747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.12747","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/44ye-e192","is_oa":true,"landing_page_url":"https://doi.org/10.17023/44ye-e192","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.12747","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.12747","pdf_url":"https://arxiv.org/pdf/1911.12747","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G1277543710","display_name":null,"funder_award_id":"EP/M013774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2990159822.pdf","grobid_xml":"https://content.openalex.org/works/W2990159822.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W753847829","https://openalex.org/W1494198834","https://openalex.org/W1821462560","https://openalex.org/W2127141656","https://openalex.org/W2134797427","https://openalex.org/W2291513470","https://openalex.org/W2293858598","https://openalex.org/W2550980560","https://openalex.org/W2551572271","https://openalex.org/W2578229578","https://openalex.org/W2594690981","https://openalex.org/W2767487732","https://openalex.org/W2782717521","https://openalex.org/W2799062425","https://openalex.org/W2808631503","https://openalex.org/W2883383043","https://openalex.org/W2886300652","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2901739041","https://openalex.org/W2936993002","https://openalex.org/W2938974662","https://openalex.org/W2952746495","https://openalex.org/W2962756039","https://openalex.org/W2963240019","https://openalex.org/W2963528589","https://openalex.org/W2963736842","https://openalex.org/W2963785710","https://openalex.org/W2964283370","https://openalex.org/W2972582323","https://openalex.org/W2972756321","https://openalex.org/W2972775954","https://openalex.org/W2973040747","https://openalex.org/W2973215447","https://openalex.org/W2981501041","https://openalex.org/W3006974783","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6629717138","https://openalex.org/W6638523607","https://openalex.org/W6679909955","https://openalex.org/W6696750753","https://openalex.org/W6712847557","https://openalex.org/W6729540071","https://openalex.org/W6729831399","https://openalex.org/W6734491695","https://openalex.org/W6747270024","https://openalex.org/W6747603840","https://openalex.org/W6754420807","https://openalex.org/W6755201655"],"related_works":["https://openalex.org/W3207460178","https://openalex.org/W3201101490","https://openalex.org/W3139663406","https://openalex.org/W3130251849","https://openalex.org/W3107298252","https://openalex.org/W2294962864","https://openalex.org/W3175220386","https://openalex.org/W2558625589","https://openalex.org/W2950548836","https://openalex.org/W3094947935","https://openalex.org/W3148906368","https://openalex.org/W2913851961","https://openalex.org/W3193714551","https://openalex.org/W3131813758","https://openalex.org/W3148101939","https://openalex.org/W3155427814","https://openalex.org/W2251047611","https://openalex.org/W3214697273","https://openalex.org/W3046609253","https://openalex.org/W2940322076"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,85],"this":[3,23],"work":[4],"is":[5],"to":[6,73,92],"train":[7,74],"strong":[8],"models":[9],"for":[10,117],"visual":[11],"speech":[12],"recognition":[13],"without":[14],"requiring":[15],"human":[16],"annotated":[17],"ground":[18,67],"truth":[19,68],"data.":[20,123],"We":[21,42],"achieve":[22],"by":[24],"distilling":[25],"from":[26],"an":[27],"Automatic":[28],"Speech":[29],"Recognition":[30],"(ASR)":[31],"model":[32],"that":[33,48,66,98],"has":[34],"been":[35],"trained":[36],"on":[37,110,120],"a":[38,44,55,75],"large-scale":[39],"audio-only":[40],"corpus.":[41],"use":[43],"cross-modal":[45],"distillation":[46,99],"method":[47],"combines":[49],"Connectionist":[50],"Temporal":[51],"Classification":[52],"(CTC)":[53],"with":[54],"frame-wise":[56],"cross-entropy":[57],"loss.":[58],"Our":[59],"contributions":[60],"are":[61,70],"fourfold:":[62],"(i)":[63],"we":[64,80,96,106],"show":[65,81],"transcriptions":[69],"not":[71],"necessary":[72],"lip":[76],"reading":[77],"system;":[78],"(ii)":[79],"how":[82],"arbitrary":[83],"amounts":[84],"unlabelled":[86],"video":[87],"data":[88],"can":[89],"be":[90],"leveraged":[91],"improve":[93],"performance;":[94],"(iii)":[95],"demonstrate":[97],"significantly":[100],"speeds":[101],"up":[102],"training;":[103],"and,":[104],"(iv)":[105],"obtain":[107],"state-of-the-art":[108],"results":[109],"the":[111],"challenging":[112],"LRS2":[113],"and":[114],"LRS3":[115],"datasets":[116],"training":[118],"only":[119],"publicly":[121],"available":[122]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}