{"id":"https://openalex.org/W4392903321","doi":"https://doi.org/10.1109/icassp48485.2024.10448473","title":"BRAVEn: Improving Self-supervised pre-training for Visual and Auditory Speech Recognition","display_name":"BRAVEn: Improving Self-supervised pre-training for Visual and Auditory Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903321","doi":"https://doi.org/10.1109/icassp48485.2024.10448473"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5010477883","display_name":"Alexandros Haliassos","orcid":"https://orcid.org/0000-0001-8856-5193"},"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":true,"raw_author_name":"Alexandros Haliassos","raw_affiliation_strings":["Imperial College London"],"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084220879","display_name":"Andreas Zinonos","orcid":null},"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":"Andreas Zinonos","raw_affiliation_strings":["Imperial College London"],"affiliations":[{"raw_affiliation_string":"Imperial College London","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":["Imperial College London"],"affiliations":[{"raw_affiliation_string":"Imperial College London","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/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":"Stavros Petridis","raw_affiliation_strings":["Imperial College London"],"affiliations":[{"raw_affiliation_string":"Imperial College London","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/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":["Imperial College London"],"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010477883"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":2.7642,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90766948,"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":"11431","last_page":"11435"},"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":0.9997000098228455,"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":0.9988999962806702,"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":0.8176016211509705},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6680566072463989},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5359073281288147},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5293204188346863},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5126677751541138},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49877500534057617},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4843691289424896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4836362600326538},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4761519432067871},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4610063433647156},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43698710203170776},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.436518132686615},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3936433792114258},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3337877690792084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176016211509705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6680566072463989},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5359073281288147},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5293204188346863},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5126677751541138},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49877500534057617},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4843691289424896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4836362600326538},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4761519432067871},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4610063433647156},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43698710203170776},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.436518132686615},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3936433792114258},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3337877690792084},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2194775991","https://openalex.org/W2331143823","https://openalex.org/W2502312327","https://openalex.org/W2808631503","https://openalex.org/W2891205112","https://openalex.org/W2963250244","https://openalex.org/W2963528589","https://openalex.org/W2972756321","https://openalex.org/W3006974783","https://openalex.org/W3015213852","https://openalex.org/W3015830103","https://openalex.org/W3162293946","https://openalex.org/W3197567540","https://openalex.org/W3203942572","https://openalex.org/W4289665794","https://openalex.org/W4297841719","https://openalex.org/W4307286264","https://openalex.org/W4312638101","https://openalex.org/W4372346152","https://openalex.org/W4376481237","https://openalex.org/W4385245566","https://openalex.org/W4386076364","https://openalex.org/W4391021811","https://openalex.org/W6724804524","https://openalex.org/W6754420807","https://openalex.org/W6757817989","https://openalex.org/W6780226713","https://openalex.org/W6794655914","https://openalex.org/W6810007534","https://openalex.org/W6810168380","https://openalex.org/W6839936984","https://openalex.org/W6847652939"],"related_works":["https://openalex.org/W1999699871","https://openalex.org/W2145230572","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2146197305","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2166312020","https://openalex.org/W2033669961","https://openalex.org/W3019226033"],"abstract_inverted_index":{"Self-supervision":[0],"has":[1],"recently":[2],"shown":[3],"great":[4],"promise":[5],"for":[6,82],"learning":[7],"visual":[8],"and":[9,98],"auditory":[10],"speech":[11,31],"representations":[12,32],"from":[13,34],"unlabelled":[14,65,109],"data.":[15,37,117],"In":[16,72],"this":[17],"work,":[18],"we":[19,55,74],"propose":[20],"BRAVEn,":[21],"an":[22],"extension":[23],"to":[24,40,44],"the":[25,62,87],"recent":[26],"RAVEn":[27,41],"method,":[28],"which":[29],"learns":[30],"entirely":[33],"raw":[35],"audio-visual":[36],"Our":[38,103],"modifications":[39],"enable":[42],"BRAVEn":[43],"achieve":[45,75],"state-of-the-art":[46],"results":[47,104],"among":[48],"self-supervised":[49,70],"methods":[50],"in":[51],"various":[52],"settings.":[53],"Moreover,":[54],"observe":[56],"favourable":[57],"scaling":[58],"behaviour":[59],"by":[60],"increasing":[61],"amount":[63],"of":[64,95],"data":[66,97,111],"well":[67],"beyond":[68],"other":[69],"works.":[71],"particular,":[73],"20.0%":[76],"/":[77,84],"1.7%":[78],"word":[79],"error":[80],"rate":[81],"VSR":[83],"ASR":[85,101],"on":[86],"LRS3":[88],"test":[89],"set,":[90],"with":[91],"only":[92],"30":[93],"hours":[94],"labelled":[96],"no":[99],"external":[100],"models.":[102],"suggest":[105],"that":[106],"readily":[107],"available":[108],"audiovisual":[110],"can":[112],"largely":[113],"replace":[114],"costly":[115],"transcribed":[116],"Code":[118],"at":[119],"https://github.com/ahaliassos/raven.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}