{"id":"https://openalex.org/W4391021811","doi":"https://doi.org/10.1109/asru57964.2023.10389642","title":"Av-Data2Vec: Self-Supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","display_name":"Av-Data2Vec: Self-Supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021811","doi":"https://doi.org/10.1109/asru57964.2023.10389642"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5108846913","display_name":"Jiachen Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiachen Lian","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031979802","display_name":"Alexei Baevski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124113","display_name":"Character","ror":"https://ror.org/02pj41y46","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210124113"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexei Baevski","raw_affiliation_strings":["Character.AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Character.AI","institution_ids":["https://openalex.org/I4210124113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Auli","raw_affiliation_strings":["FAIR, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR, Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9994999766349792,"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":0.9986000061035156,"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":0.8195589184761047},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7718178033828735},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6626589298248291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6440176367759705},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6340570449829102},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5935285091400146},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.47639408707618713},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.46461546421051025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4612729549407959},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.42049989104270935},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.4136163890361786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3983739912509918},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3409584164619446},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2813641428947449},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2634587287902832},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.23744934797286987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8195589184761047},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7718178033828735},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6626589298248291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6440176367759705},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6340570449829102},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5935285091400146},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.47639408707618713},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.46461546421051025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4612729549407959},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.42049989104270935},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.4136163890361786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3983739912509918},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3409584164619446},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2813641428947449},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2634587287902832},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.23744934797286987},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1677182931","https://openalex.org/W2115252128","https://openalex.org/W2194775991","https://openalex.org/W2212242068","https://openalex.org/W2752796333","https://openalex.org/W2766219058","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2933138175","https://openalex.org/W2962826786","https://openalex.org/W2963785710","https://openalex.org/W2963799213","https://openalex.org/W2963979492","https://openalex.org/W2972756321","https://openalex.org/W2988736778","https://openalex.org/W3006974783","https://openalex.org/W3015265920","https://openalex.org/W3015830103","https://openalex.org/W3016011332","https://openalex.org/W3035042697","https://openalex.org/W3036601975","https://openalex.org/W3097286738","https://openalex.org/W3196919915","https://openalex.org/W3198858531","https://openalex.org/W3199527474","https://openalex.org/W3203711169","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4213171936","https://openalex.org/W4223430326","https://openalex.org/W4285595742","https://openalex.org/W4297841641","https://openalex.org/W4297841719","https://openalex.org/W4307286264","https://openalex.org/W4312638101","https://openalex.org/W4321428117","https://openalex.org/W4372260274","https://openalex.org/W4372340876","https://openalex.org/W4376481237","https://openalex.org/W4385823207","https://openalex.org/W6677618333","https://openalex.org/W6754420807","https://openalex.org/W6770514103","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6810168380","https://openalex.org/W6839936984","https://openalex.org/W6846807982","https://openalex.org/W6847652939"],"related_works":["https://openalex.org/W4389505417","https://openalex.org/W2962931510","https://openalex.org/W4380551887","https://openalex.org/W2904518532","https://openalex.org/W4285159263","https://openalex.org/W4280529741","https://openalex.org/W4293919860","https://openalex.org/W2963650472","https://openalex.org/W2556013083","https://openalex.org/W3199271201"],"abstract_inverted_index":{"Self-supervision":[0],"has":[1,59],"shown":[2],"great":[3],"potential":[4],"for":[5,73],"audio-visual":[6,51],"speech":[7,85],"recognition":[8],"by":[9],"vastly":[10],"reducing":[11],"the":[12,63,101],"amount":[13,103],"of":[14,36,104],"labeled":[15],"data":[16,105],"required":[17],"to":[18,83],"build":[19],"good":[20],"systems.":[21],"However,":[22],"existing":[23,95],"methods":[24,96],"are":[25],"either":[26],"not":[27,32],"entirely":[28],"end-to-end":[29],"or":[30],"do":[31],"train":[33],"joint":[34],"representations":[35,52,57],"both":[37,74,81],"modalities.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"introduce":[43],"AV-data2vec":[44,92],"which":[45,58],"addresses":[46],"these":[47],"challenges":[48],"and":[49,76,78,106],"builds":[50],"based":[53],"on":[54,88],"predicting":[55],"contextualized":[56],"been":[60],"successful":[61],"in":[62],"uni-modal":[64],"case.":[65],"The":[66],"model":[67,107],"uses":[68],"a":[69],"shared":[70],"transformer":[71],"encoder":[72],"audio":[75],"video":[77],"can":[79],"combine":[80],"modalities":[82],"improve":[84],"recognition.":[86],"Results":[87],"LRS3":[89],"show":[90],"that":[91],"consistently":[93],"outperforms":[94],"under":[97],"all":[98],"settings":[99],"with":[100],"same":[102],"size.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}