{"id":"https://openalex.org/W4372266842","doi":"https://doi.org/10.1109/icassp49357.2023.10094585","title":"Learning Cross-Lingual Visual Speech Representations","display_name":"Learning Cross-Lingual Visual Speech Representations","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266842","doi":"https://doi.org/10.1109/icassp49357.2023.10094585"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/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":true,"raw_author_name":"Andreas Zinonos","raw_affiliation_strings":["Imperial College London,Department of Computing,UK","Department of Computing, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","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":false,"raw_author_name":"Alexandros Haliassos","raw_affiliation_strings":["Imperial College London,Department of Computing,UK","Department of Computing, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","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":["Imperial College London,Department of Computing,UK","Department of Computing, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, 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/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,Department of Computing,UK","Department of Computing, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, 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/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,Department of Computing,UK","Department of Computing, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5084220879"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":1.2405,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78766463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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":0.9950000047683716,"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":0.8142045140266418},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6113405227661133},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5846521854400635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.575724720954895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5743807554244995},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5534784197807312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5363702774047852},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5070791244506836},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4627326726913452},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4409525692462921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8142045140266418},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6113405227661133},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5846521854400635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.575724720954895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5743807554244995},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5534784197807312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5363702774047852},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5070791244506836},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4627326726913452},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4409525692462921},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1978660892","https://openalex.org/W2123798005","https://openalex.org/W2194775991","https://openalex.org/W2766219058","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2952746495","https://openalex.org/W2962893195","https://openalex.org/W2963250244","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2971840980","https://openalex.org/W2979476256","https://openalex.org/W2988736778","https://openalex.org/W2999528291","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3097777922","https://openalex.org/W3139878283","https://openalex.org/W3162061711","https://openalex.org/W3162293946","https://openalex.org/W3197567540","https://openalex.org/W3197771105","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4221153068","https://openalex.org/W4287824654","https://openalex.org/W4289665794","https://openalex.org/W4307286264","https://openalex.org/W4311553423","https://openalex.org/W4312472072","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6769196770","https://openalex.org/W6770514103","https://openalex.org/W6771917389","https://openalex.org/W6779326418","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2119949815","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W2379948177","https://openalex.org/W2107949441"],"abstract_inverted_index":{"Cross-lingual":[0],"self-supervised":[1,33],"learning":[2],"has":[3],"been":[4],"a":[5],"growing":[6],"research":[7,131],"topic":[8],"in":[9,121],"the":[10,19,39,59,81,118,122],"last":[11],"few":[12],"years.":[13],"However,":[14],"current":[15],"works":[16],"only":[17],"explored":[18],"use":[20,38],"of":[21,83],"audio":[22],"signals":[23],"to":[24,47,89,116],"create":[25],"representations.":[26],"In":[27],"this":[28],"work,":[29],"we":[30],"study":[31,128],"cross-lingual":[32],"visual":[34,60],"representation":[35,135],"learning.":[36,136],"We":[37,125],"recently-proposed":[40],"Raw":[41],"Audio-Visual":[42],"Speech":[43],"Encoders":[44],"(RAVEn)":[45],"framework":[46],"pre-train":[48],"an":[49],"audio-visual":[50],"model":[51,61],"with":[52,72],"unlabelled":[53],"multilingual":[54],"data,":[55],"and":[56,108],"then":[57],"fine-tune":[58],"on":[62,111,132],"labelled":[63],"transcriptions.":[64],"Our":[65],"experiments":[66],"show":[67],"that:":[68],"(1)":[69],"multi-lingual":[70,94],"models":[71,87],"more":[73,103],"data":[74,84],"outperform":[75],"monolingual":[76,86],"ones,":[77],"but,":[78],"when":[79],"keeping":[80],"amount":[82],"fixed,":[85],"tend":[88],"reach":[90],"better":[91,106],"performance;":[92],"(2)":[93],"outperforms":[95],"English-only":[96],"pre-training;":[97],"(3)":[98],"using":[99,117],"languages":[100,113],"which":[101],"are":[102],"similar":[104],"yields":[105],"results;":[107],"(4)":[109],"fine-tuning":[110],"unseen":[112],"is":[114],"competitive":[115],"target":[119],"language":[120],"pre-training":[123],"set.":[124],"hope":[126],"our":[127],"inspires":[129],"future":[130],"non-English-only":[133],"speech":[134]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}